voice-router-dev 0.8.2 → 0.8.4
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +252 -0
- package/dist/constants.d.mts +40 -11
- package/dist/constants.d.ts +40 -11
- package/dist/constants.js +18 -9
- package/dist/constants.mjs +17 -9
- package/dist/{field-configs-DN2_WrYr.d.mts → field-configs-DLbrsYTk.d.mts} +4485 -3300
- package/dist/{field-configs-DN2_WrYr.d.ts → field-configs-DLbrsYTk.d.ts} +4485 -3300
- package/dist/field-configs.d.mts +1 -1
- package/dist/field-configs.d.ts +1 -1
- package/dist/field-configs.js +2333 -1642
- package/dist/field-configs.mjs +2333 -1642
- package/dist/index.d.mts +1179 -2621
- package/dist/index.d.ts +1179 -2621
- package/dist/index.js +2276 -1580
- package/dist/index.mjs +2273 -1579
- package/dist/{provider-metadata-BnkedpXm.d.mts → provider-metadata-MDUUEuqF.d.mts} +4 -4
- package/dist/{provider-metadata-DbsSGAO7.d.ts → provider-metadata-_gUWlRXS.d.ts} +4 -4
- package/dist/provider-metadata.d.mts +1 -1
- package/dist/provider-metadata.d.ts +1 -1
- package/dist/{speechToTextChunkResponseModel-3IUnJXKx.d.mts → speechToTextChunkResponseModel-BcT1LJSZ.d.mts} +2810 -1209
- package/dist/{speechToTextChunkResponseModel-DExUFZT3.d.ts → speechToTextChunkResponseModel-eq8eLKEA.d.ts} +2810 -1209
- package/dist/webhooks.d.mts +242 -217
- package/dist/webhooks.d.ts +242 -217
- package/package.json +5 -5
package/dist/index.mjs
CHANGED
|
@@ -2252,13 +2252,6 @@ var TranslationLanguageCodeEnum = {
|
|
|
2252
2252
|
zh: "zh"
|
|
2253
2253
|
};
|
|
2254
2254
|
|
|
2255
|
-
// src/generated/assemblyai/schema/speechModel.ts
|
|
2256
|
-
var SpeechModel = {
|
|
2257
|
-
best: "best",
|
|
2258
|
-
"slam-1": "slam-1",
|
|
2259
|
-
universal: "universal"
|
|
2260
|
-
};
|
|
2261
|
-
|
|
2262
2255
|
// src/generated/assemblyai/schema/transcriptLanguageCode.ts
|
|
2263
2256
|
var TranscriptLanguageCode = {
|
|
2264
2257
|
en: "en",
|
|
@@ -2574,7 +2567,10 @@ var AssemblyAIEncoding = {
|
|
|
2574
2567
|
/** μ-law (telephony) */
|
|
2575
2568
|
pcmMulaw: "pcm_mulaw"
|
|
2576
2569
|
};
|
|
2577
|
-
var AssemblyAITranscriptionModel =
|
|
2570
|
+
var AssemblyAITranscriptionModel = {
|
|
2571
|
+
"universal-3-pro": "universal-3-pro",
|
|
2572
|
+
"universal-2": "universal-2"
|
|
2573
|
+
};
|
|
2578
2574
|
var AssemblyAILanguage = TranscriptLanguageCode;
|
|
2579
2575
|
var AssemblyAISpeechModel = {
|
|
2580
2576
|
/** Optimized for English */
|
|
@@ -2695,6 +2691,12 @@ var ERROR_CODES = {
|
|
|
2695
2691
|
CONNECTION_TIMEOUT: "CONNECTION_TIMEOUT",
|
|
2696
2692
|
/** Invalid input provided to API */
|
|
2697
2693
|
INVALID_INPUT: "INVALID_INPUT",
|
|
2694
|
+
/** Authentication failed (invalid or missing API key) */
|
|
2695
|
+
AUTHENTICATION_ERROR: "AUTHENTICATION_ERROR",
|
|
2696
|
+
/** Rate limit exceeded */
|
|
2697
|
+
RATE_LIMIT: "RATE_LIMIT",
|
|
2698
|
+
/** Provider server error (5xx) */
|
|
2699
|
+
SERVER_ERROR: "SERVER_ERROR",
|
|
2698
2700
|
/** Requested operation not supported by provider */
|
|
2699
2701
|
NOT_SUPPORTED: "NOT_SUPPORTED",
|
|
2700
2702
|
/** No transcription results available */
|
|
@@ -2709,6 +2711,9 @@ var ERROR_MESSAGES = {
|
|
|
2709
2711
|
TRANSCRIPTION_ERROR: "Transcription processing failed",
|
|
2710
2712
|
CONNECTION_TIMEOUT: "Connection attempt timed out",
|
|
2711
2713
|
INVALID_INPUT: "Invalid input provided",
|
|
2714
|
+
AUTHENTICATION_ERROR: "Authentication failed (invalid or missing API key)",
|
|
2715
|
+
RATE_LIMIT: "Rate limit exceeded",
|
|
2716
|
+
SERVER_ERROR: "Provider server error",
|
|
2712
2717
|
NOT_SUPPORTED: "Operation not supported by this provider",
|
|
2713
2718
|
NO_RESULTS: "No transcription results available",
|
|
2714
2719
|
UNKNOWN_ERROR: "An unknown error occurred"
|
|
@@ -2720,6 +2725,36 @@ function createError(code, customMessage, details) {
|
|
|
2720
2725
|
details
|
|
2721
2726
|
};
|
|
2722
2727
|
}
|
|
2728
|
+
function httpStatusToErrorCode(status) {
|
|
2729
|
+
switch (status) {
|
|
2730
|
+
case 400:
|
|
2731
|
+
case 404:
|
|
2732
|
+
case 422:
|
|
2733
|
+
return ERROR_CODES.INVALID_INPUT;
|
|
2734
|
+
case 401:
|
|
2735
|
+
case 403:
|
|
2736
|
+
return ERROR_CODES.AUTHENTICATION_ERROR;
|
|
2737
|
+
case 408:
|
|
2738
|
+
return ERROR_CODES.CONNECTION_TIMEOUT;
|
|
2739
|
+
case 429:
|
|
2740
|
+
return ERROR_CODES.RATE_LIMIT;
|
|
2741
|
+
default:
|
|
2742
|
+
if (status >= 500) return ERROR_CODES.SERVER_ERROR;
|
|
2743
|
+
return ERROR_CODES.UNKNOWN_ERROR;
|
|
2744
|
+
}
|
|
2745
|
+
}
|
|
2746
|
+
function extractProviderMessage(data) {
|
|
2747
|
+
if (!data || typeof data !== "object") {
|
|
2748
|
+
return typeof data === "string" ? data : void 0;
|
|
2749
|
+
}
|
|
2750
|
+
const d = data;
|
|
2751
|
+
if (d.error && typeof d.error === "object" && d.error.message) return String(d.error.message);
|
|
2752
|
+
if (typeof d.error === "string") return d.error;
|
|
2753
|
+
if (d.detail && typeof d.detail === "object" && d.detail.message) return String(d.detail.message);
|
|
2754
|
+
if (typeof d.message === "string") return d.message;
|
|
2755
|
+
if (typeof d.err_msg === "string") return d.err_msg;
|
|
2756
|
+
return void 0;
|
|
2757
|
+
}
|
|
2723
2758
|
|
|
2724
2759
|
// src/adapters/base-adapter.ts
|
|
2725
2760
|
var BaseAdapter = class {
|
|
@@ -2738,12 +2773,15 @@ var BaseAdapter = class {
|
|
|
2738
2773
|
const httpStatus = statusCode || err.statusCode || err.response?.status;
|
|
2739
2774
|
const httpStatusText = err.response?.statusText;
|
|
2740
2775
|
const responseData = err.response?.data;
|
|
2776
|
+
const errorCode = code || (httpStatus ? httpStatusToErrorCode(httpStatus) : void 0) || ERROR_CODES.UNKNOWN_ERROR;
|
|
2777
|
+
const providerMessage = extractProviderMessage(responseData);
|
|
2778
|
+
const message = providerMessage || err.message || "An unknown error occurred";
|
|
2741
2779
|
return {
|
|
2742
2780
|
success: false,
|
|
2743
2781
|
provider: this.name,
|
|
2744
2782
|
error: {
|
|
2745
|
-
code:
|
|
2746
|
-
message
|
|
2783
|
+
code: errorCode,
|
|
2784
|
+
message,
|
|
2747
2785
|
statusCode: httpStatus,
|
|
2748
2786
|
details: {
|
|
2749
2787
|
// Include full error object
|
|
@@ -5157,19 +5195,20 @@ var schema_exports2 = {};
|
|
|
5157
5195
|
__export(schema_exports2, {
|
|
5158
5196
|
AudioIntelligenceModelStatus: () => AudioIntelligenceModelStatus,
|
|
5159
5197
|
EntityType: () => EntityType,
|
|
5160
|
-
LemurModel: () => LemurModel,
|
|
5161
5198
|
PiiPolicy: () => PiiPolicy,
|
|
5162
5199
|
RedactPiiAudioQuality: () => RedactPiiAudioQuality,
|
|
5163
5200
|
RedactedAudioStatus: () => RedactedAudioStatus,
|
|
5164
5201
|
Sentiment: () => Sentiment,
|
|
5165
|
-
|
|
5202
|
+
SpeakerIdentificationRequestBodySpeakerIdentificationSpeakerType: () => SpeakerIdentificationRequestBodySpeakerIdentificationSpeakerType,
|
|
5166
5203
|
SubstitutionPolicy: () => SubstitutionPolicy,
|
|
5167
5204
|
SubtitleFormat: () => SubtitleFormat,
|
|
5168
5205
|
SummaryModel: () => SummaryModel,
|
|
5169
5206
|
SummaryType: () => SummaryType,
|
|
5170
|
-
TranscriptBoostParam: () => TranscriptBoostParam,
|
|
5171
5207
|
TranscriptLanguageCode: () => TranscriptLanguageCode,
|
|
5172
|
-
|
|
5208
|
+
TranscriptOptionalParamsRedactPiiAudioOptionsOverrideAudioRedactionMethod: () => TranscriptOptionalParamsRedactPiiAudioOptionsOverrideAudioRedactionMethod,
|
|
5209
|
+
TranscriptOptionalParamsRemoveAudioTags: () => TranscriptOptionalParamsRemoveAudioTags,
|
|
5210
|
+
TranscriptRedactPiiAudioOptionsOverrideAudioRedactionMethod: () => TranscriptRedactPiiAudioOptionsOverrideAudioRedactionMethod,
|
|
5211
|
+
TranscriptRemoveAudioTags: () => TranscriptRemoveAudioTags,
|
|
5173
5212
|
TranscriptStatus: () => TranscriptStatus
|
|
5174
5213
|
});
|
|
5175
5214
|
|
|
@@ -5227,13 +5266,6 @@ var EntityType = {
|
|
|
5227
5266
|
zodiac_sign: "zodiac_sign"
|
|
5228
5267
|
};
|
|
5229
5268
|
|
|
5230
|
-
// src/generated/assemblyai/schema/lemurModel.ts
|
|
5231
|
-
var LemurModel = {
|
|
5232
|
-
"anthropic/claude-3-5-sonnet": "anthropic/claude-3-5-sonnet",
|
|
5233
|
-
"anthropic/claude-3-opus": "anthropic/claude-3-opus",
|
|
5234
|
-
"anthropic/claude-3-haiku": "anthropic/claude-3-haiku"
|
|
5235
|
-
};
|
|
5236
|
-
|
|
5237
5269
|
// src/generated/assemblyai/schema/piiPolicy.ts
|
|
5238
5270
|
var PiiPolicy = {
|
|
5239
5271
|
account_number: "account_number",
|
|
@@ -5300,6 +5332,12 @@ var Sentiment = {
|
|
|
5300
5332
|
NEGATIVE: "NEGATIVE"
|
|
5301
5333
|
};
|
|
5302
5334
|
|
|
5335
|
+
// src/generated/assemblyai/schema/speakerIdentificationRequestBodySpeakerIdentificationSpeakerType.ts
|
|
5336
|
+
var SpeakerIdentificationRequestBodySpeakerIdentificationSpeakerType = {
|
|
5337
|
+
role: "role",
|
|
5338
|
+
name: "name"
|
|
5339
|
+
};
|
|
5340
|
+
|
|
5303
5341
|
// src/generated/assemblyai/schema/substitutionPolicy.ts
|
|
5304
5342
|
var SubstitutionPolicy = {
|
|
5305
5343
|
entity_name: "entity_name",
|
|
@@ -5328,17 +5366,24 @@ var SummaryType = {
|
|
|
5328
5366
|
paragraph: "paragraph"
|
|
5329
5367
|
};
|
|
5330
5368
|
|
|
5331
|
-
// src/generated/assemblyai/schema/
|
|
5332
|
-
var
|
|
5333
|
-
|
|
5334
|
-
default: "default",
|
|
5335
|
-
high: "high"
|
|
5369
|
+
// src/generated/assemblyai/schema/transcriptOptionalParamsRedactPiiAudioOptionsOverrideAudioRedactionMethod.ts
|
|
5370
|
+
var TranscriptOptionalParamsRedactPiiAudioOptionsOverrideAudioRedactionMethod = {
|
|
5371
|
+
silence: "silence"
|
|
5336
5372
|
};
|
|
5337
5373
|
|
|
5338
|
-
// src/generated/assemblyai/schema/
|
|
5339
|
-
var
|
|
5340
|
-
|
|
5341
|
-
|
|
5374
|
+
// src/generated/assemblyai/schema/transcriptOptionalParamsRemoveAudioTags.ts
|
|
5375
|
+
var TranscriptOptionalParamsRemoveAudioTags = {
|
|
5376
|
+
all: "all"
|
|
5377
|
+
};
|
|
5378
|
+
|
|
5379
|
+
// src/generated/assemblyai/schema/transcriptRedactPiiAudioOptionsOverrideAudioRedactionMethod.ts
|
|
5380
|
+
var TranscriptRedactPiiAudioOptionsOverrideAudioRedactionMethod = {
|
|
5381
|
+
silence: "silence"
|
|
5382
|
+
};
|
|
5383
|
+
|
|
5384
|
+
// src/generated/assemblyai/schema/transcriptRemoveAudioTags.ts
|
|
5385
|
+
var TranscriptRemoveAudioTags = {
|
|
5386
|
+
all: "all"
|
|
5342
5387
|
};
|
|
5343
5388
|
|
|
5344
5389
|
// src/generated/assemblyai/api/assemblyAIAPI.ts
|
|
@@ -5357,9 +5402,6 @@ var getTranscript = (transcriptId, options) => {
|
|
|
5357
5402
|
var deleteTranscript = (transcriptId, options) => {
|
|
5358
5403
|
return axios2.delete(`/v2/transcript/${transcriptId}`, options);
|
|
5359
5404
|
};
|
|
5360
|
-
var createTemporaryToken = (createRealtimeTemporaryTokenParams, options) => {
|
|
5361
|
-
return axios2.post(`/v2/realtime/token`, createRealtimeTemporaryTokenParams, options);
|
|
5362
|
-
};
|
|
5363
5405
|
|
|
5364
5406
|
// src/adapters/assemblyai-adapter.ts
|
|
5365
5407
|
var AssemblyAIAdapter = class extends BaseAdapter {
|
|
@@ -5384,14 +5426,61 @@ var AssemblyAIAdapter = class extends BaseAdapter {
|
|
|
5384
5426
|
this.wsBaseUrl = "wss://streaming.assemblyai.com/v3/ws";
|
|
5385
5427
|
}
|
|
5386
5428
|
// v3 Universal Streaming endpoint
|
|
5429
|
+
/**
|
|
5430
|
+
* Get regional hosts for AssemblyAI
|
|
5431
|
+
*
|
|
5432
|
+
* @param region - Regional endpoint identifier
|
|
5433
|
+
* @returns Object with api and streaming hosts
|
|
5434
|
+
*/
|
|
5435
|
+
getRegionalHosts(region) {
|
|
5436
|
+
if (region === "eu") {
|
|
5437
|
+
return { api: "api.eu.assemblyai.com", streaming: "streaming.eu.assemblyai.com" };
|
|
5438
|
+
}
|
|
5439
|
+
return { api: "api.assemblyai.com", streaming: "streaming.assemblyai.com" };
|
|
5440
|
+
}
|
|
5387
5441
|
initialize(config) {
|
|
5388
5442
|
super.initialize(config);
|
|
5389
|
-
|
|
5390
|
-
|
|
5391
|
-
|
|
5392
|
-
|
|
5443
|
+
const hosts = this.getRegionalHosts(config.region);
|
|
5444
|
+
this.baseUrl = config.baseUrl || `https://${hosts.api}`;
|
|
5445
|
+
this.wsBaseUrl = config.wsBaseUrl || (config.baseUrl ? `${this.deriveWsUrl(config.baseUrl)}/v3/ws` : `wss://${hosts.streaming}/v3/ws`);
|
|
5446
|
+
}
|
|
5447
|
+
/**
|
|
5448
|
+
* Change the regional endpoint dynamically
|
|
5449
|
+
*
|
|
5450
|
+
* Useful for switching between US and EU endpoints without reinitializing.
|
|
5451
|
+
* Affects both REST API and WebSocket streaming endpoints.
|
|
5452
|
+
*
|
|
5453
|
+
* @param region - New regional endpoint to use (`us` or `eu`)
|
|
5454
|
+
*
|
|
5455
|
+
* @example Switch to EU region
|
|
5456
|
+
* ```typescript
|
|
5457
|
+
* import { AssemblyAIRegion } from 'voice-router-dev/constants'
|
|
5458
|
+
*
|
|
5459
|
+
* adapter.setRegion(AssemblyAIRegion.eu)
|
|
5460
|
+
* await adapter.transcribe(audio) // Uses EU endpoint
|
|
5461
|
+
* ```
|
|
5462
|
+
*/
|
|
5463
|
+
setRegion(region) {
|
|
5464
|
+
this.validateConfig();
|
|
5465
|
+
if (!this.config.baseUrl) {
|
|
5466
|
+
const hosts = this.getRegionalHosts(region);
|
|
5467
|
+
this.baseUrl = `https://${hosts.api}`;
|
|
5468
|
+
if (!this.config.wsBaseUrl) {
|
|
5469
|
+
this.wsBaseUrl = `wss://${hosts.streaming}/v3/ws`;
|
|
5470
|
+
}
|
|
5393
5471
|
}
|
|
5394
5472
|
}
|
|
5473
|
+
/**
|
|
5474
|
+
* Get the current regional endpoints being used
|
|
5475
|
+
*
|
|
5476
|
+
* @returns Object with current API and WebSocket URLs
|
|
5477
|
+
*/
|
|
5478
|
+
getRegion() {
|
|
5479
|
+
return {
|
|
5480
|
+
api: this.baseUrl,
|
|
5481
|
+
websocket: this.wsBaseUrl
|
|
5482
|
+
};
|
|
5483
|
+
}
|
|
5395
5484
|
/**
|
|
5396
5485
|
* Get axios config for generated API client functions
|
|
5397
5486
|
* Configures headers and base URL using authorization header
|
|
@@ -5651,13 +5740,15 @@ var AssemblyAIAdapter = class extends BaseAdapter {
|
|
|
5651
5740
|
const request = {
|
|
5652
5741
|
...options?.assemblyai,
|
|
5653
5742
|
audio_url: audioUrl,
|
|
5743
|
+
// speech_models is required — default to universal-3-pro
|
|
5744
|
+
speech_models: options?.assemblyai?.speech_models ?? ["universal-3-pro"],
|
|
5654
5745
|
// Enable punctuation and formatting by default
|
|
5655
5746
|
punctuate: options?.assemblyai?.punctuate ?? true,
|
|
5656
5747
|
format_text: options?.assemblyai?.format_text ?? true
|
|
5657
5748
|
};
|
|
5658
5749
|
if (options) {
|
|
5659
5750
|
if (options.model) {
|
|
5660
|
-
request.
|
|
5751
|
+
request.speech_models = [options.model];
|
|
5661
5752
|
}
|
|
5662
5753
|
if (options.language) {
|
|
5663
5754
|
const languageCode = options.language.includes("_") ? options.language : `${options.language}_us`;
|
|
@@ -5673,8 +5764,7 @@ var AssemblyAIAdapter = class extends BaseAdapter {
|
|
|
5673
5764
|
}
|
|
5674
5765
|
}
|
|
5675
5766
|
if (options.customVocabulary && options.customVocabulary.length > 0) {
|
|
5676
|
-
request.
|
|
5677
|
-
request.boost_param = request.boost_param ?? "high";
|
|
5767
|
+
request.keyterms_prompt = options.customVocabulary;
|
|
5678
5768
|
}
|
|
5679
5769
|
if (options.summarization) {
|
|
5680
5770
|
request.summarization = true;
|
|
@@ -7449,6 +7539,18 @@ var transcriptionsListFiles = (id, params, options) => {
|
|
|
7449
7539
|
params: { ...params, ...options?.params }
|
|
7450
7540
|
});
|
|
7451
7541
|
};
|
|
7542
|
+
var webHooksList = (params, options) => {
|
|
7543
|
+
return axios4.get(`/webhooks`, {
|
|
7544
|
+
...options,
|
|
7545
|
+
params: { ...params, ...options?.params }
|
|
7546
|
+
});
|
|
7547
|
+
};
|
|
7548
|
+
var webHooksCreate = (webHook, options) => {
|
|
7549
|
+
return axios4.post(`/webhooks`, webHook, options);
|
|
7550
|
+
};
|
|
7551
|
+
var webHooksDelete = (id, options) => {
|
|
7552
|
+
return axios4.delete(`/webhooks/${id}`, options);
|
|
7553
|
+
};
|
|
7452
7554
|
|
|
7453
7555
|
// src/adapters/azure-stt-adapter.ts
|
|
7454
7556
|
var AzureSTTAdapter = class extends BaseAdapter {
|
|
@@ -7521,19 +7623,8 @@ var AzureSTTAdapter = class extends BaseAdapter {
|
|
|
7521
7623
|
this.getAxiosConfig()
|
|
7522
7624
|
);
|
|
7523
7625
|
const transcription = response.data;
|
|
7524
|
-
|
|
7525
|
-
|
|
7526
|
-
provider: this.name,
|
|
7527
|
-
data: {
|
|
7528
|
-
id: transcription.self?.split("/").pop() || "",
|
|
7529
|
-
text: "",
|
|
7530
|
-
// Will be populated after polling
|
|
7531
|
-
status: this.normalizeStatus(transcription.status),
|
|
7532
|
-
language: transcription.locale,
|
|
7533
|
-
createdAt: transcription.createdDateTime
|
|
7534
|
-
},
|
|
7535
|
-
raw: transcription
|
|
7536
|
-
};
|
|
7626
|
+
const transcriptId = transcription.self?.split("/").pop() || "";
|
|
7627
|
+
return await this.pollForCompletion(transcriptId);
|
|
7537
7628
|
} catch (error) {
|
|
7538
7629
|
return this.createErrorResponse(error);
|
|
7539
7630
|
}
|
|
@@ -7691,6 +7782,50 @@ var AzureSTTAdapter = class extends BaseAdapter {
|
|
|
7691
7782
|
};
|
|
7692
7783
|
}
|
|
7693
7784
|
}
|
|
7785
|
+
/**
|
|
7786
|
+
* Register a subscription-wide webhook for transcription events
|
|
7787
|
+
*
|
|
7788
|
+
* Azure webhooks are subscription-wide (not per-transcription).
|
|
7789
|
+
* Call this once during setup to receive callbacks for all transcription events.
|
|
7790
|
+
* The webhook URL will receive POST requests for transcription lifecycle events.
|
|
7791
|
+
*
|
|
7792
|
+
* @param url - The webhook URL to receive events
|
|
7793
|
+
* @param options - Optional: event filters and display name
|
|
7794
|
+
* @returns Created webhook object
|
|
7795
|
+
*/
|
|
7796
|
+
async registerWebhook(url, options) {
|
|
7797
|
+
this.validateConfig();
|
|
7798
|
+
const webhook = {
|
|
7799
|
+
webUrl: url,
|
|
7800
|
+
displayName: options?.displayName || "SDK Webhook",
|
|
7801
|
+
events: options?.events || {
|
|
7802
|
+
transcriptionCreation: true,
|
|
7803
|
+
transcriptionProcessing: true,
|
|
7804
|
+
transcriptionCompletion: true
|
|
7805
|
+
}
|
|
7806
|
+
};
|
|
7807
|
+
const response = await webHooksCreate(webhook, this.getAxiosConfig());
|
|
7808
|
+
return response.data;
|
|
7809
|
+
}
|
|
7810
|
+
/**
|
|
7811
|
+
* Unregister a subscription-wide webhook by ID
|
|
7812
|
+
*
|
|
7813
|
+
* @param webhookId - The webhook ID to delete
|
|
7814
|
+
*/
|
|
7815
|
+
async unregisterWebhook(webhookId) {
|
|
7816
|
+
this.validateConfig();
|
|
7817
|
+
await webHooksDelete(webhookId, this.getAxiosConfig());
|
|
7818
|
+
}
|
|
7819
|
+
/**
|
|
7820
|
+
* List all registered webhooks for the subscription
|
|
7821
|
+
*
|
|
7822
|
+
* @returns Array of registered webhooks
|
|
7823
|
+
*/
|
|
7824
|
+
async listWebhooks() {
|
|
7825
|
+
this.validateConfig();
|
|
7826
|
+
const response = await webHooksList(void 0, this.getAxiosConfig());
|
|
7827
|
+
return [...response.data.values || []];
|
|
7828
|
+
}
|
|
7694
7829
|
/**
|
|
7695
7830
|
* Map unified status to Azure status format using generated enum
|
|
7696
7831
|
*/
|
|
@@ -8447,6 +8582,20 @@ function createOpenAIWhisperAdapter(config) {
|
|
|
8447
8582
|
// src/adapters/speechmatics-adapter.ts
|
|
8448
8583
|
import axios8 from "axios";
|
|
8449
8584
|
|
|
8585
|
+
// src/generated/speechmatics/schema/notificationConfigContentsItem.ts
|
|
8586
|
+
var NotificationConfigContentsItem = {
|
|
8587
|
+
jobinfo: "jobinfo",
|
|
8588
|
+
transcript: "transcript",
|
|
8589
|
+
"transcriptjson-v2": "transcript.json-v2",
|
|
8590
|
+
transcripttxt: "transcript.txt",
|
|
8591
|
+
transcriptsrt: "transcript.srt",
|
|
8592
|
+
alignment: "alignment",
|
|
8593
|
+
alignmentword_start_and_end: "alignment.word_start_and_end",
|
|
8594
|
+
alignmentone_per_line: "alignment.one_per_line",
|
|
8595
|
+
data: "data",
|
|
8596
|
+
text: "text"
|
|
8597
|
+
};
|
|
8598
|
+
|
|
8450
8599
|
// src/generated/speechmatics/schema/transcriptionConfigDiarization.ts
|
|
8451
8600
|
var TranscriptionConfigDiarization = {
|
|
8452
8601
|
none: "none",
|
|
@@ -8603,6 +8752,14 @@ var SpeechmaticsAdapter = class extends BaseAdapter {
|
|
|
8603
8752
|
content: word
|
|
8604
8753
|
}));
|
|
8605
8754
|
}
|
|
8755
|
+
if (options?.webhookUrl) {
|
|
8756
|
+
jobConfig.notification_config = [
|
|
8757
|
+
{
|
|
8758
|
+
url: options.webhookUrl,
|
|
8759
|
+
contents: [NotificationConfigContentsItem.transcript]
|
|
8760
|
+
}
|
|
8761
|
+
];
|
|
8762
|
+
}
|
|
8606
8763
|
let requestBody;
|
|
8607
8764
|
let headers = {};
|
|
8608
8765
|
if (audio.type === "url") {
|
|
@@ -8628,16 +8785,20 @@ var SpeechmaticsAdapter = class extends BaseAdapter {
|
|
|
8628
8785
|
};
|
|
8629
8786
|
}
|
|
8630
8787
|
const response = await this.client.post("/jobs", requestBody, { headers });
|
|
8631
|
-
|
|
8632
|
-
|
|
8633
|
-
|
|
8634
|
-
|
|
8635
|
-
|
|
8636
|
-
|
|
8637
|
-
|
|
8638
|
-
|
|
8639
|
-
|
|
8640
|
-
|
|
8788
|
+
const jobId = response.data.id;
|
|
8789
|
+
if (options?.webhookUrl) {
|
|
8790
|
+
return {
|
|
8791
|
+
success: true,
|
|
8792
|
+
provider: this.name,
|
|
8793
|
+
data: {
|
|
8794
|
+
id: jobId,
|
|
8795
|
+
text: "",
|
|
8796
|
+
status: "queued"
|
|
8797
|
+
},
|
|
8798
|
+
raw: response.data
|
|
8799
|
+
};
|
|
8800
|
+
}
|
|
8801
|
+
return await this.pollForCompletion(jobId);
|
|
8641
8802
|
} catch (error) {
|
|
8642
8803
|
return this.createErrorResponse(error);
|
|
8643
8804
|
}
|
|
@@ -11383,15 +11544,10 @@ var deepgramStreamingOnlyParams = zod2.object({
|
|
|
11383
11544
|
// src/generated/assemblyai/api/assemblyAIAPI.zod.ts
|
|
11384
11545
|
var assemblyAIAPI_zod_exports = {};
|
|
11385
11546
|
__export(assemblyAIAPI_zod_exports, {
|
|
11386
|
-
createTemporaryTokenBody: () => createTemporaryTokenBody,
|
|
11387
|
-
createTemporaryTokenBodyExpiresInMin: () => createTemporaryTokenBodyExpiresInMin,
|
|
11388
|
-
createTemporaryTokenResponse: () => createTemporaryTokenResponse,
|
|
11389
11547
|
createTranscriptBody: () => createTranscriptBody,
|
|
11390
11548
|
createTranscriptBodyAutoChaptersDefault: () => createTranscriptBodyAutoChaptersDefault,
|
|
11391
11549
|
createTranscriptBodyAutoHighlightsDefault: () => createTranscriptBodyAutoHighlightsDefault,
|
|
11392
11550
|
createTranscriptBodyContentSafetyConfidenceDefault: () => createTranscriptBodyContentSafetyConfidenceDefault,
|
|
11393
|
-
createTranscriptBodyContentSafetyConfidenceMax: () => createTranscriptBodyContentSafetyConfidenceMax,
|
|
11394
|
-
createTranscriptBodyContentSafetyConfidenceMin: () => createTranscriptBodyContentSafetyConfidenceMin,
|
|
11395
11551
|
createTranscriptBodyContentSafetyDefault: () => createTranscriptBodyContentSafetyDefault,
|
|
11396
11552
|
createTranscriptBodyCustomTopicsDefault: () => createTranscriptBodyCustomTopicsDefault,
|
|
11397
11553
|
createTranscriptBodyDisfluenciesDefault: () => createTranscriptBodyDisfluenciesDefault,
|
|
@@ -11399,198 +11555,58 @@ __export(assemblyAIAPI_zod_exports, {
|
|
|
11399
11555
|
createTranscriptBodyFilterProfanityDefault: () => createTranscriptBodyFilterProfanityDefault,
|
|
11400
11556
|
createTranscriptBodyFormatTextDefault: () => createTranscriptBodyFormatTextDefault,
|
|
11401
11557
|
createTranscriptBodyIabCategoriesDefault: () => createTranscriptBodyIabCategoriesDefault,
|
|
11402
|
-
createTranscriptBodyLanguageCodeDefault: () => createTranscriptBodyLanguageCodeDefault,
|
|
11403
|
-
createTranscriptBodyLanguageConfidenceThresholdDefault: () => createTranscriptBodyLanguageConfidenceThresholdDefault,
|
|
11404
|
-
createTranscriptBodyLanguageConfidenceThresholdMax: () => createTranscriptBodyLanguageConfidenceThresholdMax,
|
|
11405
|
-
createTranscriptBodyLanguageConfidenceThresholdMin: () => createTranscriptBodyLanguageConfidenceThresholdMin,
|
|
11406
11558
|
createTranscriptBodyLanguageDetectionDefault: () => createTranscriptBodyLanguageDetectionDefault,
|
|
11559
|
+
createTranscriptBodyLanguageDetectionOptionsCodeSwitchingConfidenceThresholdDefault: () => createTranscriptBodyLanguageDetectionOptionsCodeSwitchingConfidenceThresholdDefault,
|
|
11560
|
+
createTranscriptBodyLanguageDetectionOptionsCodeSwitchingDefault: () => createTranscriptBodyLanguageDetectionOptionsCodeSwitchingDefault,
|
|
11561
|
+
createTranscriptBodyLanguageDetectionOptionsFallbackLanguageDefault: () => createTranscriptBodyLanguageDetectionOptionsFallbackLanguageDefault,
|
|
11407
11562
|
createTranscriptBodyMultichannelDefault: () => createTranscriptBodyMultichannelDefault,
|
|
11408
11563
|
createTranscriptBodyPunctuateDefault: () => createTranscriptBodyPunctuateDefault,
|
|
11409
11564
|
createTranscriptBodyRedactPiiAudioDefault: () => createTranscriptBodyRedactPiiAudioDefault,
|
|
11565
|
+
createTranscriptBodyRedactPiiAudioOptionsReturnRedactedNoSpeechAudioDefault: () => createTranscriptBodyRedactPiiAudioOptionsReturnRedactedNoSpeechAudioDefault,
|
|
11410
11566
|
createTranscriptBodyRedactPiiDefault: () => createTranscriptBodyRedactPiiDefault,
|
|
11411
|
-
createTranscriptBodyRedactPiiSubDefault: () => createTranscriptBodyRedactPiiSubDefault,
|
|
11412
11567
|
createTranscriptBodySentimentAnalysisDefault: () => createTranscriptBodySentimentAnalysisDefault,
|
|
11413
11568
|
createTranscriptBodySpeakerLabelsDefault: () => createTranscriptBodySpeakerLabelsDefault,
|
|
11414
|
-
|
|
11415
|
-
|
|
11416
|
-
|
|
11417
|
-
createTranscriptBodySpeechThresholdMax: () => createTranscriptBodySpeechThresholdMax,
|
|
11418
|
-
createTranscriptBodySpeechThresholdMin: () => createTranscriptBodySpeechThresholdMin,
|
|
11569
|
+
createTranscriptBodySpeakerOptionsMinSpeakersExpectedDefault: () => createTranscriptBodySpeakerOptionsMinSpeakersExpectedDefault,
|
|
11570
|
+
createTranscriptBodySpeechUnderstandingRequestTranslationFormalDefault: () => createTranscriptBodySpeechUnderstandingRequestTranslationFormalDefault,
|
|
11571
|
+
createTranscriptBodySpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault: () => createTranscriptBodySpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault,
|
|
11419
11572
|
createTranscriptBodySummarizationDefault: () => createTranscriptBodySummarizationDefault,
|
|
11420
|
-
|
|
11421
|
-
createTranscriptBodyWebhookAuthHeaderValueDefault: () => createTranscriptBodyWebhookAuthHeaderValueDefault,
|
|
11573
|
+
createTranscriptBodyTemperatureDefault: () => createTranscriptBodyTemperatureDefault,
|
|
11422
11574
|
createTranscriptResponse: () => createTranscriptResponse,
|
|
11423
|
-
|
|
11424
|
-
|
|
11425
|
-
|
|
11426
|
-
|
|
11427
|
-
|
|
11428
|
-
|
|
11429
|
-
createTranscriptResponseContentSafetyLabelsResultsItemLabelsItemSeverityMax: () => createTranscriptResponseContentSafetyLabelsResultsItemLabelsItemSeverityMax,
|
|
11430
|
-
createTranscriptResponseContentSafetyLabelsResultsItemLabelsItemSeverityMin: () => createTranscriptResponseContentSafetyLabelsResultsItemLabelsItemSeverityMin,
|
|
11431
|
-
createTranscriptResponseContentSafetyLabelsSeverityScoreSummaryHighMax: () => createTranscriptResponseContentSafetyLabelsSeverityScoreSummaryHighMax,
|
|
11432
|
-
createTranscriptResponseContentSafetyLabelsSeverityScoreSummaryHighMin: () => createTranscriptResponseContentSafetyLabelsSeverityScoreSummaryHighMin,
|
|
11433
|
-
createTranscriptResponseContentSafetyLabelsSeverityScoreSummaryLowMax: () => createTranscriptResponseContentSafetyLabelsSeverityScoreSummaryLowMax,
|
|
11434
|
-
createTranscriptResponseContentSafetyLabelsSeverityScoreSummaryLowMin: () => createTranscriptResponseContentSafetyLabelsSeverityScoreSummaryLowMin,
|
|
11435
|
-
createTranscriptResponseContentSafetyLabelsSeverityScoreSummaryMediumMax: () => createTranscriptResponseContentSafetyLabelsSeverityScoreSummaryMediumMax,
|
|
11436
|
-
createTranscriptResponseContentSafetyLabelsSeverityScoreSummaryMediumMin: () => createTranscriptResponseContentSafetyLabelsSeverityScoreSummaryMediumMin,
|
|
11437
|
-
createTranscriptResponseContentSafetyLabelsSummaryMaxOne: () => createTranscriptResponseContentSafetyLabelsSummaryMaxOne,
|
|
11438
|
-
createTranscriptResponseContentSafetyLabelsSummaryMinOne: () => createTranscriptResponseContentSafetyLabelsSummaryMinOne,
|
|
11439
|
-
createTranscriptResponseIabCategoriesResultResultsItemLabelsItemRelevanceMax: () => createTranscriptResponseIabCategoriesResultResultsItemLabelsItemRelevanceMax,
|
|
11440
|
-
createTranscriptResponseIabCategoriesResultResultsItemLabelsItemRelevanceMin: () => createTranscriptResponseIabCategoriesResultResultsItemLabelsItemRelevanceMin,
|
|
11441
|
-
createTranscriptResponseIabCategoriesResultSummaryMaxOne: () => createTranscriptResponseIabCategoriesResultSummaryMaxOne,
|
|
11442
|
-
createTranscriptResponseIabCategoriesResultSummaryMinOne: () => createTranscriptResponseIabCategoriesResultSummaryMinOne,
|
|
11443
|
-
createTranscriptResponseLanguageConfidenceMax: () => createTranscriptResponseLanguageConfidenceMax,
|
|
11444
|
-
createTranscriptResponseLanguageConfidenceMin: () => createTranscriptResponseLanguageConfidenceMin,
|
|
11445
|
-
createTranscriptResponseLanguageConfidenceThresholdMax: () => createTranscriptResponseLanguageConfidenceThresholdMax,
|
|
11446
|
-
createTranscriptResponseLanguageConfidenceThresholdMin: () => createTranscriptResponseLanguageConfidenceThresholdMin,
|
|
11447
|
-
createTranscriptResponseSentimentAnalysisResultsItemConfidenceMax: () => createTranscriptResponseSentimentAnalysisResultsItemConfidenceMax,
|
|
11448
|
-
createTranscriptResponseSentimentAnalysisResultsItemConfidenceMin: () => createTranscriptResponseSentimentAnalysisResultsItemConfidenceMin,
|
|
11449
|
-
createTranscriptResponseSpeechModelDefault: () => createTranscriptResponseSpeechModelDefault,
|
|
11450
|
-
createTranscriptResponseSpeechThresholdMax: () => createTranscriptResponseSpeechThresholdMax,
|
|
11451
|
-
createTranscriptResponseSpeechThresholdMin: () => createTranscriptResponseSpeechThresholdMin,
|
|
11452
|
-
createTranscriptResponseUtterancesItemConfidenceMax: () => createTranscriptResponseUtterancesItemConfidenceMax,
|
|
11453
|
-
createTranscriptResponseUtterancesItemConfidenceMin: () => createTranscriptResponseUtterancesItemConfidenceMin,
|
|
11454
|
-
createTranscriptResponseUtterancesItemWordsItemConfidenceMax: () => createTranscriptResponseUtterancesItemWordsItemConfidenceMax,
|
|
11455
|
-
createTranscriptResponseUtterancesItemWordsItemConfidenceMin: () => createTranscriptResponseUtterancesItemWordsItemConfidenceMin,
|
|
11456
|
-
createTranscriptResponseWordsItemConfidenceMax: () => createTranscriptResponseWordsItemConfidenceMax,
|
|
11457
|
-
createTranscriptResponseWordsItemConfidenceMin: () => createTranscriptResponseWordsItemConfidenceMin,
|
|
11575
|
+
createTranscriptResponseLanguageDetectionOptionsCodeSwitchingConfidenceThresholdDefault: () => createTranscriptResponseLanguageDetectionOptionsCodeSwitchingConfidenceThresholdDefault,
|
|
11576
|
+
createTranscriptResponseLanguageDetectionOptionsCodeSwitchingDefault: () => createTranscriptResponseLanguageDetectionOptionsCodeSwitchingDefault,
|
|
11577
|
+
createTranscriptResponseLanguageDetectionOptionsFallbackLanguageDefault: () => createTranscriptResponseLanguageDetectionOptionsFallbackLanguageDefault,
|
|
11578
|
+
createTranscriptResponseRedactPiiAudioOptionsReturnRedactedNoSpeechAudioDefault: () => createTranscriptResponseRedactPiiAudioOptionsReturnRedactedNoSpeechAudioDefault,
|
|
11579
|
+
createTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault: () => createTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault,
|
|
11580
|
+
createTranscriptResponseSpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault: () => createTranscriptResponseSpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault,
|
|
11458
11581
|
deleteTranscriptParams: () => deleteTranscriptParams,
|
|
11459
11582
|
deleteTranscriptResponse: () => deleteTranscriptResponse,
|
|
11460
|
-
|
|
11461
|
-
|
|
11462
|
-
|
|
11463
|
-
|
|
11464
|
-
|
|
11465
|
-
|
|
11466
|
-
deleteTranscriptResponseContentSafetyLabelsResultsItemLabelsItemSeverityMax: () => deleteTranscriptResponseContentSafetyLabelsResultsItemLabelsItemSeverityMax,
|
|
11467
|
-
deleteTranscriptResponseContentSafetyLabelsResultsItemLabelsItemSeverityMin: () => deleteTranscriptResponseContentSafetyLabelsResultsItemLabelsItemSeverityMin,
|
|
11468
|
-
deleteTranscriptResponseContentSafetyLabelsSeverityScoreSummaryHighMax: () => deleteTranscriptResponseContentSafetyLabelsSeverityScoreSummaryHighMax,
|
|
11469
|
-
deleteTranscriptResponseContentSafetyLabelsSeverityScoreSummaryHighMin: () => deleteTranscriptResponseContentSafetyLabelsSeverityScoreSummaryHighMin,
|
|
11470
|
-
deleteTranscriptResponseContentSafetyLabelsSeverityScoreSummaryLowMax: () => deleteTranscriptResponseContentSafetyLabelsSeverityScoreSummaryLowMax,
|
|
11471
|
-
deleteTranscriptResponseContentSafetyLabelsSeverityScoreSummaryLowMin: () => deleteTranscriptResponseContentSafetyLabelsSeverityScoreSummaryLowMin,
|
|
11472
|
-
deleteTranscriptResponseContentSafetyLabelsSeverityScoreSummaryMediumMax: () => deleteTranscriptResponseContentSafetyLabelsSeverityScoreSummaryMediumMax,
|
|
11473
|
-
deleteTranscriptResponseContentSafetyLabelsSeverityScoreSummaryMediumMin: () => deleteTranscriptResponseContentSafetyLabelsSeverityScoreSummaryMediumMin,
|
|
11474
|
-
deleteTranscriptResponseContentSafetyLabelsSummaryMaxOne: () => deleteTranscriptResponseContentSafetyLabelsSummaryMaxOne,
|
|
11475
|
-
deleteTranscriptResponseContentSafetyLabelsSummaryMinOne: () => deleteTranscriptResponseContentSafetyLabelsSummaryMinOne,
|
|
11476
|
-
deleteTranscriptResponseIabCategoriesResultResultsItemLabelsItemRelevanceMax: () => deleteTranscriptResponseIabCategoriesResultResultsItemLabelsItemRelevanceMax,
|
|
11477
|
-
deleteTranscriptResponseIabCategoriesResultResultsItemLabelsItemRelevanceMin: () => deleteTranscriptResponseIabCategoriesResultResultsItemLabelsItemRelevanceMin,
|
|
11478
|
-
deleteTranscriptResponseIabCategoriesResultSummaryMaxOne: () => deleteTranscriptResponseIabCategoriesResultSummaryMaxOne,
|
|
11479
|
-
deleteTranscriptResponseIabCategoriesResultSummaryMinOne: () => deleteTranscriptResponseIabCategoriesResultSummaryMinOne,
|
|
11480
|
-
deleteTranscriptResponseLanguageConfidenceMax: () => deleteTranscriptResponseLanguageConfidenceMax,
|
|
11481
|
-
deleteTranscriptResponseLanguageConfidenceMin: () => deleteTranscriptResponseLanguageConfidenceMin,
|
|
11482
|
-
deleteTranscriptResponseLanguageConfidenceThresholdMax: () => deleteTranscriptResponseLanguageConfidenceThresholdMax,
|
|
11483
|
-
deleteTranscriptResponseLanguageConfidenceThresholdMin: () => deleteTranscriptResponseLanguageConfidenceThresholdMin,
|
|
11484
|
-
deleteTranscriptResponseSentimentAnalysisResultsItemConfidenceMax: () => deleteTranscriptResponseSentimentAnalysisResultsItemConfidenceMax,
|
|
11485
|
-
deleteTranscriptResponseSentimentAnalysisResultsItemConfidenceMin: () => deleteTranscriptResponseSentimentAnalysisResultsItemConfidenceMin,
|
|
11486
|
-
deleteTranscriptResponseSpeechModelDefault: () => deleteTranscriptResponseSpeechModelDefault,
|
|
11487
|
-
deleteTranscriptResponseSpeechThresholdMax: () => deleteTranscriptResponseSpeechThresholdMax,
|
|
11488
|
-
deleteTranscriptResponseSpeechThresholdMin: () => deleteTranscriptResponseSpeechThresholdMin,
|
|
11489
|
-
deleteTranscriptResponseUtterancesItemConfidenceMax: () => deleteTranscriptResponseUtterancesItemConfidenceMax,
|
|
11490
|
-
deleteTranscriptResponseUtterancesItemConfidenceMin: () => deleteTranscriptResponseUtterancesItemConfidenceMin,
|
|
11491
|
-
deleteTranscriptResponseUtterancesItemWordsItemConfidenceMax: () => deleteTranscriptResponseUtterancesItemWordsItemConfidenceMax,
|
|
11492
|
-
deleteTranscriptResponseUtterancesItemWordsItemConfidenceMin: () => deleteTranscriptResponseUtterancesItemWordsItemConfidenceMin,
|
|
11493
|
-
deleteTranscriptResponseWordsItemConfidenceMax: () => deleteTranscriptResponseWordsItemConfidenceMax,
|
|
11494
|
-
deleteTranscriptResponseWordsItemConfidenceMin: () => deleteTranscriptResponseWordsItemConfidenceMin,
|
|
11495
|
-
getLemurResponseParams: () => getLemurResponseParams,
|
|
11496
|
-
getLemurResponseResponse: () => getLemurResponseResponse,
|
|
11497
|
-
getLemurResponseResponseUsageInputTokensMin: () => getLemurResponseResponseUsageInputTokensMin,
|
|
11498
|
-
getLemurResponseResponseUsageInputTokensMinOne: () => getLemurResponseResponseUsageInputTokensMinOne,
|
|
11499
|
-
getLemurResponseResponseUsageOutputTokensMin: () => getLemurResponseResponseUsageOutputTokensMin,
|
|
11500
|
-
getLemurResponseResponseUsageOutputTokensMinOne: () => getLemurResponseResponseUsageOutputTokensMinOne,
|
|
11583
|
+
deleteTranscriptResponseLanguageDetectionOptionsCodeSwitchingConfidenceThresholdDefault: () => deleteTranscriptResponseLanguageDetectionOptionsCodeSwitchingConfidenceThresholdDefault,
|
|
11584
|
+
deleteTranscriptResponseLanguageDetectionOptionsCodeSwitchingDefault: () => deleteTranscriptResponseLanguageDetectionOptionsCodeSwitchingDefault,
|
|
11585
|
+
deleteTranscriptResponseLanguageDetectionOptionsFallbackLanguageDefault: () => deleteTranscriptResponseLanguageDetectionOptionsFallbackLanguageDefault,
|
|
11586
|
+
deleteTranscriptResponseRedactPiiAudioOptionsReturnRedactedNoSpeechAudioDefault: () => deleteTranscriptResponseRedactPiiAudioOptionsReturnRedactedNoSpeechAudioDefault,
|
|
11587
|
+
deleteTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault: () => deleteTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault,
|
|
11588
|
+
deleteTranscriptResponseSpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault: () => deleteTranscriptResponseSpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault,
|
|
11501
11589
|
getRedactedAudioParams: () => getRedactedAudioParams,
|
|
11502
11590
|
getRedactedAudioResponse: () => getRedactedAudioResponse,
|
|
11503
11591
|
getSubtitlesParams: () => getSubtitlesParams,
|
|
11504
11592
|
getSubtitlesQueryParams: () => getSubtitlesQueryParams,
|
|
11593
|
+
getSubtitlesResponse: () => getSubtitlesResponse,
|
|
11505
11594
|
getTranscriptParagraphsParams: () => getTranscriptParagraphsParams,
|
|
11506
11595
|
getTranscriptParagraphsResponse: () => getTranscriptParagraphsResponse,
|
|
11507
|
-
getTranscriptParagraphsResponseConfidenceMax: () => getTranscriptParagraphsResponseConfidenceMax,
|
|
11508
|
-
getTranscriptParagraphsResponseConfidenceMin: () => getTranscriptParagraphsResponseConfidenceMin,
|
|
11509
|
-
getTranscriptParagraphsResponseParagraphsItemConfidenceMax: () => getTranscriptParagraphsResponseParagraphsItemConfidenceMax,
|
|
11510
|
-
getTranscriptParagraphsResponseParagraphsItemConfidenceMin: () => getTranscriptParagraphsResponseParagraphsItemConfidenceMin,
|
|
11511
|
-
getTranscriptParagraphsResponseParagraphsItemWordsItemConfidenceMax: () => getTranscriptParagraphsResponseParagraphsItemWordsItemConfidenceMax,
|
|
11512
|
-
getTranscriptParagraphsResponseParagraphsItemWordsItemConfidenceMin: () => getTranscriptParagraphsResponseParagraphsItemWordsItemConfidenceMin,
|
|
11513
11596
|
getTranscriptParams: () => getTranscriptParams,
|
|
11514
11597
|
getTranscriptResponse: () => getTranscriptResponse,
|
|
11515
|
-
|
|
11516
|
-
|
|
11517
|
-
|
|
11518
|
-
|
|
11519
|
-
|
|
11520
|
-
|
|
11521
|
-
getTranscriptResponseContentSafetyLabelsResultsItemLabelsItemSeverityMax: () => getTranscriptResponseContentSafetyLabelsResultsItemLabelsItemSeverityMax,
|
|
11522
|
-
getTranscriptResponseContentSafetyLabelsResultsItemLabelsItemSeverityMin: () => getTranscriptResponseContentSafetyLabelsResultsItemLabelsItemSeverityMin,
|
|
11523
|
-
getTranscriptResponseContentSafetyLabelsSeverityScoreSummaryHighMax: () => getTranscriptResponseContentSafetyLabelsSeverityScoreSummaryHighMax,
|
|
11524
|
-
getTranscriptResponseContentSafetyLabelsSeverityScoreSummaryHighMin: () => getTranscriptResponseContentSafetyLabelsSeverityScoreSummaryHighMin,
|
|
11525
|
-
getTranscriptResponseContentSafetyLabelsSeverityScoreSummaryLowMax: () => getTranscriptResponseContentSafetyLabelsSeverityScoreSummaryLowMax,
|
|
11526
|
-
getTranscriptResponseContentSafetyLabelsSeverityScoreSummaryLowMin: () => getTranscriptResponseContentSafetyLabelsSeverityScoreSummaryLowMin,
|
|
11527
|
-
getTranscriptResponseContentSafetyLabelsSeverityScoreSummaryMediumMax: () => getTranscriptResponseContentSafetyLabelsSeverityScoreSummaryMediumMax,
|
|
11528
|
-
getTranscriptResponseContentSafetyLabelsSeverityScoreSummaryMediumMin: () => getTranscriptResponseContentSafetyLabelsSeverityScoreSummaryMediumMin,
|
|
11529
|
-
getTranscriptResponseContentSafetyLabelsSummaryMaxOne: () => getTranscriptResponseContentSafetyLabelsSummaryMaxOne,
|
|
11530
|
-
getTranscriptResponseContentSafetyLabelsSummaryMinOne: () => getTranscriptResponseContentSafetyLabelsSummaryMinOne,
|
|
11531
|
-
getTranscriptResponseIabCategoriesResultResultsItemLabelsItemRelevanceMax: () => getTranscriptResponseIabCategoriesResultResultsItemLabelsItemRelevanceMax,
|
|
11532
|
-
getTranscriptResponseIabCategoriesResultResultsItemLabelsItemRelevanceMin: () => getTranscriptResponseIabCategoriesResultResultsItemLabelsItemRelevanceMin,
|
|
11533
|
-
getTranscriptResponseIabCategoriesResultSummaryMaxOne: () => getTranscriptResponseIabCategoriesResultSummaryMaxOne,
|
|
11534
|
-
getTranscriptResponseIabCategoriesResultSummaryMinOne: () => getTranscriptResponseIabCategoriesResultSummaryMinOne,
|
|
11535
|
-
getTranscriptResponseLanguageConfidenceMax: () => getTranscriptResponseLanguageConfidenceMax,
|
|
11536
|
-
getTranscriptResponseLanguageConfidenceMin: () => getTranscriptResponseLanguageConfidenceMin,
|
|
11537
|
-
getTranscriptResponseLanguageConfidenceThresholdMax: () => getTranscriptResponseLanguageConfidenceThresholdMax,
|
|
11538
|
-
getTranscriptResponseLanguageConfidenceThresholdMin: () => getTranscriptResponseLanguageConfidenceThresholdMin,
|
|
11539
|
-
getTranscriptResponseSentimentAnalysisResultsItemConfidenceMax: () => getTranscriptResponseSentimentAnalysisResultsItemConfidenceMax,
|
|
11540
|
-
getTranscriptResponseSentimentAnalysisResultsItemConfidenceMin: () => getTranscriptResponseSentimentAnalysisResultsItemConfidenceMin,
|
|
11541
|
-
getTranscriptResponseSpeechModelDefault: () => getTranscriptResponseSpeechModelDefault,
|
|
11542
|
-
getTranscriptResponseSpeechThresholdMax: () => getTranscriptResponseSpeechThresholdMax,
|
|
11543
|
-
getTranscriptResponseSpeechThresholdMin: () => getTranscriptResponseSpeechThresholdMin,
|
|
11544
|
-
getTranscriptResponseUtterancesItemConfidenceMax: () => getTranscriptResponseUtterancesItemConfidenceMax,
|
|
11545
|
-
getTranscriptResponseUtterancesItemConfidenceMin: () => getTranscriptResponseUtterancesItemConfidenceMin,
|
|
11546
|
-
getTranscriptResponseUtterancesItemWordsItemConfidenceMax: () => getTranscriptResponseUtterancesItemWordsItemConfidenceMax,
|
|
11547
|
-
getTranscriptResponseUtterancesItemWordsItemConfidenceMin: () => getTranscriptResponseUtterancesItemWordsItemConfidenceMin,
|
|
11548
|
-
getTranscriptResponseWordsItemConfidenceMax: () => getTranscriptResponseWordsItemConfidenceMax,
|
|
11549
|
-
getTranscriptResponseWordsItemConfidenceMin: () => getTranscriptResponseWordsItemConfidenceMin,
|
|
11598
|
+
getTranscriptResponseLanguageDetectionOptionsCodeSwitchingConfidenceThresholdDefault: () => getTranscriptResponseLanguageDetectionOptionsCodeSwitchingConfidenceThresholdDefault,
|
|
11599
|
+
getTranscriptResponseLanguageDetectionOptionsCodeSwitchingDefault: () => getTranscriptResponseLanguageDetectionOptionsCodeSwitchingDefault,
|
|
11600
|
+
getTranscriptResponseLanguageDetectionOptionsFallbackLanguageDefault: () => getTranscriptResponseLanguageDetectionOptionsFallbackLanguageDefault,
|
|
11601
|
+
getTranscriptResponseRedactPiiAudioOptionsReturnRedactedNoSpeechAudioDefault: () => getTranscriptResponseRedactPiiAudioOptionsReturnRedactedNoSpeechAudioDefault,
|
|
11602
|
+
getTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault: () => getTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault,
|
|
11603
|
+
getTranscriptResponseSpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault: () => getTranscriptResponseSpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault,
|
|
11550
11604
|
getTranscriptSentencesParams: () => getTranscriptSentencesParams,
|
|
11551
11605
|
getTranscriptSentencesResponse: () => getTranscriptSentencesResponse,
|
|
11552
|
-
getTranscriptSentencesResponseConfidenceMax: () => getTranscriptSentencesResponseConfidenceMax,
|
|
11553
|
-
getTranscriptSentencesResponseConfidenceMin: () => getTranscriptSentencesResponseConfidenceMin,
|
|
11554
|
-
getTranscriptSentencesResponseSentencesItemConfidenceMax: () => getTranscriptSentencesResponseSentencesItemConfidenceMax,
|
|
11555
|
-
getTranscriptSentencesResponseSentencesItemConfidenceMin: () => getTranscriptSentencesResponseSentencesItemConfidenceMin,
|
|
11556
|
-
getTranscriptSentencesResponseSentencesItemWordsItemConfidenceMax: () => getTranscriptSentencesResponseSentencesItemWordsItemConfidenceMax,
|
|
11557
|
-
getTranscriptSentencesResponseSentencesItemWordsItemConfidenceMin: () => getTranscriptSentencesResponseSentencesItemWordsItemConfidenceMin,
|
|
11558
|
-
lemurQuestionAnswerBody: () => lemurQuestionAnswerBody,
|
|
11559
|
-
lemurQuestionAnswerBodyFinalModelDefault: () => lemurQuestionAnswerBodyFinalModelDefault,
|
|
11560
|
-
lemurQuestionAnswerBodyMaxOutputSizeDefault: () => lemurQuestionAnswerBodyMaxOutputSizeDefault,
|
|
11561
|
-
lemurQuestionAnswerBodyTemperatureDefault: () => lemurQuestionAnswerBodyTemperatureDefault,
|
|
11562
|
-
lemurQuestionAnswerBodyTemperatureMax: () => lemurQuestionAnswerBodyTemperatureMax,
|
|
11563
|
-
lemurQuestionAnswerBodyTemperatureMin: () => lemurQuestionAnswerBodyTemperatureMin,
|
|
11564
|
-
lemurQuestionAnswerResponse: () => lemurQuestionAnswerResponse,
|
|
11565
|
-
lemurQuestionAnswerResponseUsageInputTokensMin: () => lemurQuestionAnswerResponseUsageInputTokensMin,
|
|
11566
|
-
lemurQuestionAnswerResponseUsageOutputTokensMin: () => lemurQuestionAnswerResponseUsageOutputTokensMin,
|
|
11567
|
-
lemurSummaryBody: () => lemurSummaryBody,
|
|
11568
|
-
lemurSummaryBodyFinalModelDefault: () => lemurSummaryBodyFinalModelDefault,
|
|
11569
|
-
lemurSummaryBodyMaxOutputSizeDefault: () => lemurSummaryBodyMaxOutputSizeDefault,
|
|
11570
|
-
lemurSummaryBodyTemperatureDefault: () => lemurSummaryBodyTemperatureDefault,
|
|
11571
|
-
lemurSummaryBodyTemperatureMax: () => lemurSummaryBodyTemperatureMax,
|
|
11572
|
-
lemurSummaryBodyTemperatureMin: () => lemurSummaryBodyTemperatureMin,
|
|
11573
|
-
lemurSummaryResponse: () => lemurSummaryResponse,
|
|
11574
|
-
lemurSummaryResponseUsageInputTokensMin: () => lemurSummaryResponseUsageInputTokensMin,
|
|
11575
|
-
lemurSummaryResponseUsageOutputTokensMin: () => lemurSummaryResponseUsageOutputTokensMin,
|
|
11576
|
-
lemurTaskBody: () => lemurTaskBody,
|
|
11577
|
-
lemurTaskBodyFinalModelDefault: () => lemurTaskBodyFinalModelDefault,
|
|
11578
|
-
lemurTaskBodyMaxOutputSizeDefault: () => lemurTaskBodyMaxOutputSizeDefault,
|
|
11579
|
-
lemurTaskBodyTemperatureDefault: () => lemurTaskBodyTemperatureDefault,
|
|
11580
|
-
lemurTaskBodyTemperatureMax: () => lemurTaskBodyTemperatureMax,
|
|
11581
|
-
lemurTaskBodyTemperatureMin: () => lemurTaskBodyTemperatureMin,
|
|
11582
|
-
lemurTaskResponse: () => lemurTaskResponse,
|
|
11583
|
-
lemurTaskResponseUsageInputTokensMin: () => lemurTaskResponseUsageInputTokensMin,
|
|
11584
|
-
lemurTaskResponseUsageOutputTokensMin: () => lemurTaskResponseUsageOutputTokensMin,
|
|
11585
11606
|
listTranscriptsQueryLimitDefault: () => listTranscriptsQueryLimitDefault,
|
|
11586
|
-
listTranscriptsQueryLimitMax: () => listTranscriptsQueryLimitMax,
|
|
11587
11607
|
listTranscriptsQueryParams: () => listTranscriptsQueryParams,
|
|
11588
11608
|
listTranscriptsQueryThrottledOnlyDefault: () => listTranscriptsQueryThrottledOnlyDefault,
|
|
11589
11609
|
listTranscriptsResponse: () => listTranscriptsResponse,
|
|
11590
|
-
listTranscriptsResponseTranscriptsItemCompletedRegExp: () => listTranscriptsResponseTranscriptsItemCompletedRegExp,
|
|
11591
|
-
listTranscriptsResponseTranscriptsItemCreatedRegExp: () => listTranscriptsResponseTranscriptsItemCreatedRegExp,
|
|
11592
|
-
purgeLemurRequestDataParams: () => purgeLemurRequestDataParams,
|
|
11593
|
-
purgeLemurRequestDataResponse: () => purgeLemurRequestDataResponse,
|
|
11594
11610
|
uploadFileResponse: () => uploadFileResponse,
|
|
11595
11611
|
wordSearchParams: () => wordSearchParams,
|
|
11596
11612
|
wordSearchQueryParams: () => wordSearchQueryParams,
|
|
@@ -11600,43 +11616,192 @@ import { z as zod3 } from "zod";
|
|
|
11600
11616
|
var uploadFileResponse = zod3.object({
|
|
11601
11617
|
upload_url: zod3.string().describe("A URL that points to your audio file, accessible only by AssemblyAI's servers\n")
|
|
11602
11618
|
});
|
|
11603
|
-
var
|
|
11604
|
-
var createTranscriptBodyLanguageDetectionDefault = false;
|
|
11605
|
-
var createTranscriptBodyLanguageConfidenceThresholdDefault = 0;
|
|
11606
|
-
var createTranscriptBodyLanguageConfidenceThresholdMin = 0;
|
|
11607
|
-
var createTranscriptBodyLanguageConfidenceThresholdMax = 1;
|
|
11608
|
-
var createTranscriptBodySpeechModelDefault = "best";
|
|
11609
|
-
var createTranscriptBodyPunctuateDefault = true;
|
|
11610
|
-
var createTranscriptBodyFormatTextDefault = true;
|
|
11611
|
-
var createTranscriptBodyDisfluenciesDefault = false;
|
|
11612
|
-
var createTranscriptBodyMultichannelDefault = false;
|
|
11613
|
-
var createTranscriptBodyWebhookAuthHeaderNameDefault = null;
|
|
11614
|
-
var createTranscriptBodyWebhookAuthHeaderValueDefault = null;
|
|
11619
|
+
var createTranscriptBodyAutoChaptersDefault = false;
|
|
11615
11620
|
var createTranscriptBodyAutoHighlightsDefault = false;
|
|
11616
|
-
var createTranscriptBodyFilterProfanityDefault = false;
|
|
11617
|
-
var createTranscriptBodyRedactPiiDefault = false;
|
|
11618
|
-
var createTranscriptBodyRedactPiiAudioDefault = false;
|
|
11619
|
-
var createTranscriptBodyRedactPiiSubDefault = "hash";
|
|
11620
|
-
var createTranscriptBodySpeakerLabelsDefault = false;
|
|
11621
|
-
var createTranscriptBodySpeakersExpectedDefault = null;
|
|
11622
11621
|
var createTranscriptBodyContentSafetyDefault = false;
|
|
11623
11622
|
var createTranscriptBodyContentSafetyConfidenceDefault = 50;
|
|
11624
|
-
var
|
|
11625
|
-
var
|
|
11623
|
+
var createTranscriptBodyDisfluenciesDefault = false;
|
|
11624
|
+
var createTranscriptBodyEntityDetectionDefault = false;
|
|
11625
|
+
var createTranscriptBodyFilterProfanityDefault = false;
|
|
11626
|
+
var createTranscriptBodyFormatTextDefault = true;
|
|
11626
11627
|
var createTranscriptBodyIabCategoriesDefault = false;
|
|
11628
|
+
var createTranscriptBodyLanguageDetectionDefault = false;
|
|
11629
|
+
var createTranscriptBodyLanguageDetectionOptionsFallbackLanguageDefault = "auto";
|
|
11630
|
+
var createTranscriptBodyLanguageDetectionOptionsCodeSwitchingDefault = false;
|
|
11631
|
+
var createTranscriptBodyLanguageDetectionOptionsCodeSwitchingConfidenceThresholdDefault = 0.3;
|
|
11632
|
+
var createTranscriptBodyMultichannelDefault = false;
|
|
11633
|
+
var createTranscriptBodyPunctuateDefault = true;
|
|
11634
|
+
var createTranscriptBodyRedactPiiDefault = false;
|
|
11635
|
+
var createTranscriptBodyRedactPiiAudioDefault = false;
|
|
11636
|
+
var createTranscriptBodyRedactPiiAudioOptionsReturnRedactedNoSpeechAudioDefault = false;
|
|
11627
11637
|
var createTranscriptBodySentimentAnalysisDefault = false;
|
|
11628
|
-
var
|
|
11629
|
-
var
|
|
11630
|
-
var
|
|
11631
|
-
var
|
|
11632
|
-
var createTranscriptBodySpeechThresholdMax = 1;
|
|
11638
|
+
var createTranscriptBodySpeakerLabelsDefault = false;
|
|
11639
|
+
var createTranscriptBodySpeakerOptionsMinSpeakersExpectedDefault = 1;
|
|
11640
|
+
var createTranscriptBodySpeechUnderstandingRequestTranslationFormalDefault = true;
|
|
11641
|
+
var createTranscriptBodySpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault = false;
|
|
11633
11642
|
var createTranscriptBodySummarizationDefault = false;
|
|
11643
|
+
var createTranscriptBodyTemperatureDefault = 0;
|
|
11634
11644
|
var createTranscriptBodyCustomTopicsDefault = false;
|
|
11635
11645
|
var createTranscriptBody = zod3.object({
|
|
11636
|
-
|
|
11637
|
-
|
|
11638
|
-
|
|
11639
|
-
|
|
11646
|
+
audio_end_at: zod3.number().optional().describe(
|
|
11647
|
+
"The point in time, in milliseconds, to stop transcribing in your media file. See [Set the start and end of the transcript](https://www.assemblyai.com/docs/pre-recorded-audio/set-the-start-and-end-of-the-transcript) for more details."
|
|
11648
|
+
),
|
|
11649
|
+
audio_start_from: zod3.number().optional().describe(
|
|
11650
|
+
"The point in time, in milliseconds, to begin transcribing in your media file. See [Set the start and end of the transcript](https://www.assemblyai.com/docs/pre-recorded-audio/set-the-start-and-end-of-the-transcript) for more details."
|
|
11651
|
+
),
|
|
11652
|
+
auto_chapters: zod3.boolean().optional().describe(
|
|
11653
|
+
"Enable [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/auto-chapters), can be true or false. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible chapter summaries. See the [updated Auto Chapters page](https://www.assemblyai.com/docs/speech-understanding/auto-chapters) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
11654
|
+
),
|
|
11655
|
+
auto_highlights: zod3.boolean().optional().describe(
|
|
11656
|
+
"Enable [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/key-phrases), either true or false"
|
|
11657
|
+
),
|
|
11658
|
+
content_safety: zod3.boolean().optional().describe(
|
|
11659
|
+
"Enable [Content Moderation](https://www.assemblyai.com/docs/content-moderation), can be true or false"
|
|
11660
|
+
),
|
|
11661
|
+
content_safety_confidence: zod3.number().default(createTranscriptBodyContentSafetyConfidenceDefault).describe(
|
|
11662
|
+
"The confidence threshold for the [Content Moderation](https://www.assemblyai.com/docs/content-moderation) model. Values must be between 25 and 100."
|
|
11663
|
+
),
|
|
11664
|
+
custom_spelling: zod3.array(
|
|
11665
|
+
zod3.object({
|
|
11666
|
+
from: zod3.array(zod3.string()).describe("Words or phrases to replace"),
|
|
11667
|
+
to: zod3.string().describe("Word to replace with")
|
|
11668
|
+
}).describe(
|
|
11669
|
+
"Object containing words or phrases to replace, and the word or phrase to replace with"
|
|
11670
|
+
)
|
|
11671
|
+
).optional().describe(
|
|
11672
|
+
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/custom-spelling) for more details."
|
|
11673
|
+
),
|
|
11674
|
+
disfluencies: zod3.boolean().optional().describe(
|
|
11675
|
+
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/filler-words), like "umm", in your media file; can be true or false'
|
|
11676
|
+
),
|
|
11677
|
+
domain: zod3.string().nullish().describe(
|
|
11678
|
+
'Enable domain-specific transcription models to improve accuracy for specialized terminology. Set to `"medical-v1"` to enable [Medical Mode](https://www.assemblyai.com/docs/pre-recorded-audio/medical-mode) for improved accuracy of medical terms such as medications, procedures, conditions, and dosages.\n\nSupported languages: English (`en`), Spanish (`es`), German (`de`), French (`fr`). If used with an unsupported language, the parameter is ignored and a warning is returned.\n'
|
|
11679
|
+
),
|
|
11680
|
+
entity_detection: zod3.boolean().optional().describe(
|
|
11681
|
+
"Enable [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/entity-detection), can be true or false"
|
|
11682
|
+
),
|
|
11683
|
+
filter_profanity: zod3.boolean().optional().describe(
|
|
11684
|
+
"Filter profanity from the transcribed text, can be true or false. See [Profanity Filtering](https://www.assemblyai.com/docs/profanity-filtering) for more details."
|
|
11685
|
+
),
|
|
11686
|
+
format_text: zod3.boolean().default(createTranscriptBodyFormatTextDefault).describe(
|
|
11687
|
+
"Enable [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio), can be true or false"
|
|
11688
|
+
),
|
|
11689
|
+
iab_categories: zod3.boolean().optional().describe(
|
|
11690
|
+
"Enable [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/topic-detection), can be true or false"
|
|
11691
|
+
),
|
|
11692
|
+
keyterms_prompt: zod3.array(zod3.string()).optional().describe(
|
|
11693
|
+
"Improve accuracy with up to 200 (for Universal-2) or 1000 (for Universal-3 Pro) domain-specific words or phrases (maximum 6 words per phrase). See [Keyterms Prompting](https://www.assemblyai.com/docs/pre-recorded-audio/keyterms-prompting) for more details.\n"
|
|
11694
|
+
),
|
|
11695
|
+
language_code: zod3.enum([
|
|
11696
|
+
"en",
|
|
11697
|
+
"en_au",
|
|
11698
|
+
"en_uk",
|
|
11699
|
+
"en_us",
|
|
11700
|
+
"es",
|
|
11701
|
+
"fr",
|
|
11702
|
+
"de",
|
|
11703
|
+
"it",
|
|
11704
|
+
"pt",
|
|
11705
|
+
"nl",
|
|
11706
|
+
"af",
|
|
11707
|
+
"sq",
|
|
11708
|
+
"am",
|
|
11709
|
+
"ar",
|
|
11710
|
+
"hy",
|
|
11711
|
+
"as",
|
|
11712
|
+
"az",
|
|
11713
|
+
"ba",
|
|
11714
|
+
"eu",
|
|
11715
|
+
"be",
|
|
11716
|
+
"bn",
|
|
11717
|
+
"bs",
|
|
11718
|
+
"br",
|
|
11719
|
+
"bg",
|
|
11720
|
+
"my",
|
|
11721
|
+
"ca",
|
|
11722
|
+
"zh",
|
|
11723
|
+
"hr",
|
|
11724
|
+
"cs",
|
|
11725
|
+
"da",
|
|
11726
|
+
"et",
|
|
11727
|
+
"fo",
|
|
11728
|
+
"fi",
|
|
11729
|
+
"gl",
|
|
11730
|
+
"ka",
|
|
11731
|
+
"el",
|
|
11732
|
+
"gu",
|
|
11733
|
+
"ht",
|
|
11734
|
+
"ha",
|
|
11735
|
+
"haw",
|
|
11736
|
+
"he",
|
|
11737
|
+
"hi",
|
|
11738
|
+
"hu",
|
|
11739
|
+
"is",
|
|
11740
|
+
"id",
|
|
11741
|
+
"ja",
|
|
11742
|
+
"jw",
|
|
11743
|
+
"kn",
|
|
11744
|
+
"kk",
|
|
11745
|
+
"km",
|
|
11746
|
+
"ko",
|
|
11747
|
+
"lo",
|
|
11748
|
+
"la",
|
|
11749
|
+
"lv",
|
|
11750
|
+
"ln",
|
|
11751
|
+
"lt",
|
|
11752
|
+
"lb",
|
|
11753
|
+
"mk",
|
|
11754
|
+
"mg",
|
|
11755
|
+
"ms",
|
|
11756
|
+
"ml",
|
|
11757
|
+
"mt",
|
|
11758
|
+
"mi",
|
|
11759
|
+
"mr",
|
|
11760
|
+
"mn",
|
|
11761
|
+
"ne",
|
|
11762
|
+
"no",
|
|
11763
|
+
"nn",
|
|
11764
|
+
"oc",
|
|
11765
|
+
"pa",
|
|
11766
|
+
"ps",
|
|
11767
|
+
"fa",
|
|
11768
|
+
"pl",
|
|
11769
|
+
"ro",
|
|
11770
|
+
"ru",
|
|
11771
|
+
"sa",
|
|
11772
|
+
"sr",
|
|
11773
|
+
"sn",
|
|
11774
|
+
"sd",
|
|
11775
|
+
"si",
|
|
11776
|
+
"sk",
|
|
11777
|
+
"sl",
|
|
11778
|
+
"so",
|
|
11779
|
+
"su",
|
|
11780
|
+
"sw",
|
|
11781
|
+
"sv",
|
|
11782
|
+
"tl",
|
|
11783
|
+
"tg",
|
|
11784
|
+
"ta",
|
|
11785
|
+
"tt",
|
|
11786
|
+
"te",
|
|
11787
|
+
"th",
|
|
11788
|
+
"bo",
|
|
11789
|
+
"tr",
|
|
11790
|
+
"tk",
|
|
11791
|
+
"uk",
|
|
11792
|
+
"ur",
|
|
11793
|
+
"uz",
|
|
11794
|
+
"vi",
|
|
11795
|
+
"cy",
|
|
11796
|
+
"yi",
|
|
11797
|
+
"yo"
|
|
11798
|
+
]).describe(
|
|
11799
|
+
"The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/pre-recorded-audio/supported-languages).\nThe default value is 'en_us'.\n"
|
|
11800
|
+
).or(zod3.null()).optional().describe(
|
|
11801
|
+
"The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/pre-recorded-audio/supported-languages).\nThe default value is 'en_us'.\n"
|
|
11802
|
+
),
|
|
11803
|
+
language_codes: zod3.array(
|
|
11804
|
+
zod3.enum([
|
|
11640
11805
|
"en",
|
|
11641
11806
|
"en_au",
|
|
11642
11807
|
"en_uk",
|
|
@@ -11740,53 +11905,365 @@ var createTranscriptBody = zod3.object({
|
|
|
11740
11905
|
"yi",
|
|
11741
11906
|
"yo"
|
|
11742
11907
|
]).describe(
|
|
11743
|
-
"The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/
|
|
11744
|
-
)
|
|
11745
|
-
|
|
11746
|
-
)
|
|
11747
|
-
|
|
11748
|
-
|
|
11749
|
-
)
|
|
11750
|
-
|
|
11751
|
-
|
|
11752
|
-
),
|
|
11753
|
-
|
|
11754
|
-
|
|
11755
|
-
)
|
|
11756
|
-
|
|
11757
|
-
format_text: zod3.boolean().default(createTranscriptBodyFormatTextDefault).describe("Enable Text Formatting, can be true or false"),
|
|
11758
|
-
disfluencies: zod3.boolean().optional().describe(
|
|
11759
|
-
'Transcribe Filler Words, like "umm", in your media file; can be true or false'
|
|
11760
|
-
),
|
|
11761
|
-
multichannel: zod3.boolean().optional().describe(
|
|
11762
|
-
"Enable [Multichannel](https://www.assemblyai.com/docs/models/speech-recognition#multichannel-transcription) transcription, can be true or false."
|
|
11763
|
-
),
|
|
11764
|
-
webhook_url: zod3.string().optional().describe(
|
|
11765
|
-
"The URL to which we send webhook requests.\nWe sends two different types of webhook requests.\nOne request when a transcript is completed or failed, and one request when the redacted audio is ready if redact_pii_audio is enabled.\n"
|
|
11908
|
+
"The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/pre-recorded-audio/supported-languages).\nThe default value is 'en_us'.\n"
|
|
11909
|
+
)
|
|
11910
|
+
).nullish().describe(
|
|
11911
|
+
"The language codes of your audio file. Used for [Code switching](/docs/speech-to-text/pre-recorded-audio/code-switching)\nOne of the values specified must be `en`.\n"
|
|
11912
|
+
),
|
|
11913
|
+
language_confidence_threshold: zod3.number().optional().describe(
|
|
11914
|
+
"The confidence threshold for the automatically detected language.\nAn error will be returned if the language confidence is below this threshold.\nDefaults to 0. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.\n"
|
|
11915
|
+
),
|
|
11916
|
+
language_detection: zod3.boolean().optional().describe(
|
|
11917
|
+
"Enable [Automatic language detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection), either true or false."
|
|
11918
|
+
),
|
|
11919
|
+
language_detection_options: zod3.object({
|
|
11920
|
+
expected_languages: zod3.array(zod3.string()).optional().describe(
|
|
11921
|
+
'List of languages expected in the audio file. Defaults to `["all"]` when unspecified. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.'
|
|
11766
11922
|
),
|
|
11767
|
-
|
|
11768
|
-
|
|
11923
|
+
fallback_language: zod3.string().default(createTranscriptBodyLanguageDetectionOptionsFallbackLanguageDefault).describe(
|
|
11924
|
+
'If the detected language of the audio file is not in the list of expected languages, the `fallback_language` is used. Specify `["auto"]` to let our model choose the fallback language from `expected_languages` with the highest confidence score. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.\n'
|
|
11769
11925
|
),
|
|
11770
|
-
|
|
11771
|
-
"
|
|
11926
|
+
code_switching: zod3.boolean().optional().describe(
|
|
11927
|
+
"Whether [code switching](/docs/speech-to-text/pre-recorded-audio/code-switching) should be detected.\n"
|
|
11772
11928
|
),
|
|
11773
|
-
|
|
11774
|
-
|
|
11775
|
-
|
|
11776
|
-
|
|
11777
|
-
|
|
11778
|
-
|
|
11779
|
-
|
|
11780
|
-
|
|
11929
|
+
code_switching_confidence_threshold: zod3.number().default(
|
|
11930
|
+
createTranscriptBodyLanguageDetectionOptionsCodeSwitchingConfidenceThresholdDefault
|
|
11931
|
+
).describe(
|
|
11932
|
+
"The confidence threshold for [code switching](/docs/speech-to-text/pre-recorded-audio/code-switching) detection. If the code switching confidence is below this threshold, the transcript will be processed in the language with the highest `language_detection_confidence` score.\n"
|
|
11933
|
+
)
|
|
11934
|
+
}).optional().describe(
|
|
11935
|
+
"Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection)."
|
|
11936
|
+
),
|
|
11937
|
+
multichannel: zod3.boolean().optional().describe(
|
|
11938
|
+
"Enable [Multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/multichannel) transcription, can be true or false."
|
|
11939
|
+
),
|
|
11940
|
+
prompt: zod3.string().optional().describe(
|
|
11941
|
+
"Provide natural language prompting of up to 1,500 words of contextual information to the model. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for best practices.\n\nNote: This parameter is only supported for the Universal-3 Pro model.\n"
|
|
11942
|
+
),
|
|
11943
|
+
punctuate: zod3.boolean().default(createTranscriptBodyPunctuateDefault).describe(
|
|
11944
|
+
"Enable [Automatic Punctuation](https://www.assemblyai.com/docs/pre-recorded-audio), can be true or false"
|
|
11945
|
+
),
|
|
11946
|
+
redact_pii: zod3.boolean().optional().describe(
|
|
11947
|
+
"Redact PII from the transcribed text using the Redact PII model, can be true or false. See [PII Redaction](https://www.assemblyai.com/docs/pii-redaction) for more details."
|
|
11948
|
+
),
|
|
11949
|
+
redact_pii_audio: zod3.boolean().optional().describe(
|
|
11950
|
+
'Generate a copy of the original media file with spoken PII "beeped" out, can be true or false. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more details.'
|
|
11951
|
+
),
|
|
11952
|
+
redact_pii_audio_options: zod3.object({
|
|
11953
|
+
return_redacted_no_speech_audio: zod3.boolean().optional().describe(
|
|
11954
|
+
"By default, audio redaction provides redacted audio URLs only when speech is detected. However, if your use-case specifically requires redacted audio files even for silent audio files without any dialogue, you can opt to receive these URLs by setting this parameter to `true`."
|
|
11781
11955
|
),
|
|
11782
|
-
|
|
11783
|
-
|
|
11956
|
+
override_audio_redaction_method: zod3.enum(["silence"]).optional().describe(
|
|
11957
|
+
"Specify the method used to redact audio. By default, redacted audio uses a beep sound. Set to `silence` to replace PII with silence instead of a beep."
|
|
11958
|
+
)
|
|
11959
|
+
}).optional().describe(
|
|
11960
|
+
"Specify options for [PII redacted audio](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) files."
|
|
11961
|
+
),
|
|
11962
|
+
redact_pii_audio_quality: zod3.enum(["mp3", "wav"]).optional().describe(
|
|
11963
|
+
"Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more details."
|
|
11964
|
+
),
|
|
11965
|
+
redact_pii_policies: zod3.array(
|
|
11966
|
+
zod3.enum([
|
|
11967
|
+
"account_number",
|
|
11968
|
+
"banking_information",
|
|
11969
|
+
"blood_type",
|
|
11970
|
+
"credit_card_cvv",
|
|
11971
|
+
"credit_card_expiration",
|
|
11972
|
+
"credit_card_number",
|
|
11973
|
+
"date",
|
|
11974
|
+
"date_interval",
|
|
11975
|
+
"date_of_birth",
|
|
11976
|
+
"drivers_license",
|
|
11977
|
+
"drug",
|
|
11978
|
+
"duration",
|
|
11979
|
+
"email_address",
|
|
11980
|
+
"event",
|
|
11981
|
+
"filename",
|
|
11982
|
+
"gender_sexuality",
|
|
11983
|
+
"healthcare_number",
|
|
11984
|
+
"injury",
|
|
11985
|
+
"ip_address",
|
|
11986
|
+
"language",
|
|
11987
|
+
"location",
|
|
11988
|
+
"marital_status",
|
|
11989
|
+
"medical_condition",
|
|
11990
|
+
"medical_process",
|
|
11991
|
+
"money_amount",
|
|
11992
|
+
"nationality",
|
|
11993
|
+
"number_sequence",
|
|
11994
|
+
"occupation",
|
|
11995
|
+
"organization",
|
|
11996
|
+
"passport_number",
|
|
11997
|
+
"password",
|
|
11998
|
+
"person_age",
|
|
11999
|
+
"person_name",
|
|
12000
|
+
"phone_number",
|
|
12001
|
+
"physical_attribute",
|
|
12002
|
+
"political_affiliation",
|
|
12003
|
+
"religion",
|
|
12004
|
+
"statistics",
|
|
12005
|
+
"time",
|
|
12006
|
+
"url",
|
|
12007
|
+
"us_social_security_number",
|
|
12008
|
+
"username",
|
|
12009
|
+
"vehicle_id",
|
|
12010
|
+
"zodiac_sign"
|
|
12011
|
+
]).describe("The type of PII to redact")
|
|
12012
|
+
).optional().describe(
|
|
12013
|
+
"The list of PII Redaction policies to enable. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more details."
|
|
12014
|
+
),
|
|
12015
|
+
redact_pii_sub: zod3.enum(["entity_name", "hash"]).describe(
|
|
12016
|
+
"The replacement logic for detected PII, can be `entity_name` or `hash`. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more details."
|
|
12017
|
+
).or(zod3.null()).optional().describe(
|
|
12018
|
+
"The replacement logic for detected PII, can be `entity_type` or `hash`. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more details."
|
|
12019
|
+
),
|
|
12020
|
+
sentiment_analysis: zod3.boolean().optional().describe(
|
|
12021
|
+
"Enable [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-analysis), can be true or false"
|
|
12022
|
+
),
|
|
12023
|
+
speaker_labels: zod3.boolean().optional().describe(
|
|
12024
|
+
"Enable [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization), can be true or false"
|
|
12025
|
+
),
|
|
12026
|
+
speaker_options: zod3.object({
|
|
12027
|
+
min_speakers_expected: zod3.number().default(createTranscriptBodySpeakerOptionsMinSpeakersExpectedDefault).describe(
|
|
12028
|
+
"The minimum number of speakers expected in the audio file. See [Set a range of possible speakers](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization#set-a-range-of-possible-speakers) for more details."
|
|
11784
12029
|
),
|
|
11785
|
-
|
|
11786
|
-
"
|
|
12030
|
+
max_speakers_expected: zod3.number().optional().describe(
|
|
12031
|
+
"<Warning>Setting this parameter too high may hurt model accuracy</Warning>\nThe maximum number of speakers expected in the audio file. The default depends on audio duration: no limit for 0-2 minutes, 10 for 2-10 minutes, and 30 for 10+ minutes. See [Set a range of possible speakers](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization#set-a-range-of-possible-speakers) for more details.\n"
|
|
12032
|
+
)
|
|
12033
|
+
}).optional().describe(
|
|
12034
|
+
"Specify options for [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization#set-a-range-of-possible-speakers). Use this to set a range of possible speakers."
|
|
12035
|
+
),
|
|
12036
|
+
speakers_expected: zod3.number().nullish().describe(
|
|
12037
|
+
"Tells the speaker label model how many speakers it should attempt to identify. See [Set number of speakers expected](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization#set-number-of-speakers-expected) for more details."
|
|
12038
|
+
),
|
|
12039
|
+
speech_models: zod3.array(
|
|
12040
|
+
zod3.string().describe(
|
|
12041
|
+
"The speech model to use for the transcription. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models."
|
|
12042
|
+
)
|
|
12043
|
+
).describe(
|
|
12044
|
+
"List multiple speech models in priority order, allowing our system to automatically route your audio to the best available option. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models and routing behavior.\n"
|
|
12045
|
+
),
|
|
12046
|
+
speech_threshold: zod3.number().nullish().describe(
|
|
12047
|
+
"Reject audio files that contain less than this fraction of speech.\nValid values are in the range [0, 1] inclusive. See [Speech Threshold](https://www.assemblyai.com/docs/speech-threshold) for more details.\n"
|
|
12048
|
+
),
|
|
12049
|
+
speech_understanding: zod3.object({
|
|
12050
|
+
request: zod3.object({
|
|
12051
|
+
translation: zod3.object({
|
|
12052
|
+
target_languages: zod3.array(zod3.string()).describe(
|
|
12053
|
+
'List of target language codes (e.g., `["es", "de"]`). See [Translation](https://www.assemblyai.com/docs/speech-understanding/translation) for supported languages.'
|
|
12054
|
+
),
|
|
12055
|
+
formal: zod3.boolean().default(createTranscriptBodySpeechUnderstandingRequestTranslationFormalDefault).describe(
|
|
12056
|
+
"Use formal language style. See [Translation](https://www.assemblyai.com/docs/speech-understanding/translation) for more details."
|
|
12057
|
+
),
|
|
12058
|
+
match_original_utterance: zod3.boolean().optional().describe(
|
|
12059
|
+
"When enabled with Speaker Labels, returns translated text in the utterances array. Each utterance will include a `translated_texts` key containing translations for each target language."
|
|
12060
|
+
)
|
|
12061
|
+
})
|
|
12062
|
+
}).describe(
|
|
12063
|
+
"Request body for [Translation](https://www.assemblyai.com/docs/speech-understanding/translation)."
|
|
12064
|
+
).or(
|
|
12065
|
+
zod3.object({
|
|
12066
|
+
speaker_identification: zod3.object({
|
|
12067
|
+
speaker_type: zod3.enum(["role", "name"]).describe(
|
|
12068
|
+
"Type of speaker identification. See [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification) for details on each type."
|
|
12069
|
+
),
|
|
12070
|
+
known_values: zod3.array(zod3.string()).optional().describe(
|
|
12071
|
+
'Required if speaker_type is "role". Each value must be 35 characters or less.'
|
|
12072
|
+
),
|
|
12073
|
+
speakers: zod3.array(
|
|
12074
|
+
zod3.object({
|
|
12075
|
+
role: zod3.string().optional().describe(
|
|
12076
|
+
'The role of the speaker. Required when `speaker_type` is "role".'
|
|
12077
|
+
),
|
|
12078
|
+
name: zod3.string().optional().describe(
|
|
12079
|
+
'The name of the speaker. Required when `speaker_type` is "name".'
|
|
12080
|
+
),
|
|
12081
|
+
description: zod3.string().optional().describe(
|
|
12082
|
+
"A description of the speaker to help the model identify them based on conversational context."
|
|
12083
|
+
)
|
|
12084
|
+
})
|
|
12085
|
+
).optional().describe(
|
|
12086
|
+
"An array of speaker objects with metadata to improve identification accuracy. Each object should include a `role` or `name` (depending on `speaker_type`) and an optional `description` to help the model identify the speaker. You can also include any additional custom properties (e.g., `company`, `title`) to provide more context. Use this as an alternative to `known_values` when you want to provide additional context about each speaker."
|
|
12087
|
+
)
|
|
12088
|
+
})
|
|
12089
|
+
}).describe(
|
|
12090
|
+
"Request body for [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification)."
|
|
12091
|
+
)
|
|
12092
|
+
).or(
|
|
12093
|
+
zod3.object({
|
|
12094
|
+
custom_formatting: zod3.object({
|
|
12095
|
+
date: zod3.string().optional().describe(
|
|
12096
|
+
'Date format pattern (e.g., `"mm/dd/yyyy"`). See [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting) for more details.'
|
|
12097
|
+
),
|
|
12098
|
+
phone_number: zod3.string().optional().describe(
|
|
12099
|
+
'Phone number format pattern (e.g., `"(xxx)xxx-xxxx"`). See [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting) for more details.'
|
|
12100
|
+
),
|
|
12101
|
+
email: zod3.string().optional().describe(
|
|
12102
|
+
'Email format pattern (e.g., `"username@domain.com"`). See [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting) for more details.'
|
|
12103
|
+
)
|
|
12104
|
+
})
|
|
12105
|
+
}).describe(
|
|
12106
|
+
"Request body for [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting)."
|
|
12107
|
+
)
|
|
12108
|
+
)
|
|
12109
|
+
}).optional().describe(
|
|
12110
|
+
"Enable speech understanding tasks like [Translation](https://www.assemblyai.com/docs/speech-understanding/translation), [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification), and [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting). See the task-specific docs for available options and configuration.\n"
|
|
12111
|
+
),
|
|
12112
|
+
summarization: zod3.boolean().optional().describe(
|
|
12113
|
+
"Enable [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization), can be true or false. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
12114
|
+
),
|
|
12115
|
+
summary_model: zod3.enum(["informative", "conversational", "catchy"]).optional().describe("The model to summarize the transcript"),
|
|
12116
|
+
summary_type: zod3.enum(["bullets", "bullets_verbose", "gist", "headline", "paragraph"]).optional().describe("The type of summary"),
|
|
12117
|
+
remove_audio_tags: zod3.enum(["all"]).describe(
|
|
12118
|
+
'Remove [audio event tags](https://www.assemblyai.com/docs/pre-recorded-audio/universal-3-pro#audio-event-tags) from the transcript text. Set to `"all"` to remove all audio tags.\n\nNote: This parameter is only supported for the Universal-3 Pro model.\n'
|
|
12119
|
+
).or(zod3.null()).optional().describe(
|
|
12120
|
+
'Remove [audio event tags](https://www.assemblyai.com/docs/pre-recorded-audio/universal-3-pro#audio-event-tags) from the transcript text. Set to `"all"` to remove all audio tags.\n\nNote: This parameter is only supported for the Universal-3 Pro model.\n'
|
|
12121
|
+
),
|
|
12122
|
+
temperature: zod3.number().optional().describe(
|
|
12123
|
+
"Control the amount of randomness injected into the model's response. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for more details.\n\nNote: This parameter can only be used with the Universal-3 Pro model.\n"
|
|
12124
|
+
),
|
|
12125
|
+
webhook_auth_header_name: zod3.string().nullish().describe(
|
|
12126
|
+
"The header name to be sent with the transcript completed or failed [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) requests"
|
|
12127
|
+
),
|
|
12128
|
+
webhook_auth_header_value: zod3.string().nullish().describe(
|
|
12129
|
+
"The header value to send back with the transcript completed or failed [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) requests for added security"
|
|
12130
|
+
),
|
|
12131
|
+
webhook_url: zod3.string().optional().describe(
|
|
12132
|
+
"The URL to which we send [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) requests.\n"
|
|
12133
|
+
),
|
|
12134
|
+
custom_topics: zod3.boolean().optional().describe("This parameter does not currently have any functionality attached to it."),
|
|
12135
|
+
speech_model: zod3.string().describe(
|
|
12136
|
+
"The speech model to use for the transcription. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models."
|
|
12137
|
+
).or(zod3.null()).optional().describe(
|
|
12138
|
+
"This parameter has been replaced with the `speech_models` parameter, learn more about the `speech_models` parameter [here](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model).\n"
|
|
12139
|
+
),
|
|
12140
|
+
topics: zod3.array(zod3.string()).optional().describe("This parameter does not currently have any functionality attached to it."),
|
|
12141
|
+
audio_url: zod3.string().describe("The URL of the audio or video file to transcribe.")
|
|
12142
|
+
}).describe("The parameters for creating a transcript");
|
|
12143
|
+
var createTranscriptResponseLanguageDetectionOptionsFallbackLanguageDefault = "auto";
|
|
12144
|
+
var createTranscriptResponseLanguageDetectionOptionsCodeSwitchingDefault = false;
|
|
12145
|
+
var createTranscriptResponseLanguageDetectionOptionsCodeSwitchingConfidenceThresholdDefault = 0.3;
|
|
12146
|
+
var createTranscriptResponseRedactPiiAudioOptionsReturnRedactedNoSpeechAudioDefault = false;
|
|
12147
|
+
var createTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault = true;
|
|
12148
|
+
var createTranscriptResponseSpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault = false;
|
|
12149
|
+
var createTranscriptResponse = zod3.object({
|
|
12150
|
+
audio_channels: zod3.number().optional().describe(
|
|
12151
|
+
"The number of audio channels in the audio file. This is only present when [multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/multichannel) is enabled."
|
|
12152
|
+
),
|
|
12153
|
+
audio_duration: zod3.number().nullish().describe("The duration of this transcript object's media file, in seconds"),
|
|
12154
|
+
audio_end_at: zod3.number().nullish().describe(
|
|
12155
|
+
"The point in time, in milliseconds, in the file at which the transcription was terminated. See [Set the start and end of the transcript](https://www.assemblyai.com/docs/pre-recorded-audio/set-the-start-and-end-of-the-transcript) for more details."
|
|
12156
|
+
),
|
|
12157
|
+
audio_start_from: zod3.number().nullish().describe(
|
|
12158
|
+
"The point in time, in milliseconds, in the file at which the transcription was started. See [Set the start and end of the transcript](https://www.assemblyai.com/docs/pre-recorded-audio/set-the-start-and-end-of-the-transcript) for more details."
|
|
12159
|
+
),
|
|
12160
|
+
audio_url: zod3.string().describe("The URL of the media that was transcribed"),
|
|
12161
|
+
auto_chapters: zod3.boolean().nullish().describe(
|
|
12162
|
+
"Whether [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/auto-chapters) is enabled, can be true or false. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible chapter summaries. See the [updated Auto Chapters page](https://www.assemblyai.com/docs/speech-understanding/auto-chapters) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
12163
|
+
),
|
|
12164
|
+
auto_highlights: zod3.boolean().describe(
|
|
12165
|
+
"Whether [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/key-phrases) is enabled, either true or false"
|
|
12166
|
+
),
|
|
12167
|
+
auto_highlights_result: zod3.object({
|
|
12168
|
+
status: zod3.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
12169
|
+
results: zod3.array(
|
|
12170
|
+
zod3.object({
|
|
12171
|
+
count: zod3.number().describe("The total number of times the key phrase appears in the audio file"),
|
|
12172
|
+
rank: zod3.number().describe(
|
|
12173
|
+
"The total relevancy to the overall audio file of this key phrase - a greater number means more relevant"
|
|
12174
|
+
),
|
|
12175
|
+
text: zod3.string().describe("The text itself of the key phrase"),
|
|
12176
|
+
timestamps: zod3.array(
|
|
12177
|
+
zod3.object({
|
|
12178
|
+
start: zod3.number().describe("The start time in milliseconds"),
|
|
12179
|
+
end: zod3.number().describe("The end time in milliseconds")
|
|
12180
|
+
}).describe("Timestamp containing a start and end property in milliseconds")
|
|
12181
|
+
).describe("The timestamp of the of the key phrase")
|
|
12182
|
+
})
|
|
12183
|
+
).describe("A temporally-sequential array of Key Phrases")
|
|
12184
|
+
}).describe(
|
|
12185
|
+
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key phrases](https://www.assemblyai.com/docs/speech-understanding/key-phrases) for more information.\n"
|
|
12186
|
+
).or(zod3.null()).optional().describe(
|
|
12187
|
+
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/key-phrases) for more information.\n"
|
|
12188
|
+
),
|
|
12189
|
+
chapters: zod3.array(
|
|
12190
|
+
zod3.object({
|
|
12191
|
+
gist: zod3.string().describe(
|
|
12192
|
+
"An ultra-short summary (just a few words) of the content spoken in the chapter"
|
|
12193
|
+
),
|
|
12194
|
+
headline: zod3.string().describe("A single sentence summary of the content spoken during the chapter"),
|
|
12195
|
+
summary: zod3.string().describe("A one paragraph summary of the content spoken during the chapter"),
|
|
12196
|
+
start: zod3.number().describe("The starting time, in milliseconds, for the chapter"),
|
|
12197
|
+
end: zod3.number().describe("The starting time, in milliseconds, for the chapter")
|
|
12198
|
+
}).describe("Chapter of the audio file")
|
|
12199
|
+
).nullish().describe(
|
|
12200
|
+
"An array of temporally sequential chapters for the audio file. See [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/auto-chapters) for more information."
|
|
12201
|
+
),
|
|
12202
|
+
confidence: zod3.number().nullish().describe(
|
|
12203
|
+
"The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence)"
|
|
12204
|
+
),
|
|
12205
|
+
content_safety: zod3.boolean().nullish().describe(
|
|
12206
|
+
"Whether [Content Moderation](https://www.assemblyai.com/docs/content-moderation) is enabled, can be true or false"
|
|
12207
|
+
),
|
|
12208
|
+
content_safety_labels: zod3.object({
|
|
12209
|
+
status: zod3.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
12210
|
+
results: zod3.array(
|
|
12211
|
+
zod3.object({
|
|
12212
|
+
text: zod3.string().describe("The transcript of the section flagged by the Content Moderation model"),
|
|
12213
|
+
labels: zod3.array(
|
|
12214
|
+
zod3.object({
|
|
12215
|
+
label: zod3.string().describe("The label of the sensitive topic"),
|
|
12216
|
+
confidence: zod3.number().describe("The confidence score for the topic being discussed, from 0 to 1"),
|
|
12217
|
+
severity: zod3.number().describe("How severely the topic is discussed in the section, from 0 to 1")
|
|
12218
|
+
})
|
|
12219
|
+
).describe(
|
|
12220
|
+
"An array of safety labels, one per sensitive topic that was detected in the section"
|
|
12221
|
+
),
|
|
12222
|
+
sentences_idx_start: zod3.number().describe("The sentence index at which the section begins"),
|
|
12223
|
+
sentences_idx_end: zod3.number().describe("The sentence index at which the section ends"),
|
|
12224
|
+
timestamp: zod3.object({
|
|
12225
|
+
start: zod3.number().describe("The start time in milliseconds"),
|
|
12226
|
+
end: zod3.number().describe("The end time in milliseconds")
|
|
12227
|
+
}).describe("Timestamp containing a start and end property in milliseconds")
|
|
12228
|
+
})
|
|
12229
|
+
).describe("An array of results for the Content Moderation model"),
|
|
12230
|
+
summary: zod3.record(zod3.string(), zod3.number()).describe(
|
|
12231
|
+
"A summary of the Content Moderation confidence results for the entire audio file"
|
|
11787
12232
|
),
|
|
11788
|
-
|
|
11789
|
-
zod3.
|
|
12233
|
+
severity_score_summary: zod3.record(
|
|
12234
|
+
zod3.string(),
|
|
12235
|
+
zod3.object({
|
|
12236
|
+
low: zod3.number(),
|
|
12237
|
+
medium: zod3.number(),
|
|
12238
|
+
high: zod3.number()
|
|
12239
|
+
})
|
|
12240
|
+
).describe(
|
|
12241
|
+
"A summary of the Content Moderation severity results for the entire audio file"
|
|
12242
|
+
)
|
|
12243
|
+
}).describe(
|
|
12244
|
+
"An array of results for the Content Moderation model, if it is enabled.\nSee [Content moderation](https://www.assemblyai.com/docs/content-moderation) for more information.\n"
|
|
12245
|
+
).or(zod3.null()).optional().describe(
|
|
12246
|
+
"An array of results for the Content Moderation model, if it is enabled.\nSee [Content moderation](https://www.assemblyai.com/docs/content-moderation) for more information.\n"
|
|
12247
|
+
),
|
|
12248
|
+
custom_spelling: zod3.array(
|
|
12249
|
+
zod3.object({
|
|
12250
|
+
from: zod3.array(zod3.string()).describe("Words or phrases to replace"),
|
|
12251
|
+
to: zod3.string().describe("Word to replace with")
|
|
12252
|
+
}).describe(
|
|
12253
|
+
"Object containing words or phrases to replace, and the word or phrase to replace with"
|
|
12254
|
+
)
|
|
12255
|
+
).nullish().describe(
|
|
12256
|
+
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/custom-spelling) for more details."
|
|
12257
|
+
),
|
|
12258
|
+
disfluencies: zod3.boolean().nullish().describe(
|
|
12259
|
+
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/filler-words), like "umm", in your media file; can be true or false'
|
|
12260
|
+
),
|
|
12261
|
+
domain: zod3.string().nullish().describe(
|
|
12262
|
+
'The domain-specific model applied to the transcript. When set to `"medical-v1"`, [Medical Mode](https://www.assemblyai.com/docs/pre-recorded-audio/medical-mode) was used to improve accuracy for medical terminology.\n'
|
|
12263
|
+
),
|
|
12264
|
+
entities: zod3.array(
|
|
12265
|
+
zod3.object({
|
|
12266
|
+
entity_type: zod3.enum([
|
|
11790
12267
|
"account_number",
|
|
11791
12268
|
"banking_information",
|
|
11792
12269
|
"blood_type",
|
|
@@ -11831,103 +12308,59 @@ var createTranscriptBody = zod3.object({
|
|
|
11831
12308
|
"username",
|
|
11832
12309
|
"vehicle_id",
|
|
11833
12310
|
"zodiac_sign"
|
|
11834
|
-
]).describe("The type of
|
|
11835
|
-
|
|
11836
|
-
|
|
11837
|
-
|
|
11838
|
-
|
|
11839
|
-
|
|
11840
|
-
|
|
11841
|
-
'The replacement logic for detected PII, can be "entity_type" or "hash". See [PII redaction](https://www.assemblyai.com/docs/models/pii-redaction) for more details.'
|
|
11842
|
-
),
|
|
11843
|
-
speaker_labels: zod3.boolean().optional().describe(
|
|
11844
|
-
"Enable [Speaker diarization](https://www.assemblyai.com/docs/models/speaker-diarization), can be true or false"
|
|
11845
|
-
),
|
|
11846
|
-
speakers_expected: zod3.number().nullish().describe(
|
|
11847
|
-
"Tells the speaker label model how many speakers it should attempt to identify. See [Speaker diarization](https://www.assemblyai.com/docs/models/speaker-diarization) for more details."
|
|
11848
|
-
),
|
|
11849
|
-
content_safety: zod3.boolean().optional().describe(
|
|
11850
|
-
"Enable [Content Moderation](https://www.assemblyai.com/docs/models/content-moderation), can be true or false"
|
|
11851
|
-
),
|
|
11852
|
-
content_safety_confidence: zod3.number().min(createTranscriptBodyContentSafetyConfidenceMin).max(createTranscriptBodyContentSafetyConfidenceMax).default(createTranscriptBodyContentSafetyConfidenceDefault).describe(
|
|
11853
|
-
"The confidence threshold for the Content Moderation model. Values must be between 25 and 100."
|
|
11854
|
-
),
|
|
11855
|
-
iab_categories: zod3.boolean().optional().describe(
|
|
11856
|
-
"Enable [Topic Detection](https://www.assemblyai.com/docs/models/topic-detection), can be true or false"
|
|
11857
|
-
),
|
|
11858
|
-
custom_spelling: zod3.array(
|
|
11859
|
-
zod3.object({
|
|
11860
|
-
from: zod3.array(zod3.string().describe("Word or phrase to replace")).describe("Words or phrases to replace"),
|
|
11861
|
-
to: zod3.string().describe("Word to replace with")
|
|
11862
|
-
}).describe(
|
|
11863
|
-
"Object containing words or phrases to replace, and the word or phrase to replace with"
|
|
12311
|
+
]).describe("The type of entity for the detected entity"),
|
|
12312
|
+
text: zod3.string().describe("The text for the detected entity"),
|
|
12313
|
+
start: zod3.number().describe(
|
|
12314
|
+
"The starting time, in milliseconds, at which the detected entity appears in the audio file"
|
|
12315
|
+
),
|
|
12316
|
+
end: zod3.number().describe(
|
|
12317
|
+
"The ending time, in milliseconds, for the detected entity in the audio file"
|
|
11864
12318
|
)
|
|
11865
|
-
).
|
|
11866
|
-
|
|
11867
|
-
|
|
11868
|
-
|
|
11869
|
-
|
|
11870
|
-
|
|
11871
|
-
|
|
11872
|
-
|
|
11873
|
-
|
|
11874
|
-
|
|
11875
|
-
|
|
11876
|
-
|
|
11877
|
-
|
|
11878
|
-
|
|
11879
|
-
|
|
11880
|
-
|
|
11881
|
-
|
|
11882
|
-
|
|
11883
|
-
|
|
11884
|
-
|
|
11885
|
-
|
|
11886
|
-
|
|
11887
|
-
|
|
11888
|
-
|
|
11889
|
-
|
|
11890
|
-
).describe(
|
|
11891
|
-
|
|
11892
|
-
|
|
11893
|
-
|
|
11894
|
-
|
|
11895
|
-
|
|
11896
|
-
|
|
11897
|
-
|
|
11898
|
-
|
|
11899
|
-
|
|
11900
|
-
|
|
11901
|
-
|
|
11902
|
-
|
|
11903
|
-
|
|
11904
|
-
|
|
11905
|
-
|
|
11906
|
-
|
|
11907
|
-
var createTranscriptResponseContentSafetyLabelsResultsItemLabelsItemConfidenceMax = 1;
|
|
11908
|
-
var createTranscriptResponseContentSafetyLabelsResultsItemLabelsItemSeverityMin = 0;
|
|
11909
|
-
var createTranscriptResponseContentSafetyLabelsResultsItemLabelsItemSeverityMax = 1;
|
|
11910
|
-
var createTranscriptResponseContentSafetyLabelsSummaryMinOne = 0;
|
|
11911
|
-
var createTranscriptResponseContentSafetyLabelsSummaryMaxOne = 1;
|
|
11912
|
-
var createTranscriptResponseContentSafetyLabelsSeverityScoreSummaryLowMin = 0;
|
|
11913
|
-
var createTranscriptResponseContentSafetyLabelsSeverityScoreSummaryLowMax = 1;
|
|
11914
|
-
var createTranscriptResponseContentSafetyLabelsSeverityScoreSummaryMediumMin = 0;
|
|
11915
|
-
var createTranscriptResponseContentSafetyLabelsSeverityScoreSummaryMediumMax = 1;
|
|
11916
|
-
var createTranscriptResponseContentSafetyLabelsSeverityScoreSummaryHighMin = 0;
|
|
11917
|
-
var createTranscriptResponseContentSafetyLabelsSeverityScoreSummaryHighMax = 1;
|
|
11918
|
-
var createTranscriptResponseIabCategoriesResultResultsItemLabelsItemRelevanceMin = 0;
|
|
11919
|
-
var createTranscriptResponseIabCategoriesResultResultsItemLabelsItemRelevanceMax = 1;
|
|
11920
|
-
var createTranscriptResponseIabCategoriesResultSummaryMinOne = 0;
|
|
11921
|
-
var createTranscriptResponseIabCategoriesResultSummaryMaxOne = 1;
|
|
11922
|
-
var createTranscriptResponseSentimentAnalysisResultsItemConfidenceMin = 0;
|
|
11923
|
-
var createTranscriptResponseSentimentAnalysisResultsItemConfidenceMax = 1;
|
|
11924
|
-
var createTranscriptResponseSpeechThresholdMin = 0;
|
|
11925
|
-
var createTranscriptResponseSpeechThresholdMax = 1;
|
|
11926
|
-
var createTranscriptResponse = zod3.object({
|
|
12319
|
+
}).describe("A detected entity")
|
|
12320
|
+
).nullish().describe(
|
|
12321
|
+
"An array of results for the Entity Detection model, if it is enabled.\nSee [Entity detection](https://www.assemblyai.com/docs/speech-understanding/entity-detection) for more information.\n"
|
|
12322
|
+
),
|
|
12323
|
+
entity_detection: zod3.boolean().nullish().describe(
|
|
12324
|
+
"Whether [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/entity-detection) is enabled, can be true or false"
|
|
12325
|
+
),
|
|
12326
|
+
error: zod3.string().optional().describe("Error message of why the transcript failed"),
|
|
12327
|
+
filter_profanity: zod3.boolean().nullish().describe(
|
|
12328
|
+
"Whether [Profanity Filtering](https://www.assemblyai.com/docs/profanity-filtering) is enabled, either true or false"
|
|
12329
|
+
),
|
|
12330
|
+
format_text: zod3.boolean().nullish().describe(
|
|
12331
|
+
"Whether [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio) is enabled, either true or false"
|
|
12332
|
+
),
|
|
12333
|
+
iab_categories: zod3.boolean().nullish().describe(
|
|
12334
|
+
"Whether [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/topic-detection) is enabled, can be true or false"
|
|
12335
|
+
),
|
|
12336
|
+
iab_categories_result: zod3.object({
|
|
12337
|
+
status: zod3.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
12338
|
+
results: zod3.array(
|
|
12339
|
+
zod3.object({
|
|
12340
|
+
text: zod3.string().describe("The text in the transcript in which a detected topic occurs"),
|
|
12341
|
+
labels: zod3.array(
|
|
12342
|
+
zod3.object({
|
|
12343
|
+
relevance: zod3.number().describe("How relevant the detected topic is of a detected topic"),
|
|
12344
|
+
label: zod3.string().describe(
|
|
12345
|
+
"The IAB taxonomical label for the label of the detected topic, where > denotes supertopic/subtopic relationship"
|
|
12346
|
+
)
|
|
12347
|
+
})
|
|
12348
|
+
).optional().describe("An array of detected topics in the text"),
|
|
12349
|
+
timestamp: zod3.object({
|
|
12350
|
+
start: zod3.number().describe("The start time in milliseconds"),
|
|
12351
|
+
end: zod3.number().describe("The end time in milliseconds")
|
|
12352
|
+
}).optional().describe("Timestamp containing a start and end property in milliseconds")
|
|
12353
|
+
}).describe("The result of the topic detection model")
|
|
12354
|
+
).describe("An array of results for the Topic Detection model"),
|
|
12355
|
+
summary: zod3.record(zod3.string(), zod3.number()).describe("The overall relevance of topic to the entire audio file")
|
|
12356
|
+
}).describe(
|
|
12357
|
+
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/topic-detection) for more information.\n"
|
|
12358
|
+
).or(zod3.null()).optional().describe(
|
|
12359
|
+
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/topic-detection) for more information.\n"
|
|
12360
|
+
),
|
|
11927
12361
|
id: zod3.string().uuid().describe("The unique identifier of your transcript"),
|
|
11928
|
-
|
|
11929
|
-
|
|
11930
|
-
"The status of your transcript. Possible values are queued, processing, completed, or error."
|
|
12362
|
+
keyterms_prompt: zod3.array(zod3.string()).optional().describe(
|
|
12363
|
+
"Improve accuracy with up to 200 (for Universal-2) or 1000 (for Universal-3 Pro) domain-specific words or phrases (maximum 6 words per phrase). See [Keyterms Prompting](https://www.assemblyai.com/docs/pre-recorded-audio/keyterms-prompting) for more details.\n"
|
|
11931
12364
|
),
|
|
11932
12365
|
language_code: zod3.enum([
|
|
11933
12366
|
"en",
|
|
@@ -12032,138 +12465,175 @@ var createTranscriptResponse = zod3.object({
|
|
|
12032
12465
|
"cy",
|
|
12033
12466
|
"yi",
|
|
12034
12467
|
"yo"
|
|
12035
|
-
]).describe(
|
|
12036
|
-
"The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/
|
|
12037
|
-
).or(zod3.string()).optional().describe(
|
|
12038
|
-
"The language of your audio file.\nPossible values are found in [Supported Languages](https://www.assemblyai.com/docs/concepts/supported-languages).\nThe default value is 'en_us'.\n"
|
|
12039
|
-
),
|
|
12040
|
-
language_detection: zod3.boolean().nullish().describe(
|
|
12041
|
-
"Whether [Automatic language detection](https://www.assemblyai.com/docs/models/speech-recognition#automatic-language-detection) is enabled, either true or false"
|
|
12042
|
-
),
|
|
12043
|
-
language_confidence_threshold: zod3.number().min(createTranscriptResponseLanguageConfidenceThresholdMin).max(createTranscriptResponseLanguageConfidenceThresholdMax).nullable().describe(
|
|
12044
|
-
"The confidence threshold for the automatically detected language.\nAn error will be returned if the language confidence is below this threshold.\n"
|
|
12045
|
-
),
|
|
12046
|
-
language_confidence: zod3.number().min(createTranscriptResponseLanguageConfidenceMin).max(createTranscriptResponseLanguageConfidenceMax).nullable().describe(
|
|
12047
|
-
"The confidence score for the detected language, between 0.0 (low confidence) and 1.0 (high confidence)"
|
|
12048
|
-
),
|
|
12049
|
-
speech_model: zod3.enum(["best", "slam-1", "universal"]).describe("The speech model to use for the transcription.").or(zod3.null()).describe(
|
|
12050
|
-
"The speech model used for the transcription. When `null`, the default model is used."
|
|
12051
|
-
),
|
|
12052
|
-
text: zod3.string().nullish().describe("The textual transcript of your media file"),
|
|
12053
|
-
words: zod3.array(
|
|
12054
|
-
zod3.object({
|
|
12055
|
-
confidence: zod3.number().min(createTranscriptResponseWordsItemConfidenceMin).max(createTranscriptResponseWordsItemConfidenceMax).describe("The confidence score for the transcript of this word"),
|
|
12056
|
-
start: zod3.number().describe("The starting time, in milliseconds, for the word"),
|
|
12057
|
-
end: zod3.number().describe("The ending time, in milliseconds, for the word"),
|
|
12058
|
-
text: zod3.string().describe("The text of the word"),
|
|
12059
|
-
channel: zod3.string().nullish().describe(
|
|
12060
|
-
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
12061
|
-
),
|
|
12062
|
-
speaker: zod3.string().nullable().describe(
|
|
12063
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/models/speaker-diarization) is enabled, else null"
|
|
12064
|
-
)
|
|
12065
|
-
})
|
|
12066
|
-
).nullish().describe(
|
|
12067
|
-
"An array of temporally-sequential word objects, one for each word in the transcript.\nSee [Speech recognition](https://www.assemblyai.com/docs/models/speech-recognition) for more information.\n"
|
|
12468
|
+
]).optional().describe(
|
|
12469
|
+
"The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/pre-recorded-audio/supported-languages).\nThe default value is 'en_us'.\n"
|
|
12068
12470
|
),
|
|
12069
|
-
|
|
12070
|
-
zod3.
|
|
12071
|
-
|
|
12072
|
-
|
|
12073
|
-
|
|
12074
|
-
|
|
12075
|
-
|
|
12076
|
-
|
|
12077
|
-
|
|
12078
|
-
|
|
12079
|
-
|
|
12080
|
-
|
|
12081
|
-
|
|
12082
|
-
|
|
12083
|
-
|
|
12084
|
-
|
|
12085
|
-
|
|
12086
|
-
|
|
12087
|
-
|
|
12088
|
-
|
|
12089
|
-
|
|
12090
|
-
|
|
12091
|
-
|
|
12092
|
-
|
|
12093
|
-
|
|
12094
|
-
|
|
12095
|
-
|
|
12471
|
+
language_codes: zod3.array(
|
|
12472
|
+
zod3.enum([
|
|
12473
|
+
"en",
|
|
12474
|
+
"en_au",
|
|
12475
|
+
"en_uk",
|
|
12476
|
+
"en_us",
|
|
12477
|
+
"es",
|
|
12478
|
+
"fr",
|
|
12479
|
+
"de",
|
|
12480
|
+
"it",
|
|
12481
|
+
"pt",
|
|
12482
|
+
"nl",
|
|
12483
|
+
"af",
|
|
12484
|
+
"sq",
|
|
12485
|
+
"am",
|
|
12486
|
+
"ar",
|
|
12487
|
+
"hy",
|
|
12488
|
+
"as",
|
|
12489
|
+
"az",
|
|
12490
|
+
"ba",
|
|
12491
|
+
"eu",
|
|
12492
|
+
"be",
|
|
12493
|
+
"bn",
|
|
12494
|
+
"bs",
|
|
12495
|
+
"br",
|
|
12496
|
+
"bg",
|
|
12497
|
+
"my",
|
|
12498
|
+
"ca",
|
|
12499
|
+
"zh",
|
|
12500
|
+
"hr",
|
|
12501
|
+
"cs",
|
|
12502
|
+
"da",
|
|
12503
|
+
"et",
|
|
12504
|
+
"fo",
|
|
12505
|
+
"fi",
|
|
12506
|
+
"gl",
|
|
12507
|
+
"ka",
|
|
12508
|
+
"el",
|
|
12509
|
+
"gu",
|
|
12510
|
+
"ht",
|
|
12511
|
+
"ha",
|
|
12512
|
+
"haw",
|
|
12513
|
+
"he",
|
|
12514
|
+
"hi",
|
|
12515
|
+
"hu",
|
|
12516
|
+
"is",
|
|
12517
|
+
"id",
|
|
12518
|
+
"ja",
|
|
12519
|
+
"jw",
|
|
12520
|
+
"kn",
|
|
12521
|
+
"kk",
|
|
12522
|
+
"km",
|
|
12523
|
+
"ko",
|
|
12524
|
+
"lo",
|
|
12525
|
+
"la",
|
|
12526
|
+
"lv",
|
|
12527
|
+
"ln",
|
|
12528
|
+
"lt",
|
|
12529
|
+
"lb",
|
|
12530
|
+
"mk",
|
|
12531
|
+
"mg",
|
|
12532
|
+
"ms",
|
|
12533
|
+
"ml",
|
|
12534
|
+
"mt",
|
|
12535
|
+
"mi",
|
|
12536
|
+
"mr",
|
|
12537
|
+
"mn",
|
|
12538
|
+
"ne",
|
|
12539
|
+
"no",
|
|
12540
|
+
"nn",
|
|
12541
|
+
"oc",
|
|
12542
|
+
"pa",
|
|
12543
|
+
"ps",
|
|
12544
|
+
"fa",
|
|
12545
|
+
"pl",
|
|
12546
|
+
"ro",
|
|
12547
|
+
"ru",
|
|
12548
|
+
"sa",
|
|
12549
|
+
"sr",
|
|
12550
|
+
"sn",
|
|
12551
|
+
"sd",
|
|
12552
|
+
"si",
|
|
12553
|
+
"sk",
|
|
12554
|
+
"sl",
|
|
12555
|
+
"so",
|
|
12556
|
+
"su",
|
|
12557
|
+
"sw",
|
|
12558
|
+
"sv",
|
|
12559
|
+
"tl",
|
|
12560
|
+
"tg",
|
|
12561
|
+
"ta",
|
|
12562
|
+
"tt",
|
|
12563
|
+
"te",
|
|
12564
|
+
"th",
|
|
12565
|
+
"bo",
|
|
12566
|
+
"tr",
|
|
12567
|
+
"tk",
|
|
12568
|
+
"uk",
|
|
12569
|
+
"ur",
|
|
12570
|
+
"uz",
|
|
12571
|
+
"vi",
|
|
12572
|
+
"cy",
|
|
12573
|
+
"yi",
|
|
12574
|
+
"yo"
|
|
12575
|
+
]).describe(
|
|
12576
|
+
"The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/pre-recorded-audio/supported-languages).\nThe default value is 'en_us'.\n"
|
|
12577
|
+
)
|
|
12096
12578
|
).nullish().describe(
|
|
12097
|
-
"
|
|
12579
|
+
"The language codes of your audio file. Used for [Code switching](/docs/speech-to-text/pre-recorded-audio/code-switching)\nOne of the values specified must be `en`.\n"
|
|
12098
12580
|
),
|
|
12099
|
-
|
|
12100
|
-
"The confidence score for the
|
|
12581
|
+
language_confidence: zod3.number().nullable().describe(
|
|
12582
|
+
"The confidence score for the detected language, between 0.0 (low confidence) and 1.0 (high confidence). See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details."
|
|
12101
12583
|
),
|
|
12102
|
-
|
|
12103
|
-
|
|
12104
|
-
format_text: zod3.boolean().nullish().describe("Whether Text Formatting is enabled, either true or false"),
|
|
12105
|
-
disfluencies: zod3.boolean().nullish().describe('Transcribe Filler Words, like "umm", in your media file; can be true or false'),
|
|
12106
|
-
multichannel: zod3.boolean().nullish().describe(
|
|
12107
|
-
"Whether [Multichannel transcription](https://www.assemblyai.com/docs/models/speech-recognition#multichannel-transcription) was enabled in the transcription request, either true or false"
|
|
12584
|
+
language_confidence_threshold: zod3.number().nullable().describe(
|
|
12585
|
+
"The confidence threshold for the automatically detected language.\nAn error will be returned if the language confidence is below this threshold.\nSee [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.\n"
|
|
12108
12586
|
),
|
|
12109
|
-
|
|
12110
|
-
"
|
|
12111
|
-
),
|
|
12112
|
-
webhook_url: zod3.string().nullish().describe(
|
|
12113
|
-
"The URL to which we send webhook requests.\nWe sends two different types of webhook requests.\nOne request when a transcript is completed or failed, and one request when the redacted audio is ready if redact_pii_audio is enabled.\n"
|
|
12114
|
-
),
|
|
12115
|
-
webhook_status_code: zod3.number().nullish().describe(
|
|
12116
|
-
"The status code we received from your server when delivering the transcript completed or failed webhook request, if a webhook URL was provided"
|
|
12587
|
+
language_detection: zod3.boolean().nullish().describe(
|
|
12588
|
+
"Whether [Automatic language detection](/docs/pre-recorded-audio/automatic-language-detection) is enabled, either true or false"
|
|
12117
12589
|
),
|
|
12118
|
-
|
|
12119
|
-
|
|
12120
|
-
|
|
12590
|
+
language_detection_options: zod3.object({
|
|
12591
|
+
expected_languages: zod3.array(zod3.string()).optional().describe(
|
|
12592
|
+
'List of languages expected in the audio file. Defaults to `["all"]` when unspecified. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.'
|
|
12593
|
+
),
|
|
12594
|
+
fallback_language: zod3.string().default(createTranscriptResponseLanguageDetectionOptionsFallbackLanguageDefault).describe(
|
|
12595
|
+
'If the detected language of the audio file is not in the list of expected languages, the `fallback_language` is used. Specify `["auto"]` to let our model choose the fallback language from `expected_languages` with the highest confidence score. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.\n'
|
|
12596
|
+
),
|
|
12597
|
+
code_switching: zod3.boolean().optional().describe(
|
|
12598
|
+
"Whether [code switching](/docs/speech-to-text/pre-recorded-audio/code-switching) should be detected.\n"
|
|
12599
|
+
),
|
|
12600
|
+
code_switching_confidence_threshold: zod3.number().default(
|
|
12601
|
+
createTranscriptResponseLanguageDetectionOptionsCodeSwitchingConfidenceThresholdDefault
|
|
12602
|
+
).describe(
|
|
12603
|
+
"The confidence threshold for [code switching](/docs/speech-to-text/pre-recorded-audio/code-switching) detection. If the code switching confidence is below this threshold, the transcript will be processed in the language with the highest `language_detection_confidence` score.\n"
|
|
12604
|
+
)
|
|
12605
|
+
}).optional().describe(
|
|
12606
|
+
"Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection)."
|
|
12121
12607
|
),
|
|
12122
|
-
|
|
12123
|
-
|
|
12124
|
-
auto_highlights_result: zod3.object({
|
|
12125
|
-
status: zod3.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
12126
|
-
results: zod3.array(
|
|
12127
|
-
zod3.object({
|
|
12128
|
-
count: zod3.number().describe("The total number of times the key phrase appears in the audio file"),
|
|
12129
|
-
rank: zod3.number().min(createTranscriptResponseAutoHighlightsResultResultsItemRankMin).max(createTranscriptResponseAutoHighlightsResultResultsItemRankMax).describe(
|
|
12130
|
-
"The total relevancy to the overall audio file of this key phrase - a greater number means more relevant"
|
|
12131
|
-
),
|
|
12132
|
-
text: zod3.string().describe("The text itself of the key phrase"),
|
|
12133
|
-
timestamps: zod3.array(
|
|
12134
|
-
zod3.object({
|
|
12135
|
-
start: zod3.number().describe("The start time in milliseconds"),
|
|
12136
|
-
end: zod3.number().describe("The end time in milliseconds")
|
|
12137
|
-
}).describe("Timestamp containing a start and end property in milliseconds")
|
|
12138
|
-
).describe("The timestamp of the of the key phrase")
|
|
12139
|
-
})
|
|
12140
|
-
).describe("A temporally-sequential array of Key Phrases")
|
|
12141
|
-
}).describe(
|
|
12142
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key phrases](https://www.assemblyai.com/docs/models/key-phrases) for more information.\n"
|
|
12143
|
-
).or(zod3.null()).optional().describe(
|
|
12144
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key Phrases](https://www.assemblyai.com/docs/models/key-phrases) for more information.\n"
|
|
12608
|
+
multichannel: zod3.boolean().nullish().describe(
|
|
12609
|
+
"Whether [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/multichannel) was enabled in the transcription request, either true or false"
|
|
12145
12610
|
),
|
|
12146
|
-
|
|
12147
|
-
"
|
|
12611
|
+
prompt: zod3.string().optional().describe(
|
|
12612
|
+
"Provide natural language prompting of up to 1,500 words of contextual information to the model. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for best practices.\n\nNote: This parameter is only supported for the Universal-3 Pro model.\n"
|
|
12148
12613
|
),
|
|
12149
|
-
|
|
12150
|
-
"
|
|
12151
|
-
),
|
|
12152
|
-
word_boost: zod3.array(zod3.string()).optional().describe("The list of custom vocabulary to boost transcription probability for"),
|
|
12153
|
-
boost_param: zod3.string().nullish().describe("The word boost parameter value"),
|
|
12154
|
-
filter_profanity: zod3.boolean().nullish().describe(
|
|
12155
|
-
"Whether [Profanity Filtering](https://www.assemblyai.com/docs/models/speech-recognition#profanity-filtering) is enabled, either true or false"
|
|
12614
|
+
punctuate: zod3.boolean().nullish().describe(
|
|
12615
|
+
"Whether [Automatic Punctuation](https://www.assemblyai.com/docs/pre-recorded-audio) is enabled, either true or false"
|
|
12156
12616
|
),
|
|
12157
12617
|
redact_pii: zod3.boolean().describe(
|
|
12158
|
-
"Whether [PII Redaction](https://www.assemblyai.com/docs/
|
|
12618
|
+
"Whether [PII Redaction](https://www.assemblyai.com/docs/pii-redaction) is enabled, either true or false"
|
|
12159
12619
|
),
|
|
12160
12620
|
redact_pii_audio: zod3.boolean().nullish().describe(
|
|
12161
|
-
"Whether a redacted version of the audio file was generated,\neither true or false. See [PII redaction](https://www.assemblyai.com/docs/
|
|
12621
|
+
"Whether a redacted version of the audio file was generated,\neither true or false. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more information.\n"
|
|
12622
|
+
),
|
|
12623
|
+
redact_pii_audio_options: zod3.object({
|
|
12624
|
+
return_redacted_no_speech_audio: zod3.boolean().optional().describe(
|
|
12625
|
+
"By default, audio redaction provides redacted audio URLs only when speech is detected. However, if your use-case specifically requires redacted audio files even for silent audio files without any dialogue, you can opt to receive these URLs by setting this parameter to `true`."
|
|
12626
|
+
),
|
|
12627
|
+
override_audio_redaction_method: zod3.enum(["silence"]).optional().describe(
|
|
12628
|
+
"Specify the method used to redact audio. By default, redacted audio uses a beep sound. Set to `silence` to replace PII with silence instead of a beep."
|
|
12629
|
+
)
|
|
12630
|
+
}).optional().describe(
|
|
12631
|
+
"The options for PII-redacted audio, if redact_pii_audio is enabled.\nSee [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more information.\n"
|
|
12162
12632
|
),
|
|
12163
12633
|
redact_pii_audio_quality: zod3.enum(["mp3", "wav"]).describe(
|
|
12164
|
-
"Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See [PII redaction](https://www.assemblyai.com/docs/
|
|
12634
|
+
"Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more details."
|
|
12165
12635
|
).or(zod3.null()).optional().describe(
|
|
12166
|
-
"The audio quality of the PII-redacted audio file, if redact_pii_audio is enabled.\nSee [PII redaction](https://www.assemblyai.com/docs/
|
|
12636
|
+
"The audio quality of the PII-redacted audio file, if redact_pii_audio is enabled.\nSee [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more information.\n"
|
|
12167
12637
|
),
|
|
12168
12638
|
redact_pii_policies: zod3.array(
|
|
12169
12639
|
zod3.enum([
|
|
@@ -12213,19 +12683,347 @@ var createTranscriptResponse = zod3.object({
|
|
|
12213
12683
|
"zodiac_sign"
|
|
12214
12684
|
]).describe("The type of PII to redact")
|
|
12215
12685
|
).nullish().describe(
|
|
12216
|
-
"The list of PII Redaction policies that were enabled, if PII Redaction is enabled.\nSee [PII redaction](https://www.assemblyai.com/docs/
|
|
12686
|
+
"The list of PII Redaction policies that were enabled, if PII Redaction is enabled.\nSee [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more information.\n"
|
|
12217
12687
|
),
|
|
12218
12688
|
redact_pii_sub: zod3.enum(["entity_name", "hash"]).optional().describe(
|
|
12219
|
-
|
|
12689
|
+
"The replacement logic for detected PII, can be `entity_name` or `hash`. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more details."
|
|
12690
|
+
),
|
|
12691
|
+
sentiment_analysis: zod3.boolean().nullish().describe(
|
|
12692
|
+
"Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-analysis) is enabled, can be true or false"
|
|
12693
|
+
),
|
|
12694
|
+
sentiment_analysis_results: zod3.array(
|
|
12695
|
+
zod3.object({
|
|
12696
|
+
text: zod3.string().describe("The transcript of the sentence"),
|
|
12697
|
+
start: zod3.number().describe("The starting time, in milliseconds, of the sentence"),
|
|
12698
|
+
end: zod3.number().describe("The ending time, in milliseconds, of the sentence"),
|
|
12699
|
+
sentiment: zod3.enum(["POSITIVE", "NEUTRAL", "NEGATIVE"]),
|
|
12700
|
+
confidence: zod3.number().describe(
|
|
12701
|
+
"The confidence score for the detected sentiment of the sentence, from 0 to 1"
|
|
12702
|
+
),
|
|
12703
|
+
channel: zod3.string().nullish().describe(
|
|
12704
|
+
"The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
12705
|
+
),
|
|
12706
|
+
speaker: zod3.string().nullable().describe(
|
|
12707
|
+
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization) is enabled, else null"
|
|
12708
|
+
)
|
|
12709
|
+
}).describe("The result of the Sentiment Analysis model")
|
|
12710
|
+
).nullish().describe(
|
|
12711
|
+
"An array of results for the Sentiment Analysis model, if it is enabled.\nSee [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-analysis) for more information.\n"
|
|
12220
12712
|
),
|
|
12221
12713
|
speaker_labels: zod3.boolean().nullish().describe(
|
|
12222
|
-
"Whether [Speaker diarization](https://www.assemblyai.com/docs/
|
|
12714
|
+
"Whether [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization) is enabled, can be true or false"
|
|
12223
12715
|
),
|
|
12224
12716
|
speakers_expected: zod3.number().nullish().describe(
|
|
12225
|
-
"Tell the speaker label model how many speakers it should attempt to identify. See [
|
|
12717
|
+
"Tell the speaker label model how many speakers it should attempt to identify. See [Set number of speakers expected](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization#set-number-of-speakers-expected) for more details."
|
|
12718
|
+
),
|
|
12719
|
+
speech_model_used: zod3.string().optional().describe(
|
|
12720
|
+
"The speech model to use for the transcription. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models."
|
|
12721
|
+
),
|
|
12722
|
+
speech_models: zod3.array(
|
|
12723
|
+
zod3.string().describe(
|
|
12724
|
+
"The speech model to use for the transcription. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models."
|
|
12725
|
+
)
|
|
12726
|
+
).nullish().describe(
|
|
12727
|
+
"List multiple speech models in priority order, allowing our system to automatically route your audio to the best available option. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models and routing behavior.\n"
|
|
12728
|
+
),
|
|
12729
|
+
speech_threshold: zod3.number().nullish().describe(
|
|
12730
|
+
"Defaults to null. Reject audio files that contain less than this fraction of speech.\nValid values are in the range [0, 1] inclusive. See [Speech Threshold](https://www.assemblyai.com/docs/speech-threshold) for more details.\n"
|
|
12731
|
+
),
|
|
12732
|
+
speech_understanding: zod3.object({
|
|
12733
|
+
request: zod3.object({
|
|
12734
|
+
translation: zod3.object({
|
|
12735
|
+
target_languages: zod3.array(zod3.string()).describe(
|
|
12736
|
+
'List of target language codes (e.g., `["es", "de"]`). See [Translation](https://www.assemblyai.com/docs/speech-understanding/translation) for supported languages.'
|
|
12737
|
+
),
|
|
12738
|
+
formal: zod3.boolean().default(createTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault).describe(
|
|
12739
|
+
"Use formal language style. See [Translation](https://www.assemblyai.com/docs/speech-understanding/translation) for more details."
|
|
12740
|
+
),
|
|
12741
|
+
match_original_utterance: zod3.boolean().optional().describe(
|
|
12742
|
+
"When enabled with Speaker Labels, returns translated text in the utterances array. Each utterance will include a `translated_texts` key containing translations for each target language."
|
|
12743
|
+
)
|
|
12744
|
+
})
|
|
12745
|
+
}).describe(
|
|
12746
|
+
"Request body for [Translation](https://www.assemblyai.com/docs/speech-understanding/translation)."
|
|
12747
|
+
).or(
|
|
12748
|
+
zod3.object({
|
|
12749
|
+
speaker_identification: zod3.object({
|
|
12750
|
+
speaker_type: zod3.enum(["role", "name"]).describe(
|
|
12751
|
+
"Type of speaker identification. See [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification) for details on each type."
|
|
12752
|
+
),
|
|
12753
|
+
known_values: zod3.array(zod3.string()).optional().describe(
|
|
12754
|
+
'Required if speaker_type is "role". Each value must be 35 characters or less.'
|
|
12755
|
+
),
|
|
12756
|
+
speakers: zod3.array(
|
|
12757
|
+
zod3.object({
|
|
12758
|
+
role: zod3.string().optional().describe(
|
|
12759
|
+
'The role of the speaker. Required when `speaker_type` is "role".'
|
|
12760
|
+
),
|
|
12761
|
+
name: zod3.string().optional().describe(
|
|
12762
|
+
'The name of the speaker. Required when `speaker_type` is "name".'
|
|
12763
|
+
),
|
|
12764
|
+
description: zod3.string().optional().describe(
|
|
12765
|
+
"A description of the speaker to help the model identify them based on conversational context."
|
|
12766
|
+
)
|
|
12767
|
+
})
|
|
12768
|
+
).optional().describe(
|
|
12769
|
+
"An array of speaker objects with metadata to improve identification accuracy. Each object should include a `role` or `name` (depending on `speaker_type`) and an optional `description` to help the model identify the speaker. You can also include any additional custom properties (e.g., `company`, `title`) to provide more context. Use this as an alternative to `known_values` when you want to provide additional context about each speaker."
|
|
12770
|
+
)
|
|
12771
|
+
})
|
|
12772
|
+
}).describe(
|
|
12773
|
+
"Request body for [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification)."
|
|
12774
|
+
)
|
|
12775
|
+
).or(
|
|
12776
|
+
zod3.object({
|
|
12777
|
+
custom_formatting: zod3.object({
|
|
12778
|
+
date: zod3.string().optional().describe(
|
|
12779
|
+
'Date format pattern (e.g., `"mm/dd/yyyy"`). See [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting) for more details.'
|
|
12780
|
+
),
|
|
12781
|
+
phone_number: zod3.string().optional().describe(
|
|
12782
|
+
'Phone number format pattern (e.g., `"(xxx)xxx-xxxx"`). See [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting) for more details.'
|
|
12783
|
+
),
|
|
12784
|
+
email: zod3.string().optional().describe(
|
|
12785
|
+
'Email format pattern (e.g., `"username@domain.com"`). See [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting) for more details.'
|
|
12786
|
+
)
|
|
12787
|
+
})
|
|
12788
|
+
}).describe(
|
|
12789
|
+
"Request body for [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting)."
|
|
12790
|
+
)
|
|
12791
|
+
).optional(),
|
|
12792
|
+
response: zod3.object({
|
|
12793
|
+
translation: zod3.object({
|
|
12794
|
+
status: zod3.string().optional()
|
|
12795
|
+
}).optional()
|
|
12796
|
+
}).or(
|
|
12797
|
+
zod3.object({
|
|
12798
|
+
speaker_identification: zod3.object({
|
|
12799
|
+
mapping: zod3.record(zod3.string(), zod3.string()).optional().describe(
|
|
12800
|
+
'A mapping of the original generic speaker labels (e.g., "A", "B") to the identified speaker names or roles.'
|
|
12801
|
+
),
|
|
12802
|
+
status: zod3.string().optional()
|
|
12803
|
+
}).optional()
|
|
12804
|
+
})
|
|
12805
|
+
).or(
|
|
12806
|
+
zod3.object({
|
|
12807
|
+
custom_formatting: zod3.object({
|
|
12808
|
+
mapping: zod3.record(zod3.string(), zod3.string()).optional(),
|
|
12809
|
+
formatted_text: zod3.string().optional()
|
|
12810
|
+
}).optional()
|
|
12811
|
+
})
|
|
12812
|
+
).optional()
|
|
12813
|
+
}).optional().describe(
|
|
12814
|
+
"Speech understanding tasks like [Translation](https://www.assemblyai.com/docs/speech-understanding/translation), [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification), and [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting). See the task-specific docs for available options and configuration.\n"
|
|
12815
|
+
),
|
|
12816
|
+
status: zod3.enum(["queued", "processing", "completed", "error"]).describe(
|
|
12817
|
+
"The status of your transcript. Possible values are queued, processing, completed, or error."
|
|
12818
|
+
),
|
|
12819
|
+
summarization: zod3.boolean().describe(
|
|
12820
|
+
"Whether [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization) is enabled, either true or false. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
12821
|
+
),
|
|
12822
|
+
summary: zod3.string().nullish().describe(
|
|
12823
|
+
"The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization) is enabled. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details."
|
|
12824
|
+
),
|
|
12825
|
+
summary_model: zod3.string().nullish().describe(
|
|
12826
|
+
"The Summarization model used to generate the summary,\nif [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization#summary-models) is enabled. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details.\n"
|
|
12827
|
+
),
|
|
12828
|
+
summary_type: zod3.string().nullish().describe(
|
|
12829
|
+
"The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization#summary-types) is enabled. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details."
|
|
12830
|
+
),
|
|
12831
|
+
remove_audio_tags: zod3.enum(["all"]).describe(
|
|
12832
|
+
"Whether [audio event tags](https://www.assemblyai.com/docs/pre-recorded-audio/universal-3-pro#audio-event-tags) were removed from the transcript text.\n\nNote: This parameter is only supported for the Universal-3 Pro model.\n"
|
|
12833
|
+
).or(zod3.null()).optional().describe(
|
|
12834
|
+
"Whether [audio event tags](https://www.assemblyai.com/docs/pre-recorded-audio/universal-3-pro#audio-event-tags) were removed from the transcript text.\n\nNote: This parameter is only supported for the Universal-3 Pro model.\n"
|
|
12835
|
+
),
|
|
12836
|
+
temperature: zod3.number().nullish().describe(
|
|
12837
|
+
"The temperature that was used for the model's response. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for more details.\n\nNote: This parameter can only be used with the Universal-3 Pro model.\n"
|
|
12838
|
+
),
|
|
12839
|
+
text: zod3.string().nullish().describe("The textual transcript of your media file"),
|
|
12840
|
+
throttled: zod3.boolean().nullish().describe(
|
|
12841
|
+
"True while a request is throttled and false when a request is no longer throttled"
|
|
12842
|
+
),
|
|
12843
|
+
utterances: zod3.array(
|
|
12844
|
+
zod3.object({
|
|
12845
|
+
confidence: zod3.number().describe("The confidence score for the transcript of this utterance"),
|
|
12846
|
+
start: zod3.number().describe("The starting time, in milliseconds, of the utterance in the audio file"),
|
|
12847
|
+
end: zod3.number().describe("The ending time, in milliseconds, of the utterance in the audio file"),
|
|
12848
|
+
text: zod3.string().describe("The text for this utterance"),
|
|
12849
|
+
words: zod3.array(
|
|
12850
|
+
zod3.object({
|
|
12851
|
+
confidence: zod3.number().describe("The confidence score for the transcript of this word"),
|
|
12852
|
+
start: zod3.number().describe("The starting time, in milliseconds, for the word"),
|
|
12853
|
+
end: zod3.number().describe("The ending time, in milliseconds, for the word"),
|
|
12854
|
+
text: zod3.string().describe("The text of the word"),
|
|
12855
|
+
channel: zod3.string().nullish().describe(
|
|
12856
|
+
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
12857
|
+
),
|
|
12858
|
+
speaker: zod3.string().nullable().describe(
|
|
12859
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization) is enabled, else null"
|
|
12860
|
+
)
|
|
12861
|
+
})
|
|
12862
|
+
).describe("The words in the utterance."),
|
|
12863
|
+
channel: zod3.string().nullish().describe(
|
|
12864
|
+
"The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
12865
|
+
),
|
|
12866
|
+
speaker: zod3.string().describe(
|
|
12867
|
+
'The speaker of this utterance, where each speaker is assigned a sequential capital letter - e.g. "A" for Speaker A, "B" for Speaker B, etc.'
|
|
12868
|
+
),
|
|
12869
|
+
translated_texts: zod3.record(zod3.string(), zod3.string()).optional().describe(
|
|
12870
|
+
'Translations keyed by language code (e.g., `{"es": "Texto traducido", "de": "\xDCbersetzter Text"}`). Only present when `match_original_utterance` is enabled with translation.'
|
|
12871
|
+
)
|
|
12872
|
+
})
|
|
12873
|
+
).nullish().describe(
|
|
12874
|
+
"When multichannel or speaker_labels is enabled, a list of turn-by-turn utterance objects.\nSee [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization) and [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/multichannel) for more information.\n"
|
|
12875
|
+
),
|
|
12876
|
+
webhook_auth: zod3.boolean().describe(
|
|
12877
|
+
"Whether [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) authentication details were provided"
|
|
12878
|
+
),
|
|
12879
|
+
webhook_auth_header_name: zod3.string().nullish().describe(
|
|
12880
|
+
"The header name to be sent with the transcript completed or failed [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) requests"
|
|
12881
|
+
),
|
|
12882
|
+
webhook_status_code: zod3.number().nullish().describe(
|
|
12883
|
+
"The status code we received from your server when delivering the transcript completed or failed [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) request, if a webhook URL was provided"
|
|
12884
|
+
),
|
|
12885
|
+
webhook_url: zod3.string().nullish().describe(
|
|
12886
|
+
"The URL to which we send [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) requests.\n"
|
|
12887
|
+
),
|
|
12888
|
+
words: zod3.array(
|
|
12889
|
+
zod3.object({
|
|
12890
|
+
confidence: zod3.number().describe("The confidence score for the transcript of this word"),
|
|
12891
|
+
start: zod3.number().describe("The starting time, in milliseconds, for the word"),
|
|
12892
|
+
end: zod3.number().describe("The ending time, in milliseconds, for the word"),
|
|
12893
|
+
text: zod3.string().describe("The text of the word"),
|
|
12894
|
+
channel: zod3.string().nullish().describe(
|
|
12895
|
+
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
12896
|
+
),
|
|
12897
|
+
speaker: zod3.string().nullable().describe(
|
|
12898
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization) is enabled, else null"
|
|
12899
|
+
)
|
|
12900
|
+
})
|
|
12901
|
+
).nullish().describe(
|
|
12902
|
+
"An array of temporally-sequential word objects, one for each word in the transcript.\n"
|
|
12903
|
+
),
|
|
12904
|
+
acoustic_model: zod3.string().describe("This parameter does not currently have any functionality attached to it."),
|
|
12905
|
+
custom_topics: zod3.boolean().nullish().describe("This parameter does not currently have any functionality attached to it."),
|
|
12906
|
+
language_model: zod3.string().describe("This parameter does not currently have any functionality attached to it."),
|
|
12907
|
+
speech_model: zod3.string().describe(
|
|
12908
|
+
"The speech model to use for the transcription. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models."
|
|
12909
|
+
).or(zod3.null()).describe(
|
|
12910
|
+
"This parameter has been replaced with the `speech_models` parameter, learn more about the `speech_models` parameter [here](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model).\n"
|
|
12911
|
+
),
|
|
12912
|
+
speed_boost: zod3.boolean().nullish().describe("This parameter does not currently have any functionality attached to it."),
|
|
12913
|
+
topics: zod3.array(zod3.string()).optional().describe("This parameter does not currently have any functionality attached to it."),
|
|
12914
|
+
translated_texts: zod3.object({
|
|
12915
|
+
language_code: zod3.string().optional().describe("Translated text for this language code")
|
|
12916
|
+
}).optional().describe(
|
|
12917
|
+
"Translated text keyed by language code. See [Translation](https://www.assemblyai.com/docs/speech-understanding/translation) for more details."
|
|
12918
|
+
)
|
|
12919
|
+
}).describe("A transcript object");
|
|
12920
|
+
var listTranscriptsQueryLimitDefault = 10;
|
|
12921
|
+
var listTranscriptsQueryThrottledOnlyDefault = false;
|
|
12922
|
+
var listTranscriptsQueryParams = zod3.object({
|
|
12923
|
+
limit: zod3.number().default(listTranscriptsQueryLimitDefault).describe("Maximum amount of transcripts to retrieve"),
|
|
12924
|
+
status: zod3.enum(["queued", "processing", "completed", "error"]).optional().describe("Filter by transcript status"),
|
|
12925
|
+
created_on: zod3.string().date().optional().describe("Only get transcripts created on this date"),
|
|
12926
|
+
before_id: zod3.string().uuid().optional().describe("Get transcripts that were created before this transcript ID"),
|
|
12927
|
+
after_id: zod3.string().uuid().optional().describe("Get transcripts that were created after this transcript ID"),
|
|
12928
|
+
throttled_only: zod3.boolean().optional().describe("Only get throttled transcripts, overrides the status filter")
|
|
12929
|
+
});
|
|
12930
|
+
var listTranscriptsResponse = zod3.object({
|
|
12931
|
+
page_details: zod3.object({
|
|
12932
|
+
limit: zod3.number().describe("The number of results this page is limited to"),
|
|
12933
|
+
result_count: zod3.number().describe("The actual number of results in the page"),
|
|
12934
|
+
current_url: zod3.string().describe("The URL used to retrieve the current page of transcripts"),
|
|
12935
|
+
prev_url: zod3.string().nullable().describe(
|
|
12936
|
+
"The URL to the next page of transcripts. The previous URL always points to a page with older transcripts."
|
|
12937
|
+
),
|
|
12938
|
+
next_url: zod3.string().nullable().describe(
|
|
12939
|
+
"The URL to the next page of transcripts. The next URL always points to a page with newer transcripts."
|
|
12940
|
+
)
|
|
12941
|
+
}).describe(
|
|
12942
|
+
"Details of the transcript page. Transcripts are sorted from newest to oldest. The previous URL always points to a page with older transcripts."
|
|
12943
|
+
),
|
|
12944
|
+
transcripts: zod3.array(
|
|
12945
|
+
zod3.object({
|
|
12946
|
+
id: zod3.string().uuid().describe("The unique identifier for the transcript"),
|
|
12947
|
+
resource_url: zod3.string().describe("The URL to retrieve the transcript"),
|
|
12948
|
+
status: zod3.enum(["queued", "processing", "completed", "error"]).describe(
|
|
12949
|
+
"The status of your transcript. Possible values are queued, processing, completed, or error."
|
|
12950
|
+
),
|
|
12951
|
+
created: zod3.string().datetime({}).describe("The date and time the transcript was created"),
|
|
12952
|
+
completed: zod3.string().datetime({}).optional().describe("The date and time the transcript was completed"),
|
|
12953
|
+
audio_url: zod3.string().describe("The URL to the audio file"),
|
|
12954
|
+
error: zod3.string().nullable().describe("Error message of why the transcript failed")
|
|
12955
|
+
})
|
|
12956
|
+
).describe("An array of transcripts")
|
|
12957
|
+
}).describe(
|
|
12958
|
+
"A list of transcripts. Transcripts are sorted from newest to oldest. The previous URL always points to a page with older transcripts."
|
|
12959
|
+
);
|
|
12960
|
+
var getTranscriptParams = zod3.object({
|
|
12961
|
+
transcript_id: zod3.string().describe("ID of the transcript")
|
|
12962
|
+
});
|
|
12963
|
+
var getTranscriptResponseLanguageDetectionOptionsFallbackLanguageDefault = "auto";
|
|
12964
|
+
var getTranscriptResponseLanguageDetectionOptionsCodeSwitchingDefault = false;
|
|
12965
|
+
var getTranscriptResponseLanguageDetectionOptionsCodeSwitchingConfidenceThresholdDefault = 0.3;
|
|
12966
|
+
var getTranscriptResponseRedactPiiAudioOptionsReturnRedactedNoSpeechAudioDefault = false;
|
|
12967
|
+
var getTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault = true;
|
|
12968
|
+
var getTranscriptResponseSpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault = false;
|
|
12969
|
+
var getTranscriptResponse = zod3.object({
|
|
12970
|
+
audio_channels: zod3.number().optional().describe(
|
|
12971
|
+
"The number of audio channels in the audio file. This is only present when [multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/multichannel) is enabled."
|
|
12972
|
+
),
|
|
12973
|
+
audio_duration: zod3.number().nullish().describe("The duration of this transcript object's media file, in seconds"),
|
|
12974
|
+
audio_end_at: zod3.number().nullish().describe(
|
|
12975
|
+
"The point in time, in milliseconds, in the file at which the transcription was terminated. See [Set the start and end of the transcript](https://www.assemblyai.com/docs/pre-recorded-audio/set-the-start-and-end-of-the-transcript) for more details."
|
|
12976
|
+
),
|
|
12977
|
+
audio_start_from: zod3.number().nullish().describe(
|
|
12978
|
+
"The point in time, in milliseconds, in the file at which the transcription was started. See [Set the start and end of the transcript](https://www.assemblyai.com/docs/pre-recorded-audio/set-the-start-and-end-of-the-transcript) for more details."
|
|
12979
|
+
),
|
|
12980
|
+
audio_url: zod3.string().describe("The URL of the media that was transcribed"),
|
|
12981
|
+
auto_chapters: zod3.boolean().nullish().describe(
|
|
12982
|
+
"Whether [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/auto-chapters) is enabled, can be true or false. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible chapter summaries. See the [updated Auto Chapters page](https://www.assemblyai.com/docs/speech-understanding/auto-chapters) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
12983
|
+
),
|
|
12984
|
+
auto_highlights: zod3.boolean().describe(
|
|
12985
|
+
"Whether [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/key-phrases) is enabled, either true or false"
|
|
12986
|
+
),
|
|
12987
|
+
auto_highlights_result: zod3.object({
|
|
12988
|
+
status: zod3.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
12989
|
+
results: zod3.array(
|
|
12990
|
+
zod3.object({
|
|
12991
|
+
count: zod3.number().describe("The total number of times the key phrase appears in the audio file"),
|
|
12992
|
+
rank: zod3.number().describe(
|
|
12993
|
+
"The total relevancy to the overall audio file of this key phrase - a greater number means more relevant"
|
|
12994
|
+
),
|
|
12995
|
+
text: zod3.string().describe("The text itself of the key phrase"),
|
|
12996
|
+
timestamps: zod3.array(
|
|
12997
|
+
zod3.object({
|
|
12998
|
+
start: zod3.number().describe("The start time in milliseconds"),
|
|
12999
|
+
end: zod3.number().describe("The end time in milliseconds")
|
|
13000
|
+
}).describe("Timestamp containing a start and end property in milliseconds")
|
|
13001
|
+
).describe("The timestamp of the of the key phrase")
|
|
13002
|
+
})
|
|
13003
|
+
).describe("A temporally-sequential array of Key Phrases")
|
|
13004
|
+
}).describe(
|
|
13005
|
+
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key phrases](https://www.assemblyai.com/docs/speech-understanding/key-phrases) for more information.\n"
|
|
13006
|
+
).or(zod3.null()).optional().describe(
|
|
13007
|
+
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/key-phrases) for more information.\n"
|
|
13008
|
+
),
|
|
13009
|
+
chapters: zod3.array(
|
|
13010
|
+
zod3.object({
|
|
13011
|
+
gist: zod3.string().describe(
|
|
13012
|
+
"An ultra-short summary (just a few words) of the content spoken in the chapter"
|
|
13013
|
+
),
|
|
13014
|
+
headline: zod3.string().describe("A single sentence summary of the content spoken during the chapter"),
|
|
13015
|
+
summary: zod3.string().describe("A one paragraph summary of the content spoken during the chapter"),
|
|
13016
|
+
start: zod3.number().describe("The starting time, in milliseconds, for the chapter"),
|
|
13017
|
+
end: zod3.number().describe("The starting time, in milliseconds, for the chapter")
|
|
13018
|
+
}).describe("Chapter of the audio file")
|
|
13019
|
+
).nullish().describe(
|
|
13020
|
+
"An array of temporally sequential chapters for the audio file. See [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/auto-chapters) for more information."
|
|
13021
|
+
),
|
|
13022
|
+
confidence: zod3.number().nullish().describe(
|
|
13023
|
+
"The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence)"
|
|
12226
13024
|
),
|
|
12227
13025
|
content_safety: zod3.boolean().nullish().describe(
|
|
12228
|
-
"Whether [Content Moderation](https://www.assemblyai.com/docs/
|
|
13026
|
+
"Whether [Content Moderation](https://www.assemblyai.com/docs/content-moderation) is enabled, can be true or false"
|
|
12229
13027
|
),
|
|
12230
13028
|
content_safety_labels: zod3.object({
|
|
12231
13029
|
status: zod3.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -12235,16 +13033,8 @@ var createTranscriptResponse = zod3.object({
|
|
|
12235
13033
|
labels: zod3.array(
|
|
12236
13034
|
zod3.object({
|
|
12237
13035
|
label: zod3.string().describe("The label of the sensitive topic"),
|
|
12238
|
-
confidence: zod3.number().
|
|
12239
|
-
|
|
12240
|
-
).max(
|
|
12241
|
-
createTranscriptResponseContentSafetyLabelsResultsItemLabelsItemConfidenceMax
|
|
12242
|
-
).describe("The confidence score for the topic being discussed, from 0 to 1"),
|
|
12243
|
-
severity: zod3.number().min(
|
|
12244
|
-
createTranscriptResponseContentSafetyLabelsResultsItemLabelsItemSeverityMin
|
|
12245
|
-
).max(
|
|
12246
|
-
createTranscriptResponseContentSafetyLabelsResultsItemLabelsItemSeverityMax
|
|
12247
|
-
).describe("How severely the topic is discussed in the section, from 0 to 1")
|
|
13036
|
+
confidence: zod3.number().describe("The confidence score for the topic being discussed, from 0 to 1"),
|
|
13037
|
+
severity: zod3.number().describe("How severely the topic is discussed in the section, from 0 to 1")
|
|
12248
13038
|
})
|
|
12249
13039
|
).describe(
|
|
12250
13040
|
"An array of safety labels, one per sensitive topic that was detected in the section"
|
|
@@ -12257,128 +13047,39 @@ var createTranscriptResponse = zod3.object({
|
|
|
12257
13047
|
}).describe("Timestamp containing a start and end property in milliseconds")
|
|
12258
13048
|
})
|
|
12259
13049
|
).describe("An array of results for the Content Moderation model"),
|
|
12260
|
-
summary: zod3.record(
|
|
12261
|
-
zod3.string(),
|
|
12262
|
-
zod3.number().min(createTranscriptResponseContentSafetyLabelsSummaryMinOne).max(createTranscriptResponseContentSafetyLabelsSummaryMaxOne).describe(
|
|
12263
|
-
'A confidence score for the presence of the sensitive topic "topic" across the entire audio file'
|
|
12264
|
-
)
|
|
12265
|
-
).describe(
|
|
13050
|
+
summary: zod3.record(zod3.string(), zod3.number()).describe(
|
|
12266
13051
|
"A summary of the Content Moderation confidence results for the entire audio file"
|
|
12267
13052
|
),
|
|
12268
13053
|
severity_score_summary: zod3.record(
|
|
12269
13054
|
zod3.string(),
|
|
12270
13055
|
zod3.object({
|
|
12271
|
-
low: zod3.number()
|
|
12272
|
-
medium: zod3.number()
|
|
12273
|
-
high: zod3.number()
|
|
13056
|
+
low: zod3.number(),
|
|
13057
|
+
medium: zod3.number(),
|
|
13058
|
+
high: zod3.number()
|
|
12274
13059
|
})
|
|
12275
13060
|
).describe(
|
|
12276
13061
|
"A summary of the Content Moderation severity results for the entire audio file"
|
|
12277
13062
|
)
|
|
12278
13063
|
}).describe(
|
|
12279
|
-
"An array of results for the Content Moderation model, if it is enabled.\nSee [Content moderation](https://www.assemblyai.com/docs/
|
|
13064
|
+
"An array of results for the Content Moderation model, if it is enabled.\nSee [Content moderation](https://www.assemblyai.com/docs/content-moderation) for more information.\n"
|
|
12280
13065
|
).or(zod3.null()).optional().describe(
|
|
12281
|
-
"An array of results for the Content Moderation model, if it is enabled.\nSee [Content moderation](https://www.assemblyai.com/docs/
|
|
12282
|
-
),
|
|
12283
|
-
iab_categories: zod3.boolean().nullish().describe(
|
|
12284
|
-
"Whether [Topic Detection](https://www.assemblyai.com/docs/models/topic-detection) is enabled, can be true or false"
|
|
12285
|
-
),
|
|
12286
|
-
iab_categories_result: zod3.object({
|
|
12287
|
-
status: zod3.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
12288
|
-
results: zod3.array(
|
|
12289
|
-
zod3.object({
|
|
12290
|
-
text: zod3.string().describe("The text in the transcript in which a detected topic occurs"),
|
|
12291
|
-
labels: zod3.array(
|
|
12292
|
-
zod3.object({
|
|
12293
|
-
relevance: zod3.number().min(
|
|
12294
|
-
createTranscriptResponseIabCategoriesResultResultsItemLabelsItemRelevanceMin
|
|
12295
|
-
).max(
|
|
12296
|
-
createTranscriptResponseIabCategoriesResultResultsItemLabelsItemRelevanceMax
|
|
12297
|
-
).describe("How relevant the detected topic is of a detected topic"),
|
|
12298
|
-
label: zod3.string().describe(
|
|
12299
|
-
"The IAB taxonomical label for the label of the detected topic, where > denotes supertopic/subtopic relationship"
|
|
12300
|
-
)
|
|
12301
|
-
})
|
|
12302
|
-
).optional().describe("An array of detected topics in the text"),
|
|
12303
|
-
timestamp: zod3.object({
|
|
12304
|
-
start: zod3.number().describe("The start time in milliseconds"),
|
|
12305
|
-
end: zod3.number().describe("The end time in milliseconds")
|
|
12306
|
-
}).optional().describe("Timestamp containing a start and end property in milliseconds")
|
|
12307
|
-
}).describe("The result of the topic detection model")
|
|
12308
|
-
).describe("An array of results for the Topic Detection model"),
|
|
12309
|
-
summary: zod3.record(
|
|
12310
|
-
zod3.string(),
|
|
12311
|
-
zod3.number().min(createTranscriptResponseIabCategoriesResultSummaryMinOne).max(createTranscriptResponseIabCategoriesResultSummaryMaxOne)
|
|
12312
|
-
).describe("The overall relevance of topic to the entire audio file")
|
|
12313
|
-
}).describe(
|
|
12314
|
-
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/models/topic-detection) for more information.\n"
|
|
12315
|
-
).or(zod3.null()).optional().describe(
|
|
12316
|
-
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/models/topic-detection) for more information.\n"
|
|
13066
|
+
"An array of results for the Content Moderation model, if it is enabled.\nSee [Content moderation](https://www.assemblyai.com/docs/content-moderation) for more information.\n"
|
|
12317
13067
|
),
|
|
12318
13068
|
custom_spelling: zod3.array(
|
|
12319
13069
|
zod3.object({
|
|
12320
|
-
from: zod3.array(zod3.string()
|
|
13070
|
+
from: zod3.array(zod3.string()).describe("Words or phrases to replace"),
|
|
12321
13071
|
to: zod3.string().describe("Word to replace with")
|
|
12322
13072
|
}).describe(
|
|
12323
13073
|
"Object containing words or phrases to replace, and the word or phrase to replace with"
|
|
12324
13074
|
)
|
|
12325
|
-
).nullish().describe("Customize how words are spelled and formatted using to and from values"),
|
|
12326
|
-
keyterms_prompt: zod3.array(zod3.string()).optional().describe(
|
|
12327
|
-
"Improve accuracy with up to 1000 domain-specific words or phrases (maximum 6 words per phrase).\n"
|
|
12328
|
-
),
|
|
12329
|
-
prompt: zod3.string().optional().describe("This parameter does not currently have any functionality attached to it."),
|
|
12330
|
-
auto_chapters: zod3.boolean().nullish().describe(
|
|
12331
|
-
"Whether [Auto Chapters](https://www.assemblyai.com/docs/models/auto-chapters) is enabled, can be true or false"
|
|
12332
|
-
),
|
|
12333
|
-
chapters: zod3.array(
|
|
12334
|
-
zod3.object({
|
|
12335
|
-
gist: zod3.string().describe(
|
|
12336
|
-
"An ultra-short summary (just a few words) of the content spoken in the chapter"
|
|
12337
|
-
),
|
|
12338
|
-
headline: zod3.string().describe("A single sentence summary of the content spoken during the chapter"),
|
|
12339
|
-
summary: zod3.string().describe("A one paragraph summary of the content spoken during the chapter"),
|
|
12340
|
-
start: zod3.number().describe("The starting time, in milliseconds, for the chapter"),
|
|
12341
|
-
end: zod3.number().describe("The starting time, in milliseconds, for the chapter")
|
|
12342
|
-
}).describe("Chapter of the audio file")
|
|
12343
|
-
).nullish().describe("An array of temporally sequential chapters for the audio file"),
|
|
12344
|
-
summarization: zod3.boolean().describe(
|
|
12345
|
-
"Whether [Summarization](https://www.assemblyai.com/docs/models/summarization) is enabled, either true or false"
|
|
12346
|
-
),
|
|
12347
|
-
summary_type: zod3.string().nullish().describe(
|
|
12348
|
-
"The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/models/summarization) is enabled"
|
|
12349
|
-
),
|
|
12350
|
-
summary_model: zod3.string().nullish().describe(
|
|
12351
|
-
"The Summarization model used to generate the summary,\nif [Summarization](https://www.assemblyai.com/docs/models/summarization) is enabled\n"
|
|
12352
|
-
),
|
|
12353
|
-
summary: zod3.string().nullish().describe(
|
|
12354
|
-
"The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/models/summarization) is enabled"
|
|
12355
|
-
),
|
|
12356
|
-
custom_topics: zod3.boolean().nullish().describe("Whether custom topics is enabled, either true or false"),
|
|
12357
|
-
topics: zod3.array(zod3.string()).optional().describe("The list of custom topics provided if custom topics is enabled"),
|
|
12358
|
-
sentiment_analysis: zod3.boolean().nullish().describe(
|
|
12359
|
-
"Whether [Sentiment Analysis](https://www.assemblyai.com/docs/models/sentiment-analysis) is enabled, can be true or false"
|
|
12360
|
-
),
|
|
12361
|
-
sentiment_analysis_results: zod3.array(
|
|
12362
|
-
zod3.object({
|
|
12363
|
-
text: zod3.string().describe("The transcript of the sentence"),
|
|
12364
|
-
start: zod3.number().describe("The starting time, in milliseconds, of the sentence"),
|
|
12365
|
-
end: zod3.number().describe("The ending time, in milliseconds, of the sentence"),
|
|
12366
|
-
sentiment: zod3.enum(["POSITIVE", "NEUTRAL", "NEGATIVE"]),
|
|
12367
|
-
confidence: zod3.number().min(createTranscriptResponseSentimentAnalysisResultsItemConfidenceMin).max(createTranscriptResponseSentimentAnalysisResultsItemConfidenceMax).describe(
|
|
12368
|
-
"The confidence score for the detected sentiment of the sentence, from 0 to 1"
|
|
12369
|
-
),
|
|
12370
|
-
channel: zod3.string().nullish().describe(
|
|
12371
|
-
"The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
12372
|
-
),
|
|
12373
|
-
speaker: zod3.string().nullable().describe(
|
|
12374
|
-
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/models/speaker-diarization) is enabled, else null"
|
|
12375
|
-
)
|
|
12376
|
-
}).describe("The result of the Sentiment Analysis model")
|
|
12377
13075
|
).nullish().describe(
|
|
12378
|
-
"
|
|
13076
|
+
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/custom-spelling) for more details."
|
|
12379
13077
|
),
|
|
12380
|
-
|
|
12381
|
-
|
|
13078
|
+
disfluencies: zod3.boolean().nullish().describe(
|
|
13079
|
+
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/filler-words), like "umm", in your media file; can be true or false'
|
|
13080
|
+
),
|
|
13081
|
+
domain: zod3.string().nullish().describe(
|
|
13082
|
+
'The domain-specific model applied to the transcript. When set to `"medical-v1"`, [Medical Mode](https://www.assemblyai.com/docs/pre-recorded-audio/medical-mode) was used to improve accuracy for medical terminology.\n'
|
|
12382
13083
|
),
|
|
12383
13084
|
entities: zod3.array(
|
|
12384
13085
|
zod3.object({
|
|
@@ -12437,108 +13138,49 @@ var createTranscriptResponse = zod3.object({
|
|
|
12437
13138
|
)
|
|
12438
13139
|
}).describe("A detected entity")
|
|
12439
13140
|
).nullish().describe(
|
|
12440
|
-
"An array of results for the Entity Detection model, if it is enabled.\nSee [Entity detection](https://www.assemblyai.com/docs/
|
|
12441
|
-
),
|
|
12442
|
-
speech_threshold: zod3.number().min(createTranscriptResponseSpeechThresholdMin).max(createTranscriptResponseSpeechThresholdMax).nullish().describe(
|
|
12443
|
-
"Defaults to null. Reject audio files that contain less than this fraction of speech.\nValid values are in the range [0, 1] inclusive.\n"
|
|
13141
|
+
"An array of results for the Entity Detection model, if it is enabled.\nSee [Entity detection](https://www.assemblyai.com/docs/speech-understanding/entity-detection) for more information.\n"
|
|
12444
13142
|
),
|
|
12445
|
-
|
|
12446
|
-
"
|
|
13143
|
+
entity_detection: zod3.boolean().nullish().describe(
|
|
13144
|
+
"Whether [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/entity-detection) is enabled, can be true or false"
|
|
12447
13145
|
),
|
|
12448
13146
|
error: zod3.string().optional().describe("Error message of why the transcript failed"),
|
|
12449
|
-
|
|
12450
|
-
|
|
12451
|
-
|
|
12452
|
-
|
|
12453
|
-
|
|
12454
|
-
|
|
12455
|
-
|
|
12456
|
-
|
|
12457
|
-
|
|
12458
|
-
|
|
12459
|
-
|
|
12460
|
-
|
|
12461
|
-
|
|
12462
|
-
|
|
12463
|
-
|
|
12464
|
-
|
|
12465
|
-
)
|
|
12466
|
-
|
|
12467
|
-
|
|
12468
|
-
)
|
|
12469
|
-
|
|
12470
|
-
|
|
12471
|
-
|
|
12472
|
-
|
|
12473
|
-
|
|
12474
|
-
|
|
12475
|
-
"The
|
|
12476
|
-
),
|
|
12477
|
-
|
|
12478
|
-
"The URL to the next page of transcripts. The next URL always points to a page with newer transcripts."
|
|
12479
|
-
)
|
|
13147
|
+
filter_profanity: zod3.boolean().nullish().describe(
|
|
13148
|
+
"Whether [Profanity Filtering](https://www.assemblyai.com/docs/profanity-filtering) is enabled, either true or false"
|
|
13149
|
+
),
|
|
13150
|
+
format_text: zod3.boolean().nullish().describe(
|
|
13151
|
+
"Whether [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio) is enabled, either true or false"
|
|
13152
|
+
),
|
|
13153
|
+
iab_categories: zod3.boolean().nullish().describe(
|
|
13154
|
+
"Whether [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/topic-detection) is enabled, can be true or false"
|
|
13155
|
+
),
|
|
13156
|
+
iab_categories_result: zod3.object({
|
|
13157
|
+
status: zod3.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
13158
|
+
results: zod3.array(
|
|
13159
|
+
zod3.object({
|
|
13160
|
+
text: zod3.string().describe("The text in the transcript in which a detected topic occurs"),
|
|
13161
|
+
labels: zod3.array(
|
|
13162
|
+
zod3.object({
|
|
13163
|
+
relevance: zod3.number().describe("How relevant the detected topic is of a detected topic"),
|
|
13164
|
+
label: zod3.string().describe(
|
|
13165
|
+
"The IAB taxonomical label for the label of the detected topic, where > denotes supertopic/subtopic relationship"
|
|
13166
|
+
)
|
|
13167
|
+
})
|
|
13168
|
+
).optional().describe("An array of detected topics in the text"),
|
|
13169
|
+
timestamp: zod3.object({
|
|
13170
|
+
start: zod3.number().describe("The start time in milliseconds"),
|
|
13171
|
+
end: zod3.number().describe("The end time in milliseconds")
|
|
13172
|
+
}).optional().describe("Timestamp containing a start and end property in milliseconds")
|
|
13173
|
+
}).describe("The result of the topic detection model")
|
|
13174
|
+
).describe("An array of results for the Topic Detection model"),
|
|
13175
|
+
summary: zod3.record(zod3.string(), zod3.number()).describe("The overall relevance of topic to the entire audio file")
|
|
12480
13176
|
}).describe(
|
|
12481
|
-
"
|
|
13177
|
+
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/topic-detection) for more information.\n"
|
|
13178
|
+
).or(zod3.null()).optional().describe(
|
|
13179
|
+
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/topic-detection) for more information.\n"
|
|
12482
13180
|
),
|
|
12483
|
-
transcripts: zod3.array(
|
|
12484
|
-
zod3.object({
|
|
12485
|
-
id: zod3.string().uuid().describe("The unique identifier for the transcript"),
|
|
12486
|
-
resource_url: zod3.string().describe("The URL to retrieve the transcript"),
|
|
12487
|
-
status: zod3.enum(["queued", "processing", "completed", "error"]).describe(
|
|
12488
|
-
"The status of your transcript. Possible values are queued, processing, completed, or error."
|
|
12489
|
-
),
|
|
12490
|
-
created: zod3.string().regex(listTranscriptsResponseTranscriptsItemCreatedRegExp).describe("The date and time the transcript was created"),
|
|
12491
|
-
completed: zod3.string().regex(listTranscriptsResponseTranscriptsItemCompletedRegExp).nullable().describe("The date and time the transcript was completed"),
|
|
12492
|
-
audio_url: zod3.string().describe("The URL to the audio file"),
|
|
12493
|
-
error: zod3.string().nullable().describe("Error message of why the transcript failed")
|
|
12494
|
-
})
|
|
12495
|
-
).describe("An array of transcripts")
|
|
12496
|
-
}).describe(
|
|
12497
|
-
"A list of transcripts. Transcripts are sorted from newest to oldest. The previous URL always points to a page with older transcripts."
|
|
12498
|
-
);
|
|
12499
|
-
var getTranscriptParams = zod3.object({
|
|
12500
|
-
transcript_id: zod3.string().describe("ID of the transcript")
|
|
12501
|
-
});
|
|
12502
|
-
var getTranscriptResponseLanguageConfidenceThresholdMin = 0;
|
|
12503
|
-
var getTranscriptResponseLanguageConfidenceThresholdMax = 1;
|
|
12504
|
-
var getTranscriptResponseLanguageConfidenceMin = 0;
|
|
12505
|
-
var getTranscriptResponseLanguageConfidenceMax = 1;
|
|
12506
|
-
var getTranscriptResponseSpeechModelDefault = null;
|
|
12507
|
-
var getTranscriptResponseWordsItemConfidenceMin = 0;
|
|
12508
|
-
var getTranscriptResponseWordsItemConfidenceMax = 1;
|
|
12509
|
-
var getTranscriptResponseUtterancesItemConfidenceMin = 0;
|
|
12510
|
-
var getTranscriptResponseUtterancesItemConfidenceMax = 1;
|
|
12511
|
-
var getTranscriptResponseUtterancesItemWordsItemConfidenceMin = 0;
|
|
12512
|
-
var getTranscriptResponseUtterancesItemWordsItemConfidenceMax = 1;
|
|
12513
|
-
var getTranscriptResponseConfidenceMin = 0;
|
|
12514
|
-
var getTranscriptResponseConfidenceMax = 1;
|
|
12515
|
-
var getTranscriptResponseAutoHighlightsResultResultsItemRankMin = 0;
|
|
12516
|
-
var getTranscriptResponseAutoHighlightsResultResultsItemRankMax = 1;
|
|
12517
|
-
var getTranscriptResponseContentSafetyLabelsResultsItemLabelsItemConfidenceMin = 0;
|
|
12518
|
-
var getTranscriptResponseContentSafetyLabelsResultsItemLabelsItemConfidenceMax = 1;
|
|
12519
|
-
var getTranscriptResponseContentSafetyLabelsResultsItemLabelsItemSeverityMin = 0;
|
|
12520
|
-
var getTranscriptResponseContentSafetyLabelsResultsItemLabelsItemSeverityMax = 1;
|
|
12521
|
-
var getTranscriptResponseContentSafetyLabelsSummaryMinOne = 0;
|
|
12522
|
-
var getTranscriptResponseContentSafetyLabelsSummaryMaxOne = 1;
|
|
12523
|
-
var getTranscriptResponseContentSafetyLabelsSeverityScoreSummaryLowMin = 0;
|
|
12524
|
-
var getTranscriptResponseContentSafetyLabelsSeverityScoreSummaryLowMax = 1;
|
|
12525
|
-
var getTranscriptResponseContentSafetyLabelsSeverityScoreSummaryMediumMin = 0;
|
|
12526
|
-
var getTranscriptResponseContentSafetyLabelsSeverityScoreSummaryMediumMax = 1;
|
|
12527
|
-
var getTranscriptResponseContentSafetyLabelsSeverityScoreSummaryHighMin = 0;
|
|
12528
|
-
var getTranscriptResponseContentSafetyLabelsSeverityScoreSummaryHighMax = 1;
|
|
12529
|
-
var getTranscriptResponseIabCategoriesResultResultsItemLabelsItemRelevanceMin = 0;
|
|
12530
|
-
var getTranscriptResponseIabCategoriesResultResultsItemLabelsItemRelevanceMax = 1;
|
|
12531
|
-
var getTranscriptResponseIabCategoriesResultSummaryMinOne = 0;
|
|
12532
|
-
var getTranscriptResponseIabCategoriesResultSummaryMaxOne = 1;
|
|
12533
|
-
var getTranscriptResponseSentimentAnalysisResultsItemConfidenceMin = 0;
|
|
12534
|
-
var getTranscriptResponseSentimentAnalysisResultsItemConfidenceMax = 1;
|
|
12535
|
-
var getTranscriptResponseSpeechThresholdMin = 0;
|
|
12536
|
-
var getTranscriptResponseSpeechThresholdMax = 1;
|
|
12537
|
-
var getTranscriptResponse = zod3.object({
|
|
12538
13181
|
id: zod3.string().uuid().describe("The unique identifier of your transcript"),
|
|
12539
|
-
|
|
12540
|
-
|
|
12541
|
-
"The status of your transcript. Possible values are queued, processing, completed, or error."
|
|
13182
|
+
keyterms_prompt: zod3.array(zod3.string()).optional().describe(
|
|
13183
|
+
"Improve accuracy with up to 200 (for Universal-2) or 1000 (for Universal-3 Pro) domain-specific words or phrases (maximum 6 words per phrase). See [Keyterms Prompting](https://www.assemblyai.com/docs/pre-recorded-audio/keyterms-prompting) for more details.\n"
|
|
12542
13184
|
),
|
|
12543
13185
|
language_code: zod3.enum([
|
|
12544
13186
|
"en",
|
|
@@ -12643,138 +13285,175 @@ var getTranscriptResponse = zod3.object({
|
|
|
12643
13285
|
"cy",
|
|
12644
13286
|
"yi",
|
|
12645
13287
|
"yo"
|
|
12646
|
-
]).describe(
|
|
12647
|
-
"The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/
|
|
12648
|
-
).or(zod3.string()).optional().describe(
|
|
12649
|
-
"The language of your audio file.\nPossible values are found in [Supported Languages](https://www.assemblyai.com/docs/concepts/supported-languages).\nThe default value is 'en_us'.\n"
|
|
12650
|
-
),
|
|
12651
|
-
language_detection: zod3.boolean().nullish().describe(
|
|
12652
|
-
"Whether [Automatic language detection](https://www.assemblyai.com/docs/models/speech-recognition#automatic-language-detection) is enabled, either true or false"
|
|
12653
|
-
),
|
|
12654
|
-
language_confidence_threshold: zod3.number().min(getTranscriptResponseLanguageConfidenceThresholdMin).max(getTranscriptResponseLanguageConfidenceThresholdMax).nullable().describe(
|
|
12655
|
-
"The confidence threshold for the automatically detected language.\nAn error will be returned if the language confidence is below this threshold.\n"
|
|
12656
|
-
),
|
|
12657
|
-
language_confidence: zod3.number().min(getTranscriptResponseLanguageConfidenceMin).max(getTranscriptResponseLanguageConfidenceMax).nullable().describe(
|
|
12658
|
-
"The confidence score for the detected language, between 0.0 (low confidence) and 1.0 (high confidence)"
|
|
12659
|
-
),
|
|
12660
|
-
speech_model: zod3.enum(["best", "slam-1", "universal"]).describe("The speech model to use for the transcription.").or(zod3.null()).describe(
|
|
12661
|
-
"The speech model used for the transcription. When `null`, the default model is used."
|
|
12662
|
-
),
|
|
12663
|
-
text: zod3.string().nullish().describe("The textual transcript of your media file"),
|
|
12664
|
-
words: zod3.array(
|
|
12665
|
-
zod3.object({
|
|
12666
|
-
confidence: zod3.number().min(getTranscriptResponseWordsItemConfidenceMin).max(getTranscriptResponseWordsItemConfidenceMax).describe("The confidence score for the transcript of this word"),
|
|
12667
|
-
start: zod3.number().describe("The starting time, in milliseconds, for the word"),
|
|
12668
|
-
end: zod3.number().describe("The ending time, in milliseconds, for the word"),
|
|
12669
|
-
text: zod3.string().describe("The text of the word"),
|
|
12670
|
-
channel: zod3.string().nullish().describe(
|
|
12671
|
-
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
12672
|
-
),
|
|
12673
|
-
speaker: zod3.string().nullable().describe(
|
|
12674
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/models/speaker-diarization) is enabled, else null"
|
|
12675
|
-
)
|
|
12676
|
-
})
|
|
12677
|
-
).nullish().describe(
|
|
12678
|
-
"An array of temporally-sequential word objects, one for each word in the transcript.\nSee [Speech recognition](https://www.assemblyai.com/docs/models/speech-recognition) for more information.\n"
|
|
13288
|
+
]).optional().describe(
|
|
13289
|
+
"The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/pre-recorded-audio/supported-languages).\nThe default value is 'en_us'.\n"
|
|
12679
13290
|
),
|
|
12680
|
-
|
|
12681
|
-
zod3.
|
|
12682
|
-
|
|
12683
|
-
|
|
12684
|
-
|
|
12685
|
-
|
|
12686
|
-
|
|
12687
|
-
|
|
12688
|
-
|
|
12689
|
-
|
|
12690
|
-
|
|
12691
|
-
|
|
12692
|
-
|
|
12693
|
-
|
|
12694
|
-
|
|
12695
|
-
|
|
12696
|
-
|
|
12697
|
-
|
|
12698
|
-
|
|
12699
|
-
|
|
12700
|
-
|
|
12701
|
-
|
|
12702
|
-
|
|
12703
|
-
|
|
12704
|
-
|
|
12705
|
-
|
|
12706
|
-
|
|
13291
|
+
language_codes: zod3.array(
|
|
13292
|
+
zod3.enum([
|
|
13293
|
+
"en",
|
|
13294
|
+
"en_au",
|
|
13295
|
+
"en_uk",
|
|
13296
|
+
"en_us",
|
|
13297
|
+
"es",
|
|
13298
|
+
"fr",
|
|
13299
|
+
"de",
|
|
13300
|
+
"it",
|
|
13301
|
+
"pt",
|
|
13302
|
+
"nl",
|
|
13303
|
+
"af",
|
|
13304
|
+
"sq",
|
|
13305
|
+
"am",
|
|
13306
|
+
"ar",
|
|
13307
|
+
"hy",
|
|
13308
|
+
"as",
|
|
13309
|
+
"az",
|
|
13310
|
+
"ba",
|
|
13311
|
+
"eu",
|
|
13312
|
+
"be",
|
|
13313
|
+
"bn",
|
|
13314
|
+
"bs",
|
|
13315
|
+
"br",
|
|
13316
|
+
"bg",
|
|
13317
|
+
"my",
|
|
13318
|
+
"ca",
|
|
13319
|
+
"zh",
|
|
13320
|
+
"hr",
|
|
13321
|
+
"cs",
|
|
13322
|
+
"da",
|
|
13323
|
+
"et",
|
|
13324
|
+
"fo",
|
|
13325
|
+
"fi",
|
|
13326
|
+
"gl",
|
|
13327
|
+
"ka",
|
|
13328
|
+
"el",
|
|
13329
|
+
"gu",
|
|
13330
|
+
"ht",
|
|
13331
|
+
"ha",
|
|
13332
|
+
"haw",
|
|
13333
|
+
"he",
|
|
13334
|
+
"hi",
|
|
13335
|
+
"hu",
|
|
13336
|
+
"is",
|
|
13337
|
+
"id",
|
|
13338
|
+
"ja",
|
|
13339
|
+
"jw",
|
|
13340
|
+
"kn",
|
|
13341
|
+
"kk",
|
|
13342
|
+
"km",
|
|
13343
|
+
"ko",
|
|
13344
|
+
"lo",
|
|
13345
|
+
"la",
|
|
13346
|
+
"lv",
|
|
13347
|
+
"ln",
|
|
13348
|
+
"lt",
|
|
13349
|
+
"lb",
|
|
13350
|
+
"mk",
|
|
13351
|
+
"mg",
|
|
13352
|
+
"ms",
|
|
13353
|
+
"ml",
|
|
13354
|
+
"mt",
|
|
13355
|
+
"mi",
|
|
13356
|
+
"mr",
|
|
13357
|
+
"mn",
|
|
13358
|
+
"ne",
|
|
13359
|
+
"no",
|
|
13360
|
+
"nn",
|
|
13361
|
+
"oc",
|
|
13362
|
+
"pa",
|
|
13363
|
+
"ps",
|
|
13364
|
+
"fa",
|
|
13365
|
+
"pl",
|
|
13366
|
+
"ro",
|
|
13367
|
+
"ru",
|
|
13368
|
+
"sa",
|
|
13369
|
+
"sr",
|
|
13370
|
+
"sn",
|
|
13371
|
+
"sd",
|
|
13372
|
+
"si",
|
|
13373
|
+
"sk",
|
|
13374
|
+
"sl",
|
|
13375
|
+
"so",
|
|
13376
|
+
"su",
|
|
13377
|
+
"sw",
|
|
13378
|
+
"sv",
|
|
13379
|
+
"tl",
|
|
13380
|
+
"tg",
|
|
13381
|
+
"ta",
|
|
13382
|
+
"tt",
|
|
13383
|
+
"te",
|
|
13384
|
+
"th",
|
|
13385
|
+
"bo",
|
|
13386
|
+
"tr",
|
|
13387
|
+
"tk",
|
|
13388
|
+
"uk",
|
|
13389
|
+
"ur",
|
|
13390
|
+
"uz",
|
|
13391
|
+
"vi",
|
|
13392
|
+
"cy",
|
|
13393
|
+
"yi",
|
|
13394
|
+
"yo"
|
|
13395
|
+
]).describe(
|
|
13396
|
+
"The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/pre-recorded-audio/supported-languages).\nThe default value is 'en_us'.\n"
|
|
13397
|
+
)
|
|
12707
13398
|
).nullish().describe(
|
|
12708
|
-
"
|
|
13399
|
+
"The language codes of your audio file. Used for [Code switching](/docs/speech-to-text/pre-recorded-audio/code-switching)\nOne of the values specified must be `en`.\n"
|
|
12709
13400
|
),
|
|
12710
|
-
|
|
12711
|
-
"The confidence score for the
|
|
13401
|
+
language_confidence: zod3.number().nullable().describe(
|
|
13402
|
+
"The confidence score for the detected language, between 0.0 (low confidence) and 1.0 (high confidence). See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details."
|
|
12712
13403
|
),
|
|
12713
|
-
|
|
12714
|
-
|
|
12715
|
-
format_text: zod3.boolean().nullish().describe("Whether Text Formatting is enabled, either true or false"),
|
|
12716
|
-
disfluencies: zod3.boolean().nullish().describe('Transcribe Filler Words, like "umm", in your media file; can be true or false'),
|
|
12717
|
-
multichannel: zod3.boolean().nullish().describe(
|
|
12718
|
-
"Whether [Multichannel transcription](https://www.assemblyai.com/docs/models/speech-recognition#multichannel-transcription) was enabled in the transcription request, either true or false"
|
|
12719
|
-
),
|
|
12720
|
-
audio_channels: zod3.number().optional().describe(
|
|
12721
|
-
"The number of audio channels in the audio file. This is only present when multichannel is enabled."
|
|
12722
|
-
),
|
|
12723
|
-
webhook_url: zod3.string().nullish().describe(
|
|
12724
|
-
"The URL to which we send webhook requests.\nWe sends two different types of webhook requests.\nOne request when a transcript is completed or failed, and one request when the redacted audio is ready if redact_pii_audio is enabled.\n"
|
|
12725
|
-
),
|
|
12726
|
-
webhook_status_code: zod3.number().nullish().describe(
|
|
12727
|
-
"The status code we received from your server when delivering the transcript completed or failed webhook request, if a webhook URL was provided"
|
|
13404
|
+
language_confidence_threshold: zod3.number().nullable().describe(
|
|
13405
|
+
"The confidence threshold for the automatically detected language.\nAn error will be returned if the language confidence is below this threshold.\nSee [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.\n"
|
|
12728
13406
|
),
|
|
12729
|
-
|
|
12730
|
-
|
|
12731
|
-
"The header name to be sent with the transcript completed or failed webhook requests"
|
|
13407
|
+
language_detection: zod3.boolean().nullish().describe(
|
|
13408
|
+
"Whether [Automatic language detection](/docs/pre-recorded-audio/automatic-language-detection) is enabled, either true or false"
|
|
12732
13409
|
),
|
|
12733
|
-
|
|
12734
|
-
|
|
12735
|
-
|
|
12736
|
-
|
|
12737
|
-
|
|
12738
|
-
|
|
12739
|
-
|
|
12740
|
-
|
|
12741
|
-
|
|
12742
|
-
|
|
12743
|
-
|
|
12744
|
-
|
|
12745
|
-
|
|
12746
|
-
|
|
12747
|
-
|
|
12748
|
-
|
|
12749
|
-
|
|
12750
|
-
})
|
|
12751
|
-
).describe("A temporally-sequential array of Key Phrases")
|
|
12752
|
-
}).describe(
|
|
12753
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key phrases](https://www.assemblyai.com/docs/models/key-phrases) for more information.\n"
|
|
12754
|
-
).or(zod3.null()).optional().describe(
|
|
12755
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key Phrases](https://www.assemblyai.com/docs/models/key-phrases) for more information.\n"
|
|
13410
|
+
language_detection_options: zod3.object({
|
|
13411
|
+
expected_languages: zod3.array(zod3.string()).optional().describe(
|
|
13412
|
+
'List of languages expected in the audio file. Defaults to `["all"]` when unspecified. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.'
|
|
13413
|
+
),
|
|
13414
|
+
fallback_language: zod3.string().default(getTranscriptResponseLanguageDetectionOptionsFallbackLanguageDefault).describe(
|
|
13415
|
+
'If the detected language of the audio file is not in the list of expected languages, the `fallback_language` is used. Specify `["auto"]` to let our model choose the fallback language from `expected_languages` with the highest confidence score. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.\n'
|
|
13416
|
+
),
|
|
13417
|
+
code_switching: zod3.boolean().optional().describe(
|
|
13418
|
+
"Whether [code switching](/docs/speech-to-text/pre-recorded-audio/code-switching) should be detected.\n"
|
|
13419
|
+
),
|
|
13420
|
+
code_switching_confidence_threshold: zod3.number().default(
|
|
13421
|
+
getTranscriptResponseLanguageDetectionOptionsCodeSwitchingConfidenceThresholdDefault
|
|
13422
|
+
).describe(
|
|
13423
|
+
"The confidence threshold for [code switching](/docs/speech-to-text/pre-recorded-audio/code-switching) detection. If the code switching confidence is below this threshold, the transcript will be processed in the language with the highest `language_detection_confidence` score.\n"
|
|
13424
|
+
)
|
|
13425
|
+
}).optional().describe(
|
|
13426
|
+
"Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection)."
|
|
12756
13427
|
),
|
|
12757
|
-
|
|
12758
|
-
"
|
|
13428
|
+
multichannel: zod3.boolean().nullish().describe(
|
|
13429
|
+
"Whether [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/multichannel) was enabled in the transcription request, either true or false"
|
|
12759
13430
|
),
|
|
12760
|
-
|
|
12761
|
-
"
|
|
13431
|
+
prompt: zod3.string().optional().describe(
|
|
13432
|
+
"Provide natural language prompting of up to 1,500 words of contextual information to the model. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for best practices.\n\nNote: This parameter is only supported for the Universal-3 Pro model.\n"
|
|
12762
13433
|
),
|
|
12763
|
-
|
|
12764
|
-
|
|
12765
|
-
filter_profanity: zod3.boolean().nullish().describe(
|
|
12766
|
-
"Whether [Profanity Filtering](https://www.assemblyai.com/docs/models/speech-recognition#profanity-filtering) is enabled, either true or false"
|
|
13434
|
+
punctuate: zod3.boolean().nullish().describe(
|
|
13435
|
+
"Whether [Automatic Punctuation](https://www.assemblyai.com/docs/pre-recorded-audio) is enabled, either true or false"
|
|
12767
13436
|
),
|
|
12768
13437
|
redact_pii: zod3.boolean().describe(
|
|
12769
|
-
"Whether [PII Redaction](https://www.assemblyai.com/docs/
|
|
13438
|
+
"Whether [PII Redaction](https://www.assemblyai.com/docs/pii-redaction) is enabled, either true or false"
|
|
12770
13439
|
),
|
|
12771
13440
|
redact_pii_audio: zod3.boolean().nullish().describe(
|
|
12772
|
-
"Whether a redacted version of the audio file was generated,\neither true or false. See [PII redaction](https://www.assemblyai.com/docs/
|
|
13441
|
+
"Whether a redacted version of the audio file was generated,\neither true or false. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more information.\n"
|
|
13442
|
+
),
|
|
13443
|
+
redact_pii_audio_options: zod3.object({
|
|
13444
|
+
return_redacted_no_speech_audio: zod3.boolean().optional().describe(
|
|
13445
|
+
"By default, audio redaction provides redacted audio URLs only when speech is detected. However, if your use-case specifically requires redacted audio files even for silent audio files without any dialogue, you can opt to receive these URLs by setting this parameter to `true`."
|
|
13446
|
+
),
|
|
13447
|
+
override_audio_redaction_method: zod3.enum(["silence"]).optional().describe(
|
|
13448
|
+
"Specify the method used to redact audio. By default, redacted audio uses a beep sound. Set to `silence` to replace PII with silence instead of a beep."
|
|
13449
|
+
)
|
|
13450
|
+
}).optional().describe(
|
|
13451
|
+
"The options for PII-redacted audio, if redact_pii_audio is enabled.\nSee [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more information.\n"
|
|
12773
13452
|
),
|
|
12774
13453
|
redact_pii_audio_quality: zod3.enum(["mp3", "wav"]).describe(
|
|
12775
|
-
"Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See [PII redaction](https://www.assemblyai.com/docs/
|
|
13454
|
+
"Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more details."
|
|
12776
13455
|
).or(zod3.null()).optional().describe(
|
|
12777
|
-
"The audio quality of the PII-redacted audio file, if redact_pii_audio is enabled.\nSee [PII redaction](https://www.assemblyai.com/docs/
|
|
13456
|
+
"The audio quality of the PII-redacted audio file, if redact_pii_audio is enabled.\nSee [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more information.\n"
|
|
12778
13457
|
),
|
|
12779
13458
|
redact_pii_policies: zod3.array(
|
|
12780
13459
|
zod3.enum([
|
|
@@ -12824,19 +13503,307 @@ var getTranscriptResponse = zod3.object({
|
|
|
12824
13503
|
"zodiac_sign"
|
|
12825
13504
|
]).describe("The type of PII to redact")
|
|
12826
13505
|
).nullish().describe(
|
|
12827
|
-
"The list of PII Redaction policies that were enabled, if PII Redaction is enabled.\nSee [PII redaction](https://www.assemblyai.com/docs/
|
|
13506
|
+
"The list of PII Redaction policies that were enabled, if PII Redaction is enabled.\nSee [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more information.\n"
|
|
12828
13507
|
),
|
|
12829
13508
|
redact_pii_sub: zod3.enum(["entity_name", "hash"]).optional().describe(
|
|
12830
|
-
|
|
13509
|
+
"The replacement logic for detected PII, can be `entity_name` or `hash`. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more details."
|
|
13510
|
+
),
|
|
13511
|
+
sentiment_analysis: zod3.boolean().nullish().describe(
|
|
13512
|
+
"Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-analysis) is enabled, can be true or false"
|
|
13513
|
+
),
|
|
13514
|
+
sentiment_analysis_results: zod3.array(
|
|
13515
|
+
zod3.object({
|
|
13516
|
+
text: zod3.string().describe("The transcript of the sentence"),
|
|
13517
|
+
start: zod3.number().describe("The starting time, in milliseconds, of the sentence"),
|
|
13518
|
+
end: zod3.number().describe("The ending time, in milliseconds, of the sentence"),
|
|
13519
|
+
sentiment: zod3.enum(["POSITIVE", "NEUTRAL", "NEGATIVE"]),
|
|
13520
|
+
confidence: zod3.number().describe(
|
|
13521
|
+
"The confidence score for the detected sentiment of the sentence, from 0 to 1"
|
|
13522
|
+
),
|
|
13523
|
+
channel: zod3.string().nullish().describe(
|
|
13524
|
+
"The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
13525
|
+
),
|
|
13526
|
+
speaker: zod3.string().nullable().describe(
|
|
13527
|
+
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization) is enabled, else null"
|
|
13528
|
+
)
|
|
13529
|
+
}).describe("The result of the Sentiment Analysis model")
|
|
13530
|
+
).nullish().describe(
|
|
13531
|
+
"An array of results for the Sentiment Analysis model, if it is enabled.\nSee [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-analysis) for more information.\n"
|
|
12831
13532
|
),
|
|
12832
13533
|
speaker_labels: zod3.boolean().nullish().describe(
|
|
12833
|
-
"Whether [Speaker diarization](https://www.assemblyai.com/docs/
|
|
13534
|
+
"Whether [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization) is enabled, can be true or false"
|
|
12834
13535
|
),
|
|
12835
13536
|
speakers_expected: zod3.number().nullish().describe(
|
|
12836
|
-
"Tell the speaker label model how many speakers it should attempt to identify. See [
|
|
13537
|
+
"Tell the speaker label model how many speakers it should attempt to identify. See [Set number of speakers expected](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization#set-number-of-speakers-expected) for more details."
|
|
13538
|
+
),
|
|
13539
|
+
speech_model_used: zod3.string().optional().describe(
|
|
13540
|
+
"The speech model to use for the transcription. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models."
|
|
13541
|
+
),
|
|
13542
|
+
speech_models: zod3.array(
|
|
13543
|
+
zod3.string().describe(
|
|
13544
|
+
"The speech model to use for the transcription. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models."
|
|
13545
|
+
)
|
|
13546
|
+
).nullish().describe(
|
|
13547
|
+
"List multiple speech models in priority order, allowing our system to automatically route your audio to the best available option. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models and routing behavior.\n"
|
|
13548
|
+
),
|
|
13549
|
+
speech_threshold: zod3.number().nullish().describe(
|
|
13550
|
+
"Defaults to null. Reject audio files that contain less than this fraction of speech.\nValid values are in the range [0, 1] inclusive. See [Speech Threshold](https://www.assemblyai.com/docs/speech-threshold) for more details.\n"
|
|
13551
|
+
),
|
|
13552
|
+
speech_understanding: zod3.object({
|
|
13553
|
+
request: zod3.object({
|
|
13554
|
+
translation: zod3.object({
|
|
13555
|
+
target_languages: zod3.array(zod3.string()).describe(
|
|
13556
|
+
'List of target language codes (e.g., `["es", "de"]`). See [Translation](https://www.assemblyai.com/docs/speech-understanding/translation) for supported languages.'
|
|
13557
|
+
),
|
|
13558
|
+
formal: zod3.boolean().default(getTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault).describe(
|
|
13559
|
+
"Use formal language style. See [Translation](https://www.assemblyai.com/docs/speech-understanding/translation) for more details."
|
|
13560
|
+
),
|
|
13561
|
+
match_original_utterance: zod3.boolean().optional().describe(
|
|
13562
|
+
"When enabled with Speaker Labels, returns translated text in the utterances array. Each utterance will include a `translated_texts` key containing translations for each target language."
|
|
13563
|
+
)
|
|
13564
|
+
})
|
|
13565
|
+
}).describe(
|
|
13566
|
+
"Request body for [Translation](https://www.assemblyai.com/docs/speech-understanding/translation)."
|
|
13567
|
+
).or(
|
|
13568
|
+
zod3.object({
|
|
13569
|
+
speaker_identification: zod3.object({
|
|
13570
|
+
speaker_type: zod3.enum(["role", "name"]).describe(
|
|
13571
|
+
"Type of speaker identification. See [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification) for details on each type."
|
|
13572
|
+
),
|
|
13573
|
+
known_values: zod3.array(zod3.string()).optional().describe(
|
|
13574
|
+
'Required if speaker_type is "role". Each value must be 35 characters or less.'
|
|
13575
|
+
),
|
|
13576
|
+
speakers: zod3.array(
|
|
13577
|
+
zod3.object({
|
|
13578
|
+
role: zod3.string().optional().describe(
|
|
13579
|
+
'The role of the speaker. Required when `speaker_type` is "role".'
|
|
13580
|
+
),
|
|
13581
|
+
name: zod3.string().optional().describe(
|
|
13582
|
+
'The name of the speaker. Required when `speaker_type` is "name".'
|
|
13583
|
+
),
|
|
13584
|
+
description: zod3.string().optional().describe(
|
|
13585
|
+
"A description of the speaker to help the model identify them based on conversational context."
|
|
13586
|
+
)
|
|
13587
|
+
})
|
|
13588
|
+
).optional().describe(
|
|
13589
|
+
"An array of speaker objects with metadata to improve identification accuracy. Each object should include a `role` or `name` (depending on `speaker_type`) and an optional `description` to help the model identify the speaker. You can also include any additional custom properties (e.g., `company`, `title`) to provide more context. Use this as an alternative to `known_values` when you want to provide additional context about each speaker."
|
|
13590
|
+
)
|
|
13591
|
+
})
|
|
13592
|
+
}).describe(
|
|
13593
|
+
"Request body for [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification)."
|
|
13594
|
+
)
|
|
13595
|
+
).or(
|
|
13596
|
+
zod3.object({
|
|
13597
|
+
custom_formatting: zod3.object({
|
|
13598
|
+
date: zod3.string().optional().describe(
|
|
13599
|
+
'Date format pattern (e.g., `"mm/dd/yyyy"`). See [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting) for more details.'
|
|
13600
|
+
),
|
|
13601
|
+
phone_number: zod3.string().optional().describe(
|
|
13602
|
+
'Phone number format pattern (e.g., `"(xxx)xxx-xxxx"`). See [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting) for more details.'
|
|
13603
|
+
),
|
|
13604
|
+
email: zod3.string().optional().describe(
|
|
13605
|
+
'Email format pattern (e.g., `"username@domain.com"`). See [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting) for more details.'
|
|
13606
|
+
)
|
|
13607
|
+
})
|
|
13608
|
+
}).describe(
|
|
13609
|
+
"Request body for [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting)."
|
|
13610
|
+
)
|
|
13611
|
+
).optional(),
|
|
13612
|
+
response: zod3.object({
|
|
13613
|
+
translation: zod3.object({
|
|
13614
|
+
status: zod3.string().optional()
|
|
13615
|
+
}).optional()
|
|
13616
|
+
}).or(
|
|
13617
|
+
zod3.object({
|
|
13618
|
+
speaker_identification: zod3.object({
|
|
13619
|
+
mapping: zod3.record(zod3.string(), zod3.string()).optional().describe(
|
|
13620
|
+
'A mapping of the original generic speaker labels (e.g., "A", "B") to the identified speaker names or roles.'
|
|
13621
|
+
),
|
|
13622
|
+
status: zod3.string().optional()
|
|
13623
|
+
}).optional()
|
|
13624
|
+
})
|
|
13625
|
+
).or(
|
|
13626
|
+
zod3.object({
|
|
13627
|
+
custom_formatting: zod3.object({
|
|
13628
|
+
mapping: zod3.record(zod3.string(), zod3.string()).optional(),
|
|
13629
|
+
formatted_text: zod3.string().optional()
|
|
13630
|
+
}).optional()
|
|
13631
|
+
})
|
|
13632
|
+
).optional()
|
|
13633
|
+
}).optional().describe(
|
|
13634
|
+
"Speech understanding tasks like [Translation](https://www.assemblyai.com/docs/speech-understanding/translation), [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification), and [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting). See the task-specific docs for available options and configuration.\n"
|
|
13635
|
+
),
|
|
13636
|
+
status: zod3.enum(["queued", "processing", "completed", "error"]).describe(
|
|
13637
|
+
"The status of your transcript. Possible values are queued, processing, completed, or error."
|
|
13638
|
+
),
|
|
13639
|
+
summarization: zod3.boolean().describe(
|
|
13640
|
+
"Whether [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization) is enabled, either true or false. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
13641
|
+
),
|
|
13642
|
+
summary: zod3.string().nullish().describe(
|
|
13643
|
+
"The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization) is enabled. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details."
|
|
13644
|
+
),
|
|
13645
|
+
summary_model: zod3.string().nullish().describe(
|
|
13646
|
+
"The Summarization model used to generate the summary,\nif [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization#summary-models) is enabled. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details.\n"
|
|
13647
|
+
),
|
|
13648
|
+
summary_type: zod3.string().nullish().describe(
|
|
13649
|
+
"The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization#summary-types) is enabled. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details."
|
|
13650
|
+
),
|
|
13651
|
+
remove_audio_tags: zod3.enum(["all"]).describe(
|
|
13652
|
+
"Whether [audio event tags](https://www.assemblyai.com/docs/pre-recorded-audio/universal-3-pro#audio-event-tags) were removed from the transcript text.\n\nNote: This parameter is only supported for the Universal-3 Pro model.\n"
|
|
13653
|
+
).or(zod3.null()).optional().describe(
|
|
13654
|
+
"Whether [audio event tags](https://www.assemblyai.com/docs/pre-recorded-audio/universal-3-pro#audio-event-tags) were removed from the transcript text.\n\nNote: This parameter is only supported for the Universal-3 Pro model.\n"
|
|
13655
|
+
),
|
|
13656
|
+
temperature: zod3.number().nullish().describe(
|
|
13657
|
+
"The temperature that was used for the model's response. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for more details.\n\nNote: This parameter can only be used with the Universal-3 Pro model.\n"
|
|
13658
|
+
),
|
|
13659
|
+
text: zod3.string().nullish().describe("The textual transcript of your media file"),
|
|
13660
|
+
throttled: zod3.boolean().nullish().describe(
|
|
13661
|
+
"True while a request is throttled and false when a request is no longer throttled"
|
|
13662
|
+
),
|
|
13663
|
+
utterances: zod3.array(
|
|
13664
|
+
zod3.object({
|
|
13665
|
+
confidence: zod3.number().describe("The confidence score for the transcript of this utterance"),
|
|
13666
|
+
start: zod3.number().describe("The starting time, in milliseconds, of the utterance in the audio file"),
|
|
13667
|
+
end: zod3.number().describe("The ending time, in milliseconds, of the utterance in the audio file"),
|
|
13668
|
+
text: zod3.string().describe("The text for this utterance"),
|
|
13669
|
+
words: zod3.array(
|
|
13670
|
+
zod3.object({
|
|
13671
|
+
confidence: zod3.number().describe("The confidence score for the transcript of this word"),
|
|
13672
|
+
start: zod3.number().describe("The starting time, in milliseconds, for the word"),
|
|
13673
|
+
end: zod3.number().describe("The ending time, in milliseconds, for the word"),
|
|
13674
|
+
text: zod3.string().describe("The text of the word"),
|
|
13675
|
+
channel: zod3.string().nullish().describe(
|
|
13676
|
+
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
13677
|
+
),
|
|
13678
|
+
speaker: zod3.string().nullable().describe(
|
|
13679
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization) is enabled, else null"
|
|
13680
|
+
)
|
|
13681
|
+
})
|
|
13682
|
+
).describe("The words in the utterance."),
|
|
13683
|
+
channel: zod3.string().nullish().describe(
|
|
13684
|
+
"The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
13685
|
+
),
|
|
13686
|
+
speaker: zod3.string().describe(
|
|
13687
|
+
'The speaker of this utterance, where each speaker is assigned a sequential capital letter - e.g. "A" for Speaker A, "B" for Speaker B, etc.'
|
|
13688
|
+
),
|
|
13689
|
+
translated_texts: zod3.record(zod3.string(), zod3.string()).optional().describe(
|
|
13690
|
+
'Translations keyed by language code (e.g., `{"es": "Texto traducido", "de": "\xDCbersetzter Text"}`). Only present when `match_original_utterance` is enabled with translation.'
|
|
13691
|
+
)
|
|
13692
|
+
})
|
|
13693
|
+
).nullish().describe(
|
|
13694
|
+
"When multichannel or speaker_labels is enabled, a list of turn-by-turn utterance objects.\nSee [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization) and [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/multichannel) for more information.\n"
|
|
13695
|
+
),
|
|
13696
|
+
webhook_auth: zod3.boolean().describe(
|
|
13697
|
+
"Whether [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) authentication details were provided"
|
|
13698
|
+
),
|
|
13699
|
+
webhook_auth_header_name: zod3.string().nullish().describe(
|
|
13700
|
+
"The header name to be sent with the transcript completed or failed [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) requests"
|
|
13701
|
+
),
|
|
13702
|
+
webhook_status_code: zod3.number().nullish().describe(
|
|
13703
|
+
"The status code we received from your server when delivering the transcript completed or failed [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) request, if a webhook URL was provided"
|
|
13704
|
+
),
|
|
13705
|
+
webhook_url: zod3.string().nullish().describe(
|
|
13706
|
+
"The URL to which we send [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) requests.\n"
|
|
13707
|
+
),
|
|
13708
|
+
words: zod3.array(
|
|
13709
|
+
zod3.object({
|
|
13710
|
+
confidence: zod3.number().describe("The confidence score for the transcript of this word"),
|
|
13711
|
+
start: zod3.number().describe("The starting time, in milliseconds, for the word"),
|
|
13712
|
+
end: zod3.number().describe("The ending time, in milliseconds, for the word"),
|
|
13713
|
+
text: zod3.string().describe("The text of the word"),
|
|
13714
|
+
channel: zod3.string().nullish().describe(
|
|
13715
|
+
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
13716
|
+
),
|
|
13717
|
+
speaker: zod3.string().nullable().describe(
|
|
13718
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization) is enabled, else null"
|
|
13719
|
+
)
|
|
13720
|
+
})
|
|
13721
|
+
).nullish().describe(
|
|
13722
|
+
"An array of temporally-sequential word objects, one for each word in the transcript.\n"
|
|
13723
|
+
),
|
|
13724
|
+
acoustic_model: zod3.string().describe("This parameter does not currently have any functionality attached to it."),
|
|
13725
|
+
custom_topics: zod3.boolean().nullish().describe("This parameter does not currently have any functionality attached to it."),
|
|
13726
|
+
language_model: zod3.string().describe("This parameter does not currently have any functionality attached to it."),
|
|
13727
|
+
speech_model: zod3.string().describe(
|
|
13728
|
+
"The speech model to use for the transcription. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models."
|
|
13729
|
+
).or(zod3.null()).describe(
|
|
13730
|
+
"This parameter has been replaced with the `speech_models` parameter, learn more about the `speech_models` parameter [here](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model).\n"
|
|
13731
|
+
),
|
|
13732
|
+
speed_boost: zod3.boolean().nullish().describe("This parameter does not currently have any functionality attached to it."),
|
|
13733
|
+
topics: zod3.array(zod3.string()).optional().describe("This parameter does not currently have any functionality attached to it."),
|
|
13734
|
+
translated_texts: zod3.object({
|
|
13735
|
+
language_code: zod3.string().optional().describe("Translated text for this language code")
|
|
13736
|
+
}).optional().describe(
|
|
13737
|
+
"Translated text keyed by language code. See [Translation](https://www.assemblyai.com/docs/speech-understanding/translation) for more details."
|
|
13738
|
+
)
|
|
13739
|
+
}).describe("A transcript object");
|
|
13740
|
+
var deleteTranscriptParams = zod3.object({
|
|
13741
|
+
transcript_id: zod3.string().describe("ID of the transcript")
|
|
13742
|
+
});
|
|
13743
|
+
var deleteTranscriptResponseLanguageDetectionOptionsFallbackLanguageDefault = "auto";
|
|
13744
|
+
var deleteTranscriptResponseLanguageDetectionOptionsCodeSwitchingDefault = false;
|
|
13745
|
+
var deleteTranscriptResponseLanguageDetectionOptionsCodeSwitchingConfidenceThresholdDefault = 0.3;
|
|
13746
|
+
var deleteTranscriptResponseRedactPiiAudioOptionsReturnRedactedNoSpeechAudioDefault = false;
|
|
13747
|
+
var deleteTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault = true;
|
|
13748
|
+
var deleteTranscriptResponseSpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault = false;
|
|
13749
|
+
var deleteTranscriptResponse = zod3.object({
|
|
13750
|
+
audio_channels: zod3.number().optional().describe(
|
|
13751
|
+
"The number of audio channels in the audio file. This is only present when [multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/multichannel) is enabled."
|
|
13752
|
+
),
|
|
13753
|
+
audio_duration: zod3.number().nullish().describe("The duration of this transcript object's media file, in seconds"),
|
|
13754
|
+
audio_end_at: zod3.number().nullish().describe(
|
|
13755
|
+
"The point in time, in milliseconds, in the file at which the transcription was terminated. See [Set the start and end of the transcript](https://www.assemblyai.com/docs/pre-recorded-audio/set-the-start-and-end-of-the-transcript) for more details."
|
|
13756
|
+
),
|
|
13757
|
+
audio_start_from: zod3.number().nullish().describe(
|
|
13758
|
+
"The point in time, in milliseconds, in the file at which the transcription was started. See [Set the start and end of the transcript](https://www.assemblyai.com/docs/pre-recorded-audio/set-the-start-and-end-of-the-transcript) for more details."
|
|
13759
|
+
),
|
|
13760
|
+
audio_url: zod3.string().describe("The URL of the media that was transcribed"),
|
|
13761
|
+
auto_chapters: zod3.boolean().nullish().describe(
|
|
13762
|
+
"Whether [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/auto-chapters) is enabled, can be true or false. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible chapter summaries. See the [updated Auto Chapters page](https://www.assemblyai.com/docs/speech-understanding/auto-chapters) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
13763
|
+
),
|
|
13764
|
+
auto_highlights: zod3.boolean().describe(
|
|
13765
|
+
"Whether [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/key-phrases) is enabled, either true or false"
|
|
13766
|
+
),
|
|
13767
|
+
auto_highlights_result: zod3.object({
|
|
13768
|
+
status: zod3.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
13769
|
+
results: zod3.array(
|
|
13770
|
+
zod3.object({
|
|
13771
|
+
count: zod3.number().describe("The total number of times the key phrase appears in the audio file"),
|
|
13772
|
+
rank: zod3.number().describe(
|
|
13773
|
+
"The total relevancy to the overall audio file of this key phrase - a greater number means more relevant"
|
|
13774
|
+
),
|
|
13775
|
+
text: zod3.string().describe("The text itself of the key phrase"),
|
|
13776
|
+
timestamps: zod3.array(
|
|
13777
|
+
zod3.object({
|
|
13778
|
+
start: zod3.number().describe("The start time in milliseconds"),
|
|
13779
|
+
end: zod3.number().describe("The end time in milliseconds")
|
|
13780
|
+
}).describe("Timestamp containing a start and end property in milliseconds")
|
|
13781
|
+
).describe("The timestamp of the of the key phrase")
|
|
13782
|
+
})
|
|
13783
|
+
).describe("A temporally-sequential array of Key Phrases")
|
|
13784
|
+
}).describe(
|
|
13785
|
+
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key phrases](https://www.assemblyai.com/docs/speech-understanding/key-phrases) for more information.\n"
|
|
13786
|
+
).or(zod3.null()).optional().describe(
|
|
13787
|
+
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/key-phrases) for more information.\n"
|
|
13788
|
+
),
|
|
13789
|
+
chapters: zod3.array(
|
|
13790
|
+
zod3.object({
|
|
13791
|
+
gist: zod3.string().describe(
|
|
13792
|
+
"An ultra-short summary (just a few words) of the content spoken in the chapter"
|
|
13793
|
+
),
|
|
13794
|
+
headline: zod3.string().describe("A single sentence summary of the content spoken during the chapter"),
|
|
13795
|
+
summary: zod3.string().describe("A one paragraph summary of the content spoken during the chapter"),
|
|
13796
|
+
start: zod3.number().describe("The starting time, in milliseconds, for the chapter"),
|
|
13797
|
+
end: zod3.number().describe("The starting time, in milliseconds, for the chapter")
|
|
13798
|
+
}).describe("Chapter of the audio file")
|
|
13799
|
+
).nullish().describe(
|
|
13800
|
+
"An array of temporally sequential chapters for the audio file. See [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/auto-chapters) for more information."
|
|
13801
|
+
),
|
|
13802
|
+
confidence: zod3.number().nullish().describe(
|
|
13803
|
+
"The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence)"
|
|
12837
13804
|
),
|
|
12838
13805
|
content_safety: zod3.boolean().nullish().describe(
|
|
12839
|
-
"Whether [Content Moderation](https://www.assemblyai.com/docs/
|
|
13806
|
+
"Whether [Content Moderation](https://www.assemblyai.com/docs/content-moderation) is enabled, can be true or false"
|
|
12840
13807
|
),
|
|
12841
13808
|
content_safety_labels: zod3.object({
|
|
12842
13809
|
status: zod3.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -12846,12 +13813,8 @@ var getTranscriptResponse = zod3.object({
|
|
|
12846
13813
|
labels: zod3.array(
|
|
12847
13814
|
zod3.object({
|
|
12848
13815
|
label: zod3.string().describe("The label of the sensitive topic"),
|
|
12849
|
-
confidence: zod3.number().
|
|
12850
|
-
|
|
12851
|
-
).max(
|
|
12852
|
-
getTranscriptResponseContentSafetyLabelsResultsItemLabelsItemConfidenceMax
|
|
12853
|
-
).describe("The confidence score for the topic being discussed, from 0 to 1"),
|
|
12854
|
-
severity: zod3.number().min(getTranscriptResponseContentSafetyLabelsResultsItemLabelsItemSeverityMin).max(getTranscriptResponseContentSafetyLabelsResultsItemLabelsItemSeverityMax).describe("How severely the topic is discussed in the section, from 0 to 1")
|
|
13816
|
+
confidence: zod3.number().describe("The confidence score for the topic being discussed, from 0 to 1"),
|
|
13817
|
+
severity: zod3.number().describe("How severely the topic is discussed in the section, from 0 to 1")
|
|
12855
13818
|
})
|
|
12856
13819
|
).describe(
|
|
12857
13820
|
"An array of safety labels, one per sensitive topic that was detected in the section"
|
|
@@ -12864,128 +13827,39 @@ var getTranscriptResponse = zod3.object({
|
|
|
12864
13827
|
}).describe("Timestamp containing a start and end property in milliseconds")
|
|
12865
13828
|
})
|
|
12866
13829
|
).describe("An array of results for the Content Moderation model"),
|
|
12867
|
-
summary: zod3.record(
|
|
12868
|
-
zod3.string(),
|
|
12869
|
-
zod3.number().min(getTranscriptResponseContentSafetyLabelsSummaryMinOne).max(getTranscriptResponseContentSafetyLabelsSummaryMaxOne).describe(
|
|
12870
|
-
'A confidence score for the presence of the sensitive topic "topic" across the entire audio file'
|
|
12871
|
-
)
|
|
12872
|
-
).describe(
|
|
13830
|
+
summary: zod3.record(zod3.string(), zod3.number()).describe(
|
|
12873
13831
|
"A summary of the Content Moderation confidence results for the entire audio file"
|
|
12874
13832
|
),
|
|
12875
13833
|
severity_score_summary: zod3.record(
|
|
12876
13834
|
zod3.string(),
|
|
12877
13835
|
zod3.object({
|
|
12878
|
-
low: zod3.number()
|
|
12879
|
-
medium: zod3.number()
|
|
12880
|
-
high: zod3.number()
|
|
13836
|
+
low: zod3.number(),
|
|
13837
|
+
medium: zod3.number(),
|
|
13838
|
+
high: zod3.number()
|
|
12881
13839
|
})
|
|
12882
13840
|
).describe(
|
|
12883
13841
|
"A summary of the Content Moderation severity results for the entire audio file"
|
|
12884
13842
|
)
|
|
12885
13843
|
}).describe(
|
|
12886
|
-
"An array of results for the Content Moderation model, if it is enabled.\nSee [Content moderation](https://www.assemblyai.com/docs/
|
|
12887
|
-
).or(zod3.null()).optional().describe(
|
|
12888
|
-
"An array of results for the Content Moderation model, if it is enabled.\nSee [Content moderation](https://www.assemblyai.com/docs/models/content-moderation) for more information.\n"
|
|
12889
|
-
),
|
|
12890
|
-
iab_categories: zod3.boolean().nullish().describe(
|
|
12891
|
-
"Whether [Topic Detection](https://www.assemblyai.com/docs/models/topic-detection) is enabled, can be true or false"
|
|
12892
|
-
),
|
|
12893
|
-
iab_categories_result: zod3.object({
|
|
12894
|
-
status: zod3.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
12895
|
-
results: zod3.array(
|
|
12896
|
-
zod3.object({
|
|
12897
|
-
text: zod3.string().describe("The text in the transcript in which a detected topic occurs"),
|
|
12898
|
-
labels: zod3.array(
|
|
12899
|
-
zod3.object({
|
|
12900
|
-
relevance: zod3.number().min(
|
|
12901
|
-
getTranscriptResponseIabCategoriesResultResultsItemLabelsItemRelevanceMin
|
|
12902
|
-
).max(
|
|
12903
|
-
getTranscriptResponseIabCategoriesResultResultsItemLabelsItemRelevanceMax
|
|
12904
|
-
).describe("How relevant the detected topic is of a detected topic"),
|
|
12905
|
-
label: zod3.string().describe(
|
|
12906
|
-
"The IAB taxonomical label for the label of the detected topic, where > denotes supertopic/subtopic relationship"
|
|
12907
|
-
)
|
|
12908
|
-
})
|
|
12909
|
-
).optional().describe("An array of detected topics in the text"),
|
|
12910
|
-
timestamp: zod3.object({
|
|
12911
|
-
start: zod3.number().describe("The start time in milliseconds"),
|
|
12912
|
-
end: zod3.number().describe("The end time in milliseconds")
|
|
12913
|
-
}).optional().describe("Timestamp containing a start and end property in milliseconds")
|
|
12914
|
-
}).describe("The result of the topic detection model")
|
|
12915
|
-
).describe("An array of results for the Topic Detection model"),
|
|
12916
|
-
summary: zod3.record(
|
|
12917
|
-
zod3.string(),
|
|
12918
|
-
zod3.number().min(getTranscriptResponseIabCategoriesResultSummaryMinOne).max(getTranscriptResponseIabCategoriesResultSummaryMaxOne)
|
|
12919
|
-
).describe("The overall relevance of topic to the entire audio file")
|
|
12920
|
-
}).describe(
|
|
12921
|
-
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/models/topic-detection) for more information.\n"
|
|
13844
|
+
"An array of results for the Content Moderation model, if it is enabled.\nSee [Content moderation](https://www.assemblyai.com/docs/content-moderation) for more information.\n"
|
|
12922
13845
|
).or(zod3.null()).optional().describe(
|
|
12923
|
-
"
|
|
13846
|
+
"An array of results for the Content Moderation model, if it is enabled.\nSee [Content moderation](https://www.assemblyai.com/docs/content-moderation) for more information.\n"
|
|
12924
13847
|
),
|
|
12925
13848
|
custom_spelling: zod3.array(
|
|
12926
13849
|
zod3.object({
|
|
12927
|
-
from: zod3.array(zod3.string()
|
|
13850
|
+
from: zod3.array(zod3.string()).describe("Words or phrases to replace"),
|
|
12928
13851
|
to: zod3.string().describe("Word to replace with")
|
|
12929
13852
|
}).describe(
|
|
12930
13853
|
"Object containing words or phrases to replace, and the word or phrase to replace with"
|
|
12931
13854
|
)
|
|
12932
|
-
).nullish().describe("Customize how words are spelled and formatted using to and from values"),
|
|
12933
|
-
keyterms_prompt: zod3.array(zod3.string()).optional().describe(
|
|
12934
|
-
"Improve accuracy with up to 1000 domain-specific words or phrases (maximum 6 words per phrase).\n"
|
|
12935
|
-
),
|
|
12936
|
-
prompt: zod3.string().optional().describe("This parameter does not currently have any functionality attached to it."),
|
|
12937
|
-
auto_chapters: zod3.boolean().nullish().describe(
|
|
12938
|
-
"Whether [Auto Chapters](https://www.assemblyai.com/docs/models/auto-chapters) is enabled, can be true or false"
|
|
12939
|
-
),
|
|
12940
|
-
chapters: zod3.array(
|
|
12941
|
-
zod3.object({
|
|
12942
|
-
gist: zod3.string().describe(
|
|
12943
|
-
"An ultra-short summary (just a few words) of the content spoken in the chapter"
|
|
12944
|
-
),
|
|
12945
|
-
headline: zod3.string().describe("A single sentence summary of the content spoken during the chapter"),
|
|
12946
|
-
summary: zod3.string().describe("A one paragraph summary of the content spoken during the chapter"),
|
|
12947
|
-
start: zod3.number().describe("The starting time, in milliseconds, for the chapter"),
|
|
12948
|
-
end: zod3.number().describe("The starting time, in milliseconds, for the chapter")
|
|
12949
|
-
}).describe("Chapter of the audio file")
|
|
12950
|
-
).nullish().describe("An array of temporally sequential chapters for the audio file"),
|
|
12951
|
-
summarization: zod3.boolean().describe(
|
|
12952
|
-
"Whether [Summarization](https://www.assemblyai.com/docs/models/summarization) is enabled, either true or false"
|
|
12953
|
-
),
|
|
12954
|
-
summary_type: zod3.string().nullish().describe(
|
|
12955
|
-
"The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/models/summarization) is enabled"
|
|
12956
|
-
),
|
|
12957
|
-
summary_model: zod3.string().nullish().describe(
|
|
12958
|
-
"The Summarization model used to generate the summary,\nif [Summarization](https://www.assemblyai.com/docs/models/summarization) is enabled\n"
|
|
12959
|
-
),
|
|
12960
|
-
summary: zod3.string().nullish().describe(
|
|
12961
|
-
"The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/models/summarization) is enabled"
|
|
12962
|
-
),
|
|
12963
|
-
custom_topics: zod3.boolean().nullish().describe("Whether custom topics is enabled, either true or false"),
|
|
12964
|
-
topics: zod3.array(zod3.string()).optional().describe("The list of custom topics provided if custom topics is enabled"),
|
|
12965
|
-
sentiment_analysis: zod3.boolean().nullish().describe(
|
|
12966
|
-
"Whether [Sentiment Analysis](https://www.assemblyai.com/docs/models/sentiment-analysis) is enabled, can be true or false"
|
|
12967
|
-
),
|
|
12968
|
-
sentiment_analysis_results: zod3.array(
|
|
12969
|
-
zod3.object({
|
|
12970
|
-
text: zod3.string().describe("The transcript of the sentence"),
|
|
12971
|
-
start: zod3.number().describe("The starting time, in milliseconds, of the sentence"),
|
|
12972
|
-
end: zod3.number().describe("The ending time, in milliseconds, of the sentence"),
|
|
12973
|
-
sentiment: zod3.enum(["POSITIVE", "NEUTRAL", "NEGATIVE"]),
|
|
12974
|
-
confidence: zod3.number().min(getTranscriptResponseSentimentAnalysisResultsItemConfidenceMin).max(getTranscriptResponseSentimentAnalysisResultsItemConfidenceMax).describe(
|
|
12975
|
-
"The confidence score for the detected sentiment of the sentence, from 0 to 1"
|
|
12976
|
-
),
|
|
12977
|
-
channel: zod3.string().nullish().describe(
|
|
12978
|
-
"The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
12979
|
-
),
|
|
12980
|
-
speaker: zod3.string().nullable().describe(
|
|
12981
|
-
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/models/speaker-diarization) is enabled, else null"
|
|
12982
|
-
)
|
|
12983
|
-
}).describe("The result of the Sentiment Analysis model")
|
|
12984
13855
|
).nullish().describe(
|
|
12985
|
-
"
|
|
13856
|
+
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/custom-spelling) for more details."
|
|
12986
13857
|
),
|
|
12987
|
-
|
|
12988
|
-
|
|
13858
|
+
disfluencies: zod3.boolean().nullish().describe(
|
|
13859
|
+
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/filler-words), like "umm", in your media file; can be true or false'
|
|
13860
|
+
),
|
|
13861
|
+
domain: zod3.string().nullish().describe(
|
|
13862
|
+
'The domain-specific model applied to the transcript. When set to `"medical-v1"`, [Medical Mode](https://www.assemblyai.com/docs/pre-recorded-audio/medical-mode) was used to improve accuracy for medical terminology.\n'
|
|
12989
13863
|
),
|
|
12990
13864
|
entities: zod3.array(
|
|
12991
13865
|
zod3.object({
|
|
@@ -13044,61 +13918,49 @@ var getTranscriptResponse = zod3.object({
|
|
|
13044
13918
|
)
|
|
13045
13919
|
}).describe("A detected entity")
|
|
13046
13920
|
).nullish().describe(
|
|
13047
|
-
"An array of results for the Entity Detection model, if it is enabled.\nSee [Entity detection](https://www.assemblyai.com/docs/
|
|
13921
|
+
"An array of results for the Entity Detection model, if it is enabled.\nSee [Entity detection](https://www.assemblyai.com/docs/speech-understanding/entity-detection) for more information.\n"
|
|
13048
13922
|
),
|
|
13049
|
-
|
|
13050
|
-
"
|
|
13051
|
-
),
|
|
13052
|
-
throttled: zod3.boolean().nullish().describe(
|
|
13053
|
-
"True while a request is throttled and false when a request is no longer throttled"
|
|
13923
|
+
entity_detection: zod3.boolean().nullish().describe(
|
|
13924
|
+
"Whether [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/entity-detection) is enabled, can be true or false"
|
|
13054
13925
|
),
|
|
13055
13926
|
error: zod3.string().optional().describe("Error message of why the transcript failed"),
|
|
13056
|
-
|
|
13057
|
-
|
|
13058
|
-
|
|
13059
|
-
|
|
13060
|
-
|
|
13061
|
-
|
|
13062
|
-
|
|
13063
|
-
|
|
13064
|
-
|
|
13065
|
-
|
|
13066
|
-
|
|
13067
|
-
|
|
13068
|
-
|
|
13069
|
-
|
|
13070
|
-
|
|
13071
|
-
|
|
13072
|
-
|
|
13073
|
-
|
|
13074
|
-
|
|
13075
|
-
|
|
13076
|
-
|
|
13077
|
-
|
|
13078
|
-
|
|
13079
|
-
|
|
13080
|
-
|
|
13081
|
-
|
|
13082
|
-
|
|
13083
|
-
|
|
13084
|
-
|
|
13085
|
-
|
|
13086
|
-
|
|
13087
|
-
|
|
13088
|
-
|
|
13089
|
-
|
|
13090
|
-
var deleteTranscriptResponseIabCategoriesResultResultsItemLabelsItemRelevanceMax = 1;
|
|
13091
|
-
var deleteTranscriptResponseIabCategoriesResultSummaryMinOne = 0;
|
|
13092
|
-
var deleteTranscriptResponseIabCategoriesResultSummaryMaxOne = 1;
|
|
13093
|
-
var deleteTranscriptResponseSentimentAnalysisResultsItemConfidenceMin = 0;
|
|
13094
|
-
var deleteTranscriptResponseSentimentAnalysisResultsItemConfidenceMax = 1;
|
|
13095
|
-
var deleteTranscriptResponseSpeechThresholdMin = 0;
|
|
13096
|
-
var deleteTranscriptResponseSpeechThresholdMax = 1;
|
|
13097
|
-
var deleteTranscriptResponse = zod3.object({
|
|
13927
|
+
filter_profanity: zod3.boolean().nullish().describe(
|
|
13928
|
+
"Whether [Profanity Filtering](https://www.assemblyai.com/docs/profanity-filtering) is enabled, either true or false"
|
|
13929
|
+
),
|
|
13930
|
+
format_text: zod3.boolean().nullish().describe(
|
|
13931
|
+
"Whether [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio) is enabled, either true or false"
|
|
13932
|
+
),
|
|
13933
|
+
iab_categories: zod3.boolean().nullish().describe(
|
|
13934
|
+
"Whether [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/topic-detection) is enabled, can be true or false"
|
|
13935
|
+
),
|
|
13936
|
+
iab_categories_result: zod3.object({
|
|
13937
|
+
status: zod3.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
13938
|
+
results: zod3.array(
|
|
13939
|
+
zod3.object({
|
|
13940
|
+
text: zod3.string().describe("The text in the transcript in which a detected topic occurs"),
|
|
13941
|
+
labels: zod3.array(
|
|
13942
|
+
zod3.object({
|
|
13943
|
+
relevance: zod3.number().describe("How relevant the detected topic is of a detected topic"),
|
|
13944
|
+
label: zod3.string().describe(
|
|
13945
|
+
"The IAB taxonomical label for the label of the detected topic, where > denotes supertopic/subtopic relationship"
|
|
13946
|
+
)
|
|
13947
|
+
})
|
|
13948
|
+
).optional().describe("An array of detected topics in the text"),
|
|
13949
|
+
timestamp: zod3.object({
|
|
13950
|
+
start: zod3.number().describe("The start time in milliseconds"),
|
|
13951
|
+
end: zod3.number().describe("The end time in milliseconds")
|
|
13952
|
+
}).optional().describe("Timestamp containing a start and end property in milliseconds")
|
|
13953
|
+
}).describe("The result of the topic detection model")
|
|
13954
|
+
).describe("An array of results for the Topic Detection model"),
|
|
13955
|
+
summary: zod3.record(zod3.string(), zod3.number()).describe("The overall relevance of topic to the entire audio file")
|
|
13956
|
+
}).describe(
|
|
13957
|
+
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/topic-detection) for more information.\n"
|
|
13958
|
+
).or(zod3.null()).optional().describe(
|
|
13959
|
+
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/topic-detection) for more information.\n"
|
|
13960
|
+
),
|
|
13098
13961
|
id: zod3.string().uuid().describe("The unique identifier of your transcript"),
|
|
13099
|
-
|
|
13100
|
-
|
|
13101
|
-
"The status of your transcript. Possible values are queued, processing, completed, or error."
|
|
13962
|
+
keyterms_prompt: zod3.array(zod3.string()).optional().describe(
|
|
13963
|
+
"Improve accuracy with up to 200 (for Universal-2) or 1000 (for Universal-3 Pro) domain-specific words or phrases (maximum 6 words per phrase). See [Keyterms Prompting](https://www.assemblyai.com/docs/pre-recorded-audio/keyterms-prompting) for more details.\n"
|
|
13102
13964
|
),
|
|
13103
13965
|
language_code: zod3.enum([
|
|
13104
13966
|
"en",
|
|
@@ -13203,138 +14065,175 @@ var deleteTranscriptResponse = zod3.object({
|
|
|
13203
14065
|
"cy",
|
|
13204
14066
|
"yi",
|
|
13205
14067
|
"yo"
|
|
13206
|
-
]).describe(
|
|
13207
|
-
"The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/
|
|
13208
|
-
).or(zod3.string()).optional().describe(
|
|
13209
|
-
"The language of your audio file.\nPossible values are found in [Supported Languages](https://www.assemblyai.com/docs/concepts/supported-languages).\nThe default value is 'en_us'.\n"
|
|
13210
|
-
),
|
|
13211
|
-
language_detection: zod3.boolean().nullish().describe(
|
|
13212
|
-
"Whether [Automatic language detection](https://www.assemblyai.com/docs/models/speech-recognition#automatic-language-detection) is enabled, either true or false"
|
|
13213
|
-
),
|
|
13214
|
-
language_confidence_threshold: zod3.number().min(deleteTranscriptResponseLanguageConfidenceThresholdMin).max(deleteTranscriptResponseLanguageConfidenceThresholdMax).nullable().describe(
|
|
13215
|
-
"The confidence threshold for the automatically detected language.\nAn error will be returned if the language confidence is below this threshold.\n"
|
|
13216
|
-
),
|
|
13217
|
-
language_confidence: zod3.number().min(deleteTranscriptResponseLanguageConfidenceMin).max(deleteTranscriptResponseLanguageConfidenceMax).nullable().describe(
|
|
13218
|
-
"The confidence score for the detected language, between 0.0 (low confidence) and 1.0 (high confidence)"
|
|
13219
|
-
),
|
|
13220
|
-
speech_model: zod3.enum(["best", "slam-1", "universal"]).describe("The speech model to use for the transcription.").or(zod3.null()).describe(
|
|
13221
|
-
"The speech model used for the transcription. When `null`, the default model is used."
|
|
13222
|
-
),
|
|
13223
|
-
text: zod3.string().nullish().describe("The textual transcript of your media file"),
|
|
13224
|
-
words: zod3.array(
|
|
13225
|
-
zod3.object({
|
|
13226
|
-
confidence: zod3.number().min(deleteTranscriptResponseWordsItemConfidenceMin).max(deleteTranscriptResponseWordsItemConfidenceMax).describe("The confidence score for the transcript of this word"),
|
|
13227
|
-
start: zod3.number().describe("The starting time, in milliseconds, for the word"),
|
|
13228
|
-
end: zod3.number().describe("The ending time, in milliseconds, for the word"),
|
|
13229
|
-
text: zod3.string().describe("The text of the word"),
|
|
13230
|
-
channel: zod3.string().nullish().describe(
|
|
13231
|
-
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
13232
|
-
),
|
|
13233
|
-
speaker: zod3.string().nullable().describe(
|
|
13234
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/models/speaker-diarization) is enabled, else null"
|
|
13235
|
-
)
|
|
13236
|
-
})
|
|
13237
|
-
).nullish().describe(
|
|
13238
|
-
"An array of temporally-sequential word objects, one for each word in the transcript.\nSee [Speech recognition](https://www.assemblyai.com/docs/models/speech-recognition) for more information.\n"
|
|
14068
|
+
]).optional().describe(
|
|
14069
|
+
"The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/pre-recorded-audio/supported-languages).\nThe default value is 'en_us'.\n"
|
|
13239
14070
|
),
|
|
13240
|
-
|
|
13241
|
-
zod3.
|
|
13242
|
-
|
|
13243
|
-
|
|
13244
|
-
|
|
13245
|
-
|
|
13246
|
-
|
|
13247
|
-
|
|
13248
|
-
|
|
13249
|
-
|
|
13250
|
-
|
|
13251
|
-
|
|
13252
|
-
|
|
13253
|
-
|
|
13254
|
-
|
|
13255
|
-
|
|
13256
|
-
|
|
13257
|
-
|
|
13258
|
-
|
|
13259
|
-
|
|
13260
|
-
|
|
13261
|
-
|
|
13262
|
-
|
|
13263
|
-
|
|
13264
|
-
|
|
13265
|
-
|
|
13266
|
-
|
|
14071
|
+
language_codes: zod3.array(
|
|
14072
|
+
zod3.enum([
|
|
14073
|
+
"en",
|
|
14074
|
+
"en_au",
|
|
14075
|
+
"en_uk",
|
|
14076
|
+
"en_us",
|
|
14077
|
+
"es",
|
|
14078
|
+
"fr",
|
|
14079
|
+
"de",
|
|
14080
|
+
"it",
|
|
14081
|
+
"pt",
|
|
14082
|
+
"nl",
|
|
14083
|
+
"af",
|
|
14084
|
+
"sq",
|
|
14085
|
+
"am",
|
|
14086
|
+
"ar",
|
|
14087
|
+
"hy",
|
|
14088
|
+
"as",
|
|
14089
|
+
"az",
|
|
14090
|
+
"ba",
|
|
14091
|
+
"eu",
|
|
14092
|
+
"be",
|
|
14093
|
+
"bn",
|
|
14094
|
+
"bs",
|
|
14095
|
+
"br",
|
|
14096
|
+
"bg",
|
|
14097
|
+
"my",
|
|
14098
|
+
"ca",
|
|
14099
|
+
"zh",
|
|
14100
|
+
"hr",
|
|
14101
|
+
"cs",
|
|
14102
|
+
"da",
|
|
14103
|
+
"et",
|
|
14104
|
+
"fo",
|
|
14105
|
+
"fi",
|
|
14106
|
+
"gl",
|
|
14107
|
+
"ka",
|
|
14108
|
+
"el",
|
|
14109
|
+
"gu",
|
|
14110
|
+
"ht",
|
|
14111
|
+
"ha",
|
|
14112
|
+
"haw",
|
|
14113
|
+
"he",
|
|
14114
|
+
"hi",
|
|
14115
|
+
"hu",
|
|
14116
|
+
"is",
|
|
14117
|
+
"id",
|
|
14118
|
+
"ja",
|
|
14119
|
+
"jw",
|
|
14120
|
+
"kn",
|
|
14121
|
+
"kk",
|
|
14122
|
+
"km",
|
|
14123
|
+
"ko",
|
|
14124
|
+
"lo",
|
|
14125
|
+
"la",
|
|
14126
|
+
"lv",
|
|
14127
|
+
"ln",
|
|
14128
|
+
"lt",
|
|
14129
|
+
"lb",
|
|
14130
|
+
"mk",
|
|
14131
|
+
"mg",
|
|
14132
|
+
"ms",
|
|
14133
|
+
"ml",
|
|
14134
|
+
"mt",
|
|
14135
|
+
"mi",
|
|
14136
|
+
"mr",
|
|
14137
|
+
"mn",
|
|
14138
|
+
"ne",
|
|
14139
|
+
"no",
|
|
14140
|
+
"nn",
|
|
14141
|
+
"oc",
|
|
14142
|
+
"pa",
|
|
14143
|
+
"ps",
|
|
14144
|
+
"fa",
|
|
14145
|
+
"pl",
|
|
14146
|
+
"ro",
|
|
14147
|
+
"ru",
|
|
14148
|
+
"sa",
|
|
14149
|
+
"sr",
|
|
14150
|
+
"sn",
|
|
14151
|
+
"sd",
|
|
14152
|
+
"si",
|
|
14153
|
+
"sk",
|
|
14154
|
+
"sl",
|
|
14155
|
+
"so",
|
|
14156
|
+
"su",
|
|
14157
|
+
"sw",
|
|
14158
|
+
"sv",
|
|
14159
|
+
"tl",
|
|
14160
|
+
"tg",
|
|
14161
|
+
"ta",
|
|
14162
|
+
"tt",
|
|
14163
|
+
"te",
|
|
14164
|
+
"th",
|
|
14165
|
+
"bo",
|
|
14166
|
+
"tr",
|
|
14167
|
+
"tk",
|
|
14168
|
+
"uk",
|
|
14169
|
+
"ur",
|
|
14170
|
+
"uz",
|
|
14171
|
+
"vi",
|
|
14172
|
+
"cy",
|
|
14173
|
+
"yi",
|
|
14174
|
+
"yo"
|
|
14175
|
+
]).describe(
|
|
14176
|
+
"The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/pre-recorded-audio/supported-languages).\nThe default value is 'en_us'.\n"
|
|
14177
|
+
)
|
|
13267
14178
|
).nullish().describe(
|
|
13268
|
-
"
|
|
13269
|
-
),
|
|
13270
|
-
confidence: zod3.number().min(deleteTranscriptResponseConfidenceMin).max(deleteTranscriptResponseConfidenceMax).nullish().describe(
|
|
13271
|
-
"The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence)"
|
|
13272
|
-
),
|
|
13273
|
-
audio_duration: zod3.number().nullish().describe("The duration of this transcript object's media file, in seconds"),
|
|
13274
|
-
punctuate: zod3.boolean().nullish().describe("Whether Automatic Punctuation is enabled, either true or false"),
|
|
13275
|
-
format_text: zod3.boolean().nullish().describe("Whether Text Formatting is enabled, either true or false"),
|
|
13276
|
-
disfluencies: zod3.boolean().nullish().describe('Transcribe Filler Words, like "umm", in your media file; can be true or false'),
|
|
13277
|
-
multichannel: zod3.boolean().nullish().describe(
|
|
13278
|
-
"Whether [Multichannel transcription](https://www.assemblyai.com/docs/models/speech-recognition#multichannel-transcription) was enabled in the transcription request, either true or false"
|
|
13279
|
-
),
|
|
13280
|
-
audio_channels: zod3.number().optional().describe(
|
|
13281
|
-
"The number of audio channels in the audio file. This is only present when multichannel is enabled."
|
|
14179
|
+
"The language codes of your audio file. Used for [Code switching](/docs/speech-to-text/pre-recorded-audio/code-switching)\nOne of the values specified must be `en`.\n"
|
|
13282
14180
|
),
|
|
13283
|
-
|
|
13284
|
-
"The
|
|
14181
|
+
language_confidence: zod3.number().nullable().describe(
|
|
14182
|
+
"The confidence score for the detected language, between 0.0 (low confidence) and 1.0 (high confidence). See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details."
|
|
13285
14183
|
),
|
|
13286
|
-
|
|
13287
|
-
"The
|
|
14184
|
+
language_confidence_threshold: zod3.number().nullable().describe(
|
|
14185
|
+
"The confidence threshold for the automatically detected language.\nAn error will be returned if the language confidence is below this threshold.\nSee [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.\n"
|
|
13288
14186
|
),
|
|
13289
|
-
|
|
13290
|
-
|
|
13291
|
-
"The header name to be sent with the transcript completed or failed webhook requests"
|
|
14187
|
+
language_detection: zod3.boolean().nullish().describe(
|
|
14188
|
+
"Whether [Automatic language detection](/docs/pre-recorded-audio/automatic-language-detection) is enabled, either true or false"
|
|
13292
14189
|
),
|
|
13293
|
-
|
|
13294
|
-
|
|
13295
|
-
|
|
13296
|
-
|
|
13297
|
-
|
|
13298
|
-
|
|
13299
|
-
|
|
13300
|
-
|
|
13301
|
-
|
|
13302
|
-
|
|
13303
|
-
|
|
13304
|
-
|
|
13305
|
-
|
|
13306
|
-
|
|
13307
|
-
|
|
13308
|
-
|
|
13309
|
-
|
|
13310
|
-
})
|
|
13311
|
-
).describe("A temporally-sequential array of Key Phrases")
|
|
13312
|
-
}).describe(
|
|
13313
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key phrases](https://www.assemblyai.com/docs/models/key-phrases) for more information.\n"
|
|
13314
|
-
).or(zod3.null()).optional().describe(
|
|
13315
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key Phrases](https://www.assemblyai.com/docs/models/key-phrases) for more information.\n"
|
|
14190
|
+
language_detection_options: zod3.object({
|
|
14191
|
+
expected_languages: zod3.array(zod3.string()).optional().describe(
|
|
14192
|
+
'List of languages expected in the audio file. Defaults to `["all"]` when unspecified. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.'
|
|
14193
|
+
),
|
|
14194
|
+
fallback_language: zod3.string().default(deleteTranscriptResponseLanguageDetectionOptionsFallbackLanguageDefault).describe(
|
|
14195
|
+
'If the detected language of the audio file is not in the list of expected languages, the `fallback_language` is used. Specify `["auto"]` to let our model choose the fallback language from `expected_languages` with the highest confidence score. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.\n'
|
|
14196
|
+
),
|
|
14197
|
+
code_switching: zod3.boolean().optional().describe(
|
|
14198
|
+
"Whether [code switching](/docs/speech-to-text/pre-recorded-audio/code-switching) should be detected.\n"
|
|
14199
|
+
),
|
|
14200
|
+
code_switching_confidence_threshold: zod3.number().default(
|
|
14201
|
+
deleteTranscriptResponseLanguageDetectionOptionsCodeSwitchingConfidenceThresholdDefault
|
|
14202
|
+
).describe(
|
|
14203
|
+
"The confidence threshold for [code switching](/docs/speech-to-text/pre-recorded-audio/code-switching) detection. If the code switching confidence is below this threshold, the transcript will be processed in the language with the highest `language_detection_confidence` score.\n"
|
|
14204
|
+
)
|
|
14205
|
+
}).optional().describe(
|
|
14206
|
+
"Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection)."
|
|
13316
14207
|
),
|
|
13317
|
-
|
|
13318
|
-
"
|
|
14208
|
+
multichannel: zod3.boolean().nullish().describe(
|
|
14209
|
+
"Whether [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/multichannel) was enabled in the transcription request, either true or false"
|
|
13319
14210
|
),
|
|
13320
|
-
|
|
13321
|
-
"
|
|
14211
|
+
prompt: zod3.string().optional().describe(
|
|
14212
|
+
"Provide natural language prompting of up to 1,500 words of contextual information to the model. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for best practices.\n\nNote: This parameter is only supported for the Universal-3 Pro model.\n"
|
|
13322
14213
|
),
|
|
13323
|
-
|
|
13324
|
-
|
|
13325
|
-
filter_profanity: zod3.boolean().nullish().describe(
|
|
13326
|
-
"Whether [Profanity Filtering](https://www.assemblyai.com/docs/models/speech-recognition#profanity-filtering) is enabled, either true or false"
|
|
14214
|
+
punctuate: zod3.boolean().nullish().describe(
|
|
14215
|
+
"Whether [Automatic Punctuation](https://www.assemblyai.com/docs/pre-recorded-audio) is enabled, either true or false"
|
|
13327
14216
|
),
|
|
13328
14217
|
redact_pii: zod3.boolean().describe(
|
|
13329
|
-
"Whether [PII Redaction](https://www.assemblyai.com/docs/
|
|
14218
|
+
"Whether [PII Redaction](https://www.assemblyai.com/docs/pii-redaction) is enabled, either true or false"
|
|
13330
14219
|
),
|
|
13331
14220
|
redact_pii_audio: zod3.boolean().nullish().describe(
|
|
13332
|
-
"Whether a redacted version of the audio file was generated,\neither true or false. See [PII redaction](https://www.assemblyai.com/docs/
|
|
14221
|
+
"Whether a redacted version of the audio file was generated,\neither true or false. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more information.\n"
|
|
14222
|
+
),
|
|
14223
|
+
redact_pii_audio_options: zod3.object({
|
|
14224
|
+
return_redacted_no_speech_audio: zod3.boolean().optional().describe(
|
|
14225
|
+
"By default, audio redaction provides redacted audio URLs only when speech is detected. However, if your use-case specifically requires redacted audio files even for silent audio files without any dialogue, you can opt to receive these URLs by setting this parameter to `true`."
|
|
14226
|
+
),
|
|
14227
|
+
override_audio_redaction_method: zod3.enum(["silence"]).optional().describe(
|
|
14228
|
+
"Specify the method used to redact audio. By default, redacted audio uses a beep sound. Set to `silence` to replace PII with silence instead of a beep."
|
|
14229
|
+
)
|
|
14230
|
+
}).optional().describe(
|
|
14231
|
+
"The options for PII-redacted audio, if redact_pii_audio is enabled.\nSee [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more information.\n"
|
|
13333
14232
|
),
|
|
13334
14233
|
redact_pii_audio_quality: zod3.enum(["mp3", "wav"]).describe(
|
|
13335
|
-
"Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See [PII redaction](https://www.assemblyai.com/docs/
|
|
14234
|
+
"Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more details."
|
|
13336
14235
|
).or(zod3.null()).optional().describe(
|
|
13337
|
-
"The audio quality of the PII-redacted audio file, if redact_pii_audio is enabled.\nSee [PII redaction](https://www.assemblyai.com/docs/
|
|
14236
|
+
"The audio quality of the PII-redacted audio file, if redact_pii_audio is enabled.\nSee [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more information.\n"
|
|
13338
14237
|
),
|
|
13339
14238
|
redact_pii_policies: zod3.array(
|
|
13340
14239
|
zod3.enum([
|
|
@@ -13384,271 +14283,256 @@ var deleteTranscriptResponse = zod3.object({
|
|
|
13384
14283
|
"zodiac_sign"
|
|
13385
14284
|
]).describe("The type of PII to redact")
|
|
13386
14285
|
).nullish().describe(
|
|
13387
|
-
"The list of PII Redaction policies that were enabled, if PII Redaction is enabled.\nSee [PII redaction](https://www.assemblyai.com/docs/
|
|
14286
|
+
"The list of PII Redaction policies that were enabled, if PII Redaction is enabled.\nSee [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more information.\n"
|
|
13388
14287
|
),
|
|
13389
14288
|
redact_pii_sub: zod3.enum(["entity_name", "hash"]).optional().describe(
|
|
13390
|
-
|
|
14289
|
+
"The replacement logic for detected PII, can be `entity_name` or `hash`. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more details."
|
|
14290
|
+
),
|
|
14291
|
+
sentiment_analysis: zod3.boolean().nullish().describe(
|
|
14292
|
+
"Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-analysis) is enabled, can be true or false"
|
|
14293
|
+
),
|
|
14294
|
+
sentiment_analysis_results: zod3.array(
|
|
14295
|
+
zod3.object({
|
|
14296
|
+
text: zod3.string().describe("The transcript of the sentence"),
|
|
14297
|
+
start: zod3.number().describe("The starting time, in milliseconds, of the sentence"),
|
|
14298
|
+
end: zod3.number().describe("The ending time, in milliseconds, of the sentence"),
|
|
14299
|
+
sentiment: zod3.enum(["POSITIVE", "NEUTRAL", "NEGATIVE"]),
|
|
14300
|
+
confidence: zod3.number().describe(
|
|
14301
|
+
"The confidence score for the detected sentiment of the sentence, from 0 to 1"
|
|
14302
|
+
),
|
|
14303
|
+
channel: zod3.string().nullish().describe(
|
|
14304
|
+
"The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
14305
|
+
),
|
|
14306
|
+
speaker: zod3.string().nullable().describe(
|
|
14307
|
+
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization) is enabled, else null"
|
|
14308
|
+
)
|
|
14309
|
+
}).describe("The result of the Sentiment Analysis model")
|
|
14310
|
+
).nullish().describe(
|
|
14311
|
+
"An array of results for the Sentiment Analysis model, if it is enabled.\nSee [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-analysis) for more information.\n"
|
|
13391
14312
|
),
|
|
13392
14313
|
speaker_labels: zod3.boolean().nullish().describe(
|
|
13393
|
-
"Whether [Speaker diarization](https://www.assemblyai.com/docs/
|
|
14314
|
+
"Whether [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization) is enabled, can be true or false"
|
|
13394
14315
|
),
|
|
13395
14316
|
speakers_expected: zod3.number().nullish().describe(
|
|
13396
|
-
"Tell the speaker label model how many speakers it should attempt to identify. See [
|
|
14317
|
+
"Tell the speaker label model how many speakers it should attempt to identify. See [Set number of speakers expected](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization#set-number-of-speakers-expected) for more details."
|
|
13397
14318
|
),
|
|
13398
|
-
|
|
13399
|
-
"
|
|
14319
|
+
speech_model_used: zod3.string().optional().describe(
|
|
14320
|
+
"The speech model to use for the transcription. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models."
|
|
13400
14321
|
),
|
|
13401
|
-
|
|
13402
|
-
|
|
13403
|
-
|
|
13404
|
-
|
|
13405
|
-
|
|
13406
|
-
|
|
13407
|
-
|
|
13408
|
-
|
|
13409
|
-
|
|
13410
|
-
|
|
13411
|
-
|
|
13412
|
-
|
|
13413
|
-
|
|
13414
|
-
|
|
13415
|
-
|
|
13416
|
-
).max(
|
|
13417
|
-
deleteTranscriptResponseContentSafetyLabelsResultsItemLabelsItemSeverityMax
|
|
13418
|
-
).describe("How severely the topic is discussed in the section, from 0 to 1")
|
|
13419
|
-
})
|
|
13420
|
-
).describe(
|
|
13421
|
-
"An array of safety labels, one per sensitive topic that was detected in the section"
|
|
14322
|
+
speech_models: zod3.array(
|
|
14323
|
+
zod3.string().describe(
|
|
14324
|
+
"The speech model to use for the transcription. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models."
|
|
14325
|
+
)
|
|
14326
|
+
).nullish().describe(
|
|
14327
|
+
"List multiple speech models in priority order, allowing our system to automatically route your audio to the best available option. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models and routing behavior.\n"
|
|
14328
|
+
),
|
|
14329
|
+
speech_threshold: zod3.number().nullish().describe(
|
|
14330
|
+
"Defaults to null. Reject audio files that contain less than this fraction of speech.\nValid values are in the range [0, 1] inclusive. See [Speech Threshold](https://www.assemblyai.com/docs/speech-threshold) for more details.\n"
|
|
14331
|
+
),
|
|
14332
|
+
speech_understanding: zod3.object({
|
|
14333
|
+
request: zod3.object({
|
|
14334
|
+
translation: zod3.object({
|
|
14335
|
+
target_languages: zod3.array(zod3.string()).describe(
|
|
14336
|
+
'List of target language codes (e.g., `["es", "de"]`). See [Translation](https://www.assemblyai.com/docs/speech-understanding/translation) for supported languages.'
|
|
13422
14337
|
),
|
|
13423
|
-
|
|
13424
|
-
|
|
13425
|
-
|
|
13426
|
-
|
|
13427
|
-
|
|
13428
|
-
|
|
14338
|
+
formal: zod3.boolean().default(deleteTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault).describe(
|
|
14339
|
+
"Use formal language style. See [Translation](https://www.assemblyai.com/docs/speech-understanding/translation) for more details."
|
|
14340
|
+
),
|
|
14341
|
+
match_original_utterance: zod3.boolean().optional().describe(
|
|
14342
|
+
"When enabled with Speaker Labels, returns translated text in the utterances array. Each utterance will include a `translated_texts` key containing translations for each target language."
|
|
14343
|
+
)
|
|
13429
14344
|
})
|
|
13430
|
-
).describe(
|
|
13431
|
-
|
|
13432
|
-
|
|
13433
|
-
zod3.
|
|
13434
|
-
|
|
14345
|
+
}).describe(
|
|
14346
|
+
"Request body for [Translation](https://www.assemblyai.com/docs/speech-understanding/translation)."
|
|
14347
|
+
).or(
|
|
14348
|
+
zod3.object({
|
|
14349
|
+
speaker_identification: zod3.object({
|
|
14350
|
+
speaker_type: zod3.enum(["role", "name"]).describe(
|
|
14351
|
+
"Type of speaker identification. See [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification) for details on each type."
|
|
14352
|
+
),
|
|
14353
|
+
known_values: zod3.array(zod3.string()).optional().describe(
|
|
14354
|
+
'Required if speaker_type is "role". Each value must be 35 characters or less.'
|
|
14355
|
+
),
|
|
14356
|
+
speakers: zod3.array(
|
|
14357
|
+
zod3.object({
|
|
14358
|
+
role: zod3.string().optional().describe(
|
|
14359
|
+
'The role of the speaker. Required when `speaker_type` is "role".'
|
|
14360
|
+
),
|
|
14361
|
+
name: zod3.string().optional().describe(
|
|
14362
|
+
'The name of the speaker. Required when `speaker_type` is "name".'
|
|
14363
|
+
),
|
|
14364
|
+
description: zod3.string().optional().describe(
|
|
14365
|
+
"A description of the speaker to help the model identify them based on conversational context."
|
|
14366
|
+
)
|
|
14367
|
+
})
|
|
14368
|
+
).optional().describe(
|
|
14369
|
+
"An array of speaker objects with metadata to improve identification accuracy. Each object should include a `role` or `name` (depending on `speaker_type`) and an optional `description` to help the model identify the speaker. You can also include any additional custom properties (e.g., `company`, `title`) to provide more context. Use this as an alternative to `known_values` when you want to provide additional context about each speaker."
|
|
14370
|
+
)
|
|
14371
|
+
})
|
|
14372
|
+
}).describe(
|
|
14373
|
+
"Request body for [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification)."
|
|
13435
14374
|
)
|
|
13436
|
-
).
|
|
13437
|
-
|
|
13438
|
-
|
|
13439
|
-
|
|
13440
|
-
|
|
14375
|
+
).or(
|
|
14376
|
+
zod3.object({
|
|
14377
|
+
custom_formatting: zod3.object({
|
|
14378
|
+
date: zod3.string().optional().describe(
|
|
14379
|
+
'Date format pattern (e.g., `"mm/dd/yyyy"`). See [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting) for more details.'
|
|
14380
|
+
),
|
|
14381
|
+
phone_number: zod3.string().optional().describe(
|
|
14382
|
+
'Phone number format pattern (e.g., `"(xxx)xxx-xxxx"`). See [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting) for more details.'
|
|
14383
|
+
),
|
|
14384
|
+
email: zod3.string().optional().describe(
|
|
14385
|
+
'Email format pattern (e.g., `"username@domain.com"`). See [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting) for more details.'
|
|
14386
|
+
)
|
|
14387
|
+
})
|
|
14388
|
+
}).describe(
|
|
14389
|
+
"Request body for [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting)."
|
|
14390
|
+
)
|
|
14391
|
+
).optional(),
|
|
14392
|
+
response: zod3.object({
|
|
14393
|
+
translation: zod3.object({
|
|
14394
|
+
status: zod3.string().optional()
|
|
14395
|
+
}).optional()
|
|
14396
|
+
}).or(
|
|
13441
14397
|
zod3.object({
|
|
13442
|
-
|
|
13443
|
-
|
|
13444
|
-
|
|
14398
|
+
speaker_identification: zod3.object({
|
|
14399
|
+
mapping: zod3.record(zod3.string(), zod3.string()).optional().describe(
|
|
14400
|
+
'A mapping of the original generic speaker labels (e.g., "A", "B") to the identified speaker names or roles.'
|
|
14401
|
+
),
|
|
14402
|
+
status: zod3.string().optional()
|
|
14403
|
+
}).optional()
|
|
13445
14404
|
})
|
|
13446
|
-
).
|
|
13447
|
-
"A summary of the Content Moderation severity results for the entire audio file"
|
|
13448
|
-
)
|
|
13449
|
-
}).describe(
|
|
13450
|
-
"An array of results for the Content Moderation model, if it is enabled.\nSee [Content moderation](https://www.assemblyai.com/docs/models/content-moderation) for more information.\n"
|
|
13451
|
-
).or(zod3.null()).optional().describe(
|
|
13452
|
-
"An array of results for the Content Moderation model, if it is enabled.\nSee [Content moderation](https://www.assemblyai.com/docs/models/content-moderation) for more information.\n"
|
|
13453
|
-
),
|
|
13454
|
-
iab_categories: zod3.boolean().nullish().describe(
|
|
13455
|
-
"Whether [Topic Detection](https://www.assemblyai.com/docs/models/topic-detection) is enabled, can be true or false"
|
|
13456
|
-
),
|
|
13457
|
-
iab_categories_result: zod3.object({
|
|
13458
|
-
status: zod3.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
13459
|
-
results: zod3.array(
|
|
14405
|
+
).or(
|
|
13460
14406
|
zod3.object({
|
|
13461
|
-
|
|
13462
|
-
|
|
13463
|
-
zod3.
|
|
13464
|
-
|
|
13465
|
-
|
|
13466
|
-
|
|
13467
|
-
|
|
13468
|
-
|
|
13469
|
-
label: zod3.string().describe(
|
|
13470
|
-
"The IAB taxonomical label for the label of the detected topic, where > denotes supertopic/subtopic relationship"
|
|
13471
|
-
)
|
|
13472
|
-
})
|
|
13473
|
-
).optional().describe("An array of detected topics in the text"),
|
|
13474
|
-
timestamp: zod3.object({
|
|
13475
|
-
start: zod3.number().describe("The start time in milliseconds"),
|
|
13476
|
-
end: zod3.number().describe("The end time in milliseconds")
|
|
13477
|
-
}).optional().describe("Timestamp containing a start and end property in milliseconds")
|
|
13478
|
-
}).describe("The result of the topic detection model")
|
|
13479
|
-
).describe("An array of results for the Topic Detection model"),
|
|
13480
|
-
summary: zod3.record(
|
|
13481
|
-
zod3.string(),
|
|
13482
|
-
zod3.number().min(deleteTranscriptResponseIabCategoriesResultSummaryMinOne).max(deleteTranscriptResponseIabCategoriesResultSummaryMaxOne)
|
|
13483
|
-
).describe("The overall relevance of topic to the entire audio file")
|
|
13484
|
-
}).describe(
|
|
13485
|
-
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/models/topic-detection) for more information.\n"
|
|
13486
|
-
).or(zod3.null()).optional().describe(
|
|
13487
|
-
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/models/topic-detection) for more information.\n"
|
|
13488
|
-
),
|
|
13489
|
-
custom_spelling: zod3.array(
|
|
13490
|
-
zod3.object({
|
|
13491
|
-
from: zod3.array(zod3.string().describe("Word or phrase to replace")).describe("Words or phrases to replace"),
|
|
13492
|
-
to: zod3.string().describe("Word to replace with")
|
|
13493
|
-
}).describe(
|
|
13494
|
-
"Object containing words or phrases to replace, and the word or phrase to replace with"
|
|
13495
|
-
)
|
|
13496
|
-
).nullish().describe("Customize how words are spelled and formatted using to and from values"),
|
|
13497
|
-
keyterms_prompt: zod3.array(zod3.string()).optional().describe(
|
|
13498
|
-
"Improve accuracy with up to 1000 domain-specific words or phrases (maximum 6 words per phrase).\n"
|
|
14407
|
+
custom_formatting: zod3.object({
|
|
14408
|
+
mapping: zod3.record(zod3.string(), zod3.string()).optional(),
|
|
14409
|
+
formatted_text: zod3.string().optional()
|
|
14410
|
+
}).optional()
|
|
14411
|
+
})
|
|
14412
|
+
).optional()
|
|
14413
|
+
}).optional().describe(
|
|
14414
|
+
"Speech understanding tasks like [Translation](https://www.assemblyai.com/docs/speech-understanding/translation), [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification), and [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting). See the task-specific docs for available options and configuration.\n"
|
|
13499
14415
|
),
|
|
13500
|
-
|
|
13501
|
-
|
|
13502
|
-
"Whether [Auto Chapters](https://www.assemblyai.com/docs/models/auto-chapters) is enabled, can be true or false"
|
|
14416
|
+
status: zod3.enum(["queued", "processing", "completed", "error"]).describe(
|
|
14417
|
+
"The status of your transcript. Possible values are queued, processing, completed, or error."
|
|
13503
14418
|
),
|
|
13504
|
-
chapters: zod3.array(
|
|
13505
|
-
zod3.object({
|
|
13506
|
-
gist: zod3.string().describe(
|
|
13507
|
-
"An ultra-short summary (just a few words) of the content spoken in the chapter"
|
|
13508
|
-
),
|
|
13509
|
-
headline: zod3.string().describe("A single sentence summary of the content spoken during the chapter"),
|
|
13510
|
-
summary: zod3.string().describe("A one paragraph summary of the content spoken during the chapter"),
|
|
13511
|
-
start: zod3.number().describe("The starting time, in milliseconds, for the chapter"),
|
|
13512
|
-
end: zod3.number().describe("The starting time, in milliseconds, for the chapter")
|
|
13513
|
-
}).describe("Chapter of the audio file")
|
|
13514
|
-
).nullish().describe("An array of temporally sequential chapters for the audio file"),
|
|
13515
14419
|
summarization: zod3.boolean().describe(
|
|
13516
|
-
"Whether [Summarization](https://www.assemblyai.com/docs/
|
|
14420
|
+
"Whether [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization) is enabled, either true or false. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
13517
14421
|
),
|
|
13518
|
-
|
|
13519
|
-
"The
|
|
14422
|
+
summary: zod3.string().nullish().describe(
|
|
14423
|
+
"The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization) is enabled. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details."
|
|
13520
14424
|
),
|
|
13521
14425
|
summary_model: zod3.string().nullish().describe(
|
|
13522
|
-
"The Summarization model used to generate the summary,\nif [Summarization](https://www.assemblyai.com/docs/
|
|
14426
|
+
"The Summarization model used to generate the summary,\nif [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization#summary-models) is enabled. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details.\n"
|
|
13523
14427
|
),
|
|
13524
|
-
|
|
13525
|
-
"The
|
|
14428
|
+
summary_type: zod3.string().nullish().describe(
|
|
14429
|
+
"The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization#summary-types) is enabled. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details."
|
|
13526
14430
|
),
|
|
13527
|
-
|
|
13528
|
-
|
|
13529
|
-
|
|
13530
|
-
"Whether [
|
|
14431
|
+
remove_audio_tags: zod3.enum(["all"]).describe(
|
|
14432
|
+
"Whether [audio event tags](https://www.assemblyai.com/docs/pre-recorded-audio/universal-3-pro#audio-event-tags) were removed from the transcript text.\n\nNote: This parameter is only supported for the Universal-3 Pro model.\n"
|
|
14433
|
+
).or(zod3.null()).optional().describe(
|
|
14434
|
+
"Whether [audio event tags](https://www.assemblyai.com/docs/pre-recorded-audio/universal-3-pro#audio-event-tags) were removed from the transcript text.\n\nNote: This parameter is only supported for the Universal-3 Pro model.\n"
|
|
13531
14435
|
),
|
|
13532
|
-
|
|
14436
|
+
temperature: zod3.number().nullish().describe(
|
|
14437
|
+
"The temperature that was used for the model's response. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for more details.\n\nNote: This parameter can only be used with the Universal-3 Pro model.\n"
|
|
14438
|
+
),
|
|
14439
|
+
text: zod3.string().nullish().describe("The textual transcript of your media file"),
|
|
14440
|
+
throttled: zod3.boolean().nullish().describe(
|
|
14441
|
+
"True while a request is throttled and false when a request is no longer throttled"
|
|
14442
|
+
),
|
|
14443
|
+
utterances: zod3.array(
|
|
13533
14444
|
zod3.object({
|
|
13534
|
-
|
|
13535
|
-
start: zod3.number().describe("The starting time, in milliseconds, of the
|
|
13536
|
-
end: zod3.number().describe("The ending time, in milliseconds, of the
|
|
13537
|
-
|
|
13538
|
-
|
|
13539
|
-
|
|
13540
|
-
|
|
14445
|
+
confidence: zod3.number().describe("The confidence score for the transcript of this utterance"),
|
|
14446
|
+
start: zod3.number().describe("The starting time, in milliseconds, of the utterance in the audio file"),
|
|
14447
|
+
end: zod3.number().describe("The ending time, in milliseconds, of the utterance in the audio file"),
|
|
14448
|
+
text: zod3.string().describe("The text for this utterance"),
|
|
14449
|
+
words: zod3.array(
|
|
14450
|
+
zod3.object({
|
|
14451
|
+
confidence: zod3.number().describe("The confidence score for the transcript of this word"),
|
|
14452
|
+
start: zod3.number().describe("The starting time, in milliseconds, for the word"),
|
|
14453
|
+
end: zod3.number().describe("The ending time, in milliseconds, for the word"),
|
|
14454
|
+
text: zod3.string().describe("The text of the word"),
|
|
14455
|
+
channel: zod3.string().nullish().describe(
|
|
14456
|
+
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
14457
|
+
),
|
|
14458
|
+
speaker: zod3.string().nullable().describe(
|
|
14459
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization) is enabled, else null"
|
|
14460
|
+
)
|
|
14461
|
+
})
|
|
14462
|
+
).describe("The words in the utterance."),
|
|
13541
14463
|
channel: zod3.string().nullish().describe(
|
|
13542
14464
|
"The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
13543
14465
|
),
|
|
13544
|
-
speaker: zod3.string().
|
|
13545
|
-
|
|
14466
|
+
speaker: zod3.string().describe(
|
|
14467
|
+
'The speaker of this utterance, where each speaker is assigned a sequential capital letter - e.g. "A" for Speaker A, "B" for Speaker B, etc.'
|
|
14468
|
+
),
|
|
14469
|
+
translated_texts: zod3.record(zod3.string(), zod3.string()).optional().describe(
|
|
14470
|
+
'Translations keyed by language code (e.g., `{"es": "Texto traducido", "de": "\xDCbersetzter Text"}`). Only present when `match_original_utterance` is enabled with translation.'
|
|
13546
14471
|
)
|
|
13547
|
-
})
|
|
14472
|
+
})
|
|
13548
14473
|
).nullish().describe(
|
|
13549
|
-
"
|
|
14474
|
+
"When multichannel or speaker_labels is enabled, a list of turn-by-turn utterance objects.\nSee [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization) and [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/multichannel) for more information.\n"
|
|
13550
14475
|
),
|
|
13551
|
-
|
|
13552
|
-
"Whether [
|
|
14476
|
+
webhook_auth: zod3.boolean().describe(
|
|
14477
|
+
"Whether [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) authentication details were provided"
|
|
13553
14478
|
),
|
|
13554
|
-
|
|
14479
|
+
webhook_auth_header_name: zod3.string().nullish().describe(
|
|
14480
|
+
"The header name to be sent with the transcript completed or failed [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) requests"
|
|
14481
|
+
),
|
|
14482
|
+
webhook_status_code: zod3.number().nullish().describe(
|
|
14483
|
+
"The status code we received from your server when delivering the transcript completed or failed [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) request, if a webhook URL was provided"
|
|
14484
|
+
),
|
|
14485
|
+
webhook_url: zod3.string().nullish().describe(
|
|
14486
|
+
"The URL to which we send [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) requests.\n"
|
|
14487
|
+
),
|
|
14488
|
+
words: zod3.array(
|
|
13555
14489
|
zod3.object({
|
|
13556
|
-
|
|
13557
|
-
|
|
13558
|
-
|
|
13559
|
-
|
|
13560
|
-
|
|
13561
|
-
"
|
|
13562
|
-
"credit_card_number",
|
|
13563
|
-
"date",
|
|
13564
|
-
"date_interval",
|
|
13565
|
-
"date_of_birth",
|
|
13566
|
-
"drivers_license",
|
|
13567
|
-
"drug",
|
|
13568
|
-
"duration",
|
|
13569
|
-
"email_address",
|
|
13570
|
-
"event",
|
|
13571
|
-
"filename",
|
|
13572
|
-
"gender_sexuality",
|
|
13573
|
-
"healthcare_number",
|
|
13574
|
-
"injury",
|
|
13575
|
-
"ip_address",
|
|
13576
|
-
"language",
|
|
13577
|
-
"location",
|
|
13578
|
-
"marital_status",
|
|
13579
|
-
"medical_condition",
|
|
13580
|
-
"medical_process",
|
|
13581
|
-
"money_amount",
|
|
13582
|
-
"nationality",
|
|
13583
|
-
"number_sequence",
|
|
13584
|
-
"occupation",
|
|
13585
|
-
"organization",
|
|
13586
|
-
"passport_number",
|
|
13587
|
-
"password",
|
|
13588
|
-
"person_age",
|
|
13589
|
-
"person_name",
|
|
13590
|
-
"phone_number",
|
|
13591
|
-
"physical_attribute",
|
|
13592
|
-
"political_affiliation",
|
|
13593
|
-
"religion",
|
|
13594
|
-
"statistics",
|
|
13595
|
-
"time",
|
|
13596
|
-
"url",
|
|
13597
|
-
"us_social_security_number",
|
|
13598
|
-
"username",
|
|
13599
|
-
"vehicle_id",
|
|
13600
|
-
"zodiac_sign"
|
|
13601
|
-
]).describe("The type of entity for the detected entity"),
|
|
13602
|
-
text: zod3.string().describe("The text for the detected entity"),
|
|
13603
|
-
start: zod3.number().describe(
|
|
13604
|
-
"The starting time, in milliseconds, at which the detected entity appears in the audio file"
|
|
14490
|
+
confidence: zod3.number().describe("The confidence score for the transcript of this word"),
|
|
14491
|
+
start: zod3.number().describe("The starting time, in milliseconds, for the word"),
|
|
14492
|
+
end: zod3.number().describe("The ending time, in milliseconds, for the word"),
|
|
14493
|
+
text: zod3.string().describe("The text of the word"),
|
|
14494
|
+
channel: zod3.string().nullish().describe(
|
|
14495
|
+
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
13605
14496
|
),
|
|
13606
|
-
|
|
13607
|
-
"The
|
|
14497
|
+
speaker: zod3.string().nullable().describe(
|
|
14498
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization) is enabled, else null"
|
|
13608
14499
|
)
|
|
13609
|
-
})
|
|
14500
|
+
})
|
|
13610
14501
|
).nullish().describe(
|
|
13611
|
-
"An array of
|
|
13612
|
-
),
|
|
13613
|
-
|
|
13614
|
-
|
|
13615
|
-
),
|
|
13616
|
-
|
|
13617
|
-
"
|
|
13618
|
-
)
|
|
13619
|
-
|
|
13620
|
-
|
|
13621
|
-
|
|
14502
|
+
"An array of temporally-sequential word objects, one for each word in the transcript.\n"
|
|
14503
|
+
),
|
|
14504
|
+
acoustic_model: zod3.string().describe("This parameter does not currently have any functionality attached to it."),
|
|
14505
|
+
custom_topics: zod3.boolean().nullish().describe("This parameter does not currently have any functionality attached to it."),
|
|
14506
|
+
language_model: zod3.string().describe("This parameter does not currently have any functionality attached to it."),
|
|
14507
|
+
speech_model: zod3.string().describe(
|
|
14508
|
+
"The speech model to use for the transcription. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models."
|
|
14509
|
+
).or(zod3.null()).describe(
|
|
14510
|
+
"This parameter has been replaced with the `speech_models` parameter, learn more about the `speech_models` parameter [here](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model).\n"
|
|
14511
|
+
),
|
|
14512
|
+
speed_boost: zod3.boolean().nullish().describe("This parameter does not currently have any functionality attached to it."),
|
|
14513
|
+
topics: zod3.array(zod3.string()).optional().describe("This parameter does not currently have any functionality attached to it."),
|
|
14514
|
+
translated_texts: zod3.object({
|
|
14515
|
+
language_code: zod3.string().optional().describe("Translated text for this language code")
|
|
14516
|
+
}).optional().describe(
|
|
14517
|
+
"Translated text keyed by language code. See [Translation](https://www.assemblyai.com/docs/speech-understanding/translation) for more details."
|
|
14518
|
+
)
|
|
13622
14519
|
}).describe("A transcript object");
|
|
13623
|
-
var getSubtitlesParams = zod3.object({
|
|
13624
|
-
transcript_id: zod3.string().describe("ID of the transcript"),
|
|
13625
|
-
subtitle_format: zod3.enum(["srt", "vtt"]).describe("The format of the captions")
|
|
13626
|
-
});
|
|
13627
|
-
var getSubtitlesQueryParams = zod3.object({
|
|
13628
|
-
chars_per_caption: zod3.number().optional().describe("The maximum number of characters per caption")
|
|
13629
|
-
});
|
|
13630
14520
|
var getTranscriptSentencesParams = zod3.object({
|
|
13631
14521
|
transcript_id: zod3.string().describe("ID of the transcript")
|
|
13632
14522
|
});
|
|
13633
|
-
var getTranscriptSentencesResponseConfidenceMin = 0;
|
|
13634
|
-
var getTranscriptSentencesResponseConfidenceMax = 1;
|
|
13635
|
-
var getTranscriptSentencesResponseSentencesItemConfidenceMin = 0;
|
|
13636
|
-
var getTranscriptSentencesResponseSentencesItemConfidenceMax = 1;
|
|
13637
|
-
var getTranscriptSentencesResponseSentencesItemWordsItemConfidenceMin = 0;
|
|
13638
|
-
var getTranscriptSentencesResponseSentencesItemWordsItemConfidenceMax = 1;
|
|
13639
14523
|
var getTranscriptSentencesResponse = zod3.object({
|
|
13640
14524
|
id: zod3.string().uuid().describe("The unique identifier for the transcript"),
|
|
13641
|
-
confidence: zod3.number().
|
|
14525
|
+
confidence: zod3.number().describe("The confidence score for the transcript"),
|
|
13642
14526
|
audio_duration: zod3.number().describe("The duration of the audio file in seconds"),
|
|
13643
14527
|
sentences: zod3.array(
|
|
13644
14528
|
zod3.object({
|
|
13645
14529
|
text: zod3.string().describe("The transcript of the sentence"),
|
|
13646
14530
|
start: zod3.number().describe("The starting time, in milliseconds, for the sentence"),
|
|
13647
14531
|
end: zod3.number().describe("The ending time, in milliseconds, for the sentence"),
|
|
13648
|
-
confidence: zod3.number().
|
|
14532
|
+
confidence: zod3.number().describe("The confidence score for the transcript of this sentence"),
|
|
13649
14533
|
words: zod3.array(
|
|
13650
14534
|
zod3.object({
|
|
13651
|
-
confidence: zod3.number().
|
|
14535
|
+
confidence: zod3.number().describe("The confidence score for the transcript of this word"),
|
|
13652
14536
|
start: zod3.number().describe("The starting time, in milliseconds, for the word"),
|
|
13653
14537
|
end: zod3.number().describe("The ending time, in milliseconds, for the word"),
|
|
13654
14538
|
text: zod3.string().describe("The text of the word"),
|
|
@@ -13656,7 +14540,7 @@ var getTranscriptSentencesResponse = zod3.object({
|
|
|
13656
14540
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
13657
14541
|
),
|
|
13658
14542
|
speaker: zod3.string().nullable().describe(
|
|
13659
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/
|
|
14543
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization) is enabled, else null"
|
|
13660
14544
|
)
|
|
13661
14545
|
})
|
|
13662
14546
|
).describe("An array of words in the sentence"),
|
|
@@ -13664,7 +14548,7 @@ var getTranscriptSentencesResponse = zod3.object({
|
|
|
13664
14548
|
"The channel of the sentence. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
13665
14549
|
),
|
|
13666
14550
|
speaker: zod3.string().nullable().describe(
|
|
13667
|
-
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/
|
|
14551
|
+
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization) is enabled, else null"
|
|
13668
14552
|
)
|
|
13669
14553
|
})
|
|
13670
14554
|
).describe("An array of sentences in the transcript")
|
|
@@ -13672,25 +14556,19 @@ var getTranscriptSentencesResponse = zod3.object({
|
|
|
13672
14556
|
var getTranscriptParagraphsParams = zod3.object({
|
|
13673
14557
|
transcript_id: zod3.string().describe("ID of the transcript")
|
|
13674
14558
|
});
|
|
13675
|
-
var getTranscriptParagraphsResponseConfidenceMin = 0;
|
|
13676
|
-
var getTranscriptParagraphsResponseConfidenceMax = 1;
|
|
13677
|
-
var getTranscriptParagraphsResponseParagraphsItemConfidenceMin = 0;
|
|
13678
|
-
var getTranscriptParagraphsResponseParagraphsItemConfidenceMax = 1;
|
|
13679
|
-
var getTranscriptParagraphsResponseParagraphsItemWordsItemConfidenceMin = 0;
|
|
13680
|
-
var getTranscriptParagraphsResponseParagraphsItemWordsItemConfidenceMax = 1;
|
|
13681
14559
|
var getTranscriptParagraphsResponse = zod3.object({
|
|
13682
14560
|
id: zod3.string().uuid().describe("The unique identifier of your transcript"),
|
|
13683
|
-
confidence: zod3.number().
|
|
14561
|
+
confidence: zod3.number().describe("The confidence score for the transcript"),
|
|
13684
14562
|
audio_duration: zod3.number().describe("The duration of the audio file in seconds"),
|
|
13685
14563
|
paragraphs: zod3.array(
|
|
13686
14564
|
zod3.object({
|
|
13687
14565
|
text: zod3.string().describe("The transcript of the paragraph"),
|
|
13688
14566
|
start: zod3.number().describe("The starting time, in milliseconds, of the paragraph"),
|
|
13689
14567
|
end: zod3.number().describe("The ending time, in milliseconds, of the paragraph"),
|
|
13690
|
-
confidence: zod3.number().
|
|
14568
|
+
confidence: zod3.number().describe("The confidence score for the transcript of this paragraph"),
|
|
13691
14569
|
words: zod3.array(
|
|
13692
14570
|
zod3.object({
|
|
13693
|
-
confidence: zod3.number().
|
|
14571
|
+
confidence: zod3.number().describe("The confidence score for the transcript of this word"),
|
|
13694
14572
|
start: zod3.number().describe("The starting time, in milliseconds, for the word"),
|
|
13695
14573
|
end: zod3.number().describe("The ending time, in milliseconds, for the word"),
|
|
13696
14574
|
text: zod3.string().describe("The text of the word"),
|
|
@@ -13698,13 +14576,28 @@ var getTranscriptParagraphsResponse = zod3.object({
|
|
|
13698
14576
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
13699
14577
|
),
|
|
13700
14578
|
speaker: zod3.string().nullable().describe(
|
|
13701
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/
|
|
14579
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/speaker-diarization) is enabled, else null"
|
|
13702
14580
|
)
|
|
13703
14581
|
})
|
|
13704
14582
|
).describe("An array of words in the paragraph")
|
|
13705
14583
|
})
|
|
13706
14584
|
).describe("An array of paragraphs in the transcript")
|
|
13707
14585
|
});
|
|
14586
|
+
var getSubtitlesParams = zod3.object({
|
|
14587
|
+
transcript_id: zod3.string().describe("ID of the transcript"),
|
|
14588
|
+
subtitle_format: zod3.enum(["srt", "vtt"]).describe("The format of the captions")
|
|
14589
|
+
});
|
|
14590
|
+
var getSubtitlesQueryParams = zod3.object({
|
|
14591
|
+
chars_per_caption: zod3.number().optional().describe("The maximum number of characters per caption")
|
|
14592
|
+
});
|
|
14593
|
+
var getSubtitlesResponse = zod3.object({});
|
|
14594
|
+
var getRedactedAudioParams = zod3.object({
|
|
14595
|
+
transcript_id: zod3.string().describe("ID of the transcript")
|
|
14596
|
+
});
|
|
14597
|
+
var getRedactedAudioResponse = zod3.object({
|
|
14598
|
+
status: zod3.enum(["redacted_audio_ready"]).describe("The status of the redacted audio"),
|
|
14599
|
+
redacted_audio_url: zod3.string().describe("The URL of the redacted audio file")
|
|
14600
|
+
});
|
|
13708
14601
|
var wordSearchParams = zod3.object({
|
|
13709
14602
|
transcript_id: zod3.string().describe("ID of the transcript")
|
|
13710
14603
|
});
|
|
@@ -13721,7 +14614,7 @@ var wordSearchResponse = zod3.object({
|
|
|
13721
14614
|
text: zod3.string().describe("The matched word"),
|
|
13722
14615
|
count: zod3.number().describe("The total amount of times the word is in the transcript"),
|
|
13723
14616
|
timestamps: zod3.array(
|
|
13724
|
-
zod3.array(zod3.number()
|
|
14617
|
+
zod3.array(zod3.number()).describe(
|
|
13725
14618
|
"An array of timestamps structured as [`start_time`, `end_time`] in milliseconds"
|
|
13726
14619
|
)
|
|
13727
14620
|
).describe("An array of timestamps"),
|
|
@@ -13731,205 +14624,6 @@ var wordSearchResponse = zod3.object({
|
|
|
13731
14624
|
})
|
|
13732
14625
|
).describe("The matches of the search")
|
|
13733
14626
|
});
|
|
13734
|
-
var getRedactedAudioParams = zod3.object({
|
|
13735
|
-
transcript_id: zod3.string().describe("ID of the transcript")
|
|
13736
|
-
});
|
|
13737
|
-
var getRedactedAudioResponse = zod3.object({
|
|
13738
|
-
status: zod3.enum(["redacted_audio_ready"]).describe("The status of the redacted audio"),
|
|
13739
|
-
redacted_audio_url: zod3.string().describe("The URL of the redacted audio file")
|
|
13740
|
-
});
|
|
13741
|
-
var createTemporaryTokenBodyExpiresInMin = 60;
|
|
13742
|
-
var createTemporaryTokenBody = zod3.object({
|
|
13743
|
-
expires_in: zod3.number().min(createTemporaryTokenBodyExpiresInMin).describe("The amount of time until the token expires in seconds")
|
|
13744
|
-
});
|
|
13745
|
-
var createTemporaryTokenResponse = zod3.object({
|
|
13746
|
-
token: zod3.string().describe("The temporary authentication token for Streaming Speech-to-Text")
|
|
13747
|
-
});
|
|
13748
|
-
var lemurTaskBodyFinalModelDefault = "default";
|
|
13749
|
-
var lemurTaskBodyMaxOutputSizeDefault = 2e3;
|
|
13750
|
-
var lemurTaskBodyTemperatureDefault = 0;
|
|
13751
|
-
var lemurTaskBodyTemperatureMin = 0;
|
|
13752
|
-
var lemurTaskBodyTemperatureMax = 1;
|
|
13753
|
-
var lemurTaskBody = zod3.object({
|
|
13754
|
-
prompt: zod3.string().describe(
|
|
13755
|
-
"Your text to prompt the model to produce a desired output, including any context you want to pass into the model."
|
|
13756
|
-
)
|
|
13757
|
-
}).and(
|
|
13758
|
-
zod3.object({
|
|
13759
|
-
transcript_ids: zod3.array(zod3.string().uuid()).optional().describe(
|
|
13760
|
-
"A list of completed transcripts with text. Up to a maximum of 100 hours of audio.\nUse either transcript_ids or input_text as input into LeMUR.\n"
|
|
13761
|
-
),
|
|
13762
|
-
input_text: zod3.string().optional().describe(
|
|
13763
|
-
"Custom formatted transcript data. Maximum size is the context limit of the selected model.\nUse either transcript_ids or input_text as input into LeMUR.\n"
|
|
13764
|
-
),
|
|
13765
|
-
context: zod3.string().or(zod3.record(zod3.string(), zod3.any())).optional().describe("Context to provide the model. This can be a string or a free-form JSON value."),
|
|
13766
|
-
final_model: zod3.enum([
|
|
13767
|
-
"anthropic/claude-3-5-sonnet",
|
|
13768
|
-
"anthropic/claude-3-opus",
|
|
13769
|
-
"anthropic/claude-3-haiku"
|
|
13770
|
-
]).describe("The model that is used for the final prompt after compression is performed.\n").or(zod3.string()).describe("The model that is used for the final prompt after compression is performed.\n"),
|
|
13771
|
-
max_output_size: zod3.number().default(lemurTaskBodyMaxOutputSizeDefault).describe("Max output size in tokens."),
|
|
13772
|
-
temperature: zod3.number().min(lemurTaskBodyTemperatureMin).max(lemurTaskBodyTemperatureMax).optional().describe(
|
|
13773
|
-
"The temperature to use for the model.\nHigher values result in answers that are more creative, lower values are more conservative.\nCan be any value between 0.0 and 1.0 inclusive.\n"
|
|
13774
|
-
)
|
|
13775
|
-
})
|
|
13776
|
-
);
|
|
13777
|
-
var lemurTaskResponseUsageInputTokensMin = 0;
|
|
13778
|
-
var lemurTaskResponseUsageOutputTokensMin = 0;
|
|
13779
|
-
var lemurTaskResponse = zod3.object({
|
|
13780
|
-
response: zod3.string().describe("The response generated by LeMUR.")
|
|
13781
|
-
}).and(
|
|
13782
|
-
zod3.object({
|
|
13783
|
-
request_id: zod3.string().uuid().describe("The ID of the LeMUR request"),
|
|
13784
|
-
usage: zod3.object({
|
|
13785
|
-
input_tokens: zod3.number().min(lemurTaskResponseUsageInputTokensMin).describe("The number of input tokens used by the model"),
|
|
13786
|
-
output_tokens: zod3.number().min(lemurTaskResponseUsageOutputTokensMin).describe("The number of output tokens generated by the model")
|
|
13787
|
-
}).describe("The usage numbers for the LeMUR request")
|
|
13788
|
-
})
|
|
13789
|
-
);
|
|
13790
|
-
var lemurSummaryBodyFinalModelDefault = "default";
|
|
13791
|
-
var lemurSummaryBodyMaxOutputSizeDefault = 2e3;
|
|
13792
|
-
var lemurSummaryBodyTemperatureDefault = 0;
|
|
13793
|
-
var lemurSummaryBodyTemperatureMin = 0;
|
|
13794
|
-
var lemurSummaryBodyTemperatureMax = 1;
|
|
13795
|
-
var lemurSummaryBody = zod3.object({
|
|
13796
|
-
transcript_ids: zod3.array(zod3.string().uuid()).optional().describe(
|
|
13797
|
-
"A list of completed transcripts with text. Up to a maximum of 100 hours of audio.\nUse either transcript_ids or input_text as input into LeMUR.\n"
|
|
13798
|
-
),
|
|
13799
|
-
input_text: zod3.string().optional().describe(
|
|
13800
|
-
"Custom formatted transcript data. Maximum size is the context limit of the selected model.\nUse either transcript_ids or input_text as input into LeMUR.\n"
|
|
13801
|
-
),
|
|
13802
|
-
context: zod3.string().or(zod3.record(zod3.string(), zod3.any())).optional().describe("Context to provide the model. This can be a string or a free-form JSON value."),
|
|
13803
|
-
final_model: zod3.enum(["anthropic/claude-3-5-sonnet", "anthropic/claude-3-opus", "anthropic/claude-3-haiku"]).describe("The model that is used for the final prompt after compression is performed.\n").or(zod3.string()).describe("The model that is used for the final prompt after compression is performed.\n"),
|
|
13804
|
-
max_output_size: zod3.number().default(lemurSummaryBodyMaxOutputSizeDefault).describe("Max output size in tokens."),
|
|
13805
|
-
temperature: zod3.number().min(lemurSummaryBodyTemperatureMin).max(lemurSummaryBodyTemperatureMax).optional().describe(
|
|
13806
|
-
"The temperature to use for the model.\nHigher values result in answers that are more creative, lower values are more conservative.\nCan be any value between 0.0 and 1.0 inclusive.\n"
|
|
13807
|
-
)
|
|
13808
|
-
}).and(
|
|
13809
|
-
zod3.object({
|
|
13810
|
-
answer_format: zod3.string().optional().describe(
|
|
13811
|
-
'How you want the summary to be returned. This can be any text. Examples: "TLDR", "bullet points"\n'
|
|
13812
|
-
)
|
|
13813
|
-
})
|
|
13814
|
-
);
|
|
13815
|
-
var lemurSummaryResponseUsageInputTokensMin = 0;
|
|
13816
|
-
var lemurSummaryResponseUsageOutputTokensMin = 0;
|
|
13817
|
-
var lemurSummaryResponse = zod3.object({
|
|
13818
|
-
response: zod3.string().describe("The response generated by LeMUR.")
|
|
13819
|
-
}).and(
|
|
13820
|
-
zod3.object({
|
|
13821
|
-
request_id: zod3.string().uuid().describe("The ID of the LeMUR request"),
|
|
13822
|
-
usage: zod3.object({
|
|
13823
|
-
input_tokens: zod3.number().min(lemurSummaryResponseUsageInputTokensMin).describe("The number of input tokens used by the model"),
|
|
13824
|
-
output_tokens: zod3.number().min(lemurSummaryResponseUsageOutputTokensMin).describe("The number of output tokens generated by the model")
|
|
13825
|
-
}).describe("The usage numbers for the LeMUR request")
|
|
13826
|
-
})
|
|
13827
|
-
);
|
|
13828
|
-
var lemurQuestionAnswerBodyFinalModelDefault = "default";
|
|
13829
|
-
var lemurQuestionAnswerBodyMaxOutputSizeDefault = 2e3;
|
|
13830
|
-
var lemurQuestionAnswerBodyTemperatureDefault = 0;
|
|
13831
|
-
var lemurQuestionAnswerBodyTemperatureMin = 0;
|
|
13832
|
-
var lemurQuestionAnswerBodyTemperatureMax = 1;
|
|
13833
|
-
var lemurQuestionAnswerBody = zod3.object({
|
|
13834
|
-
transcript_ids: zod3.array(zod3.string().uuid()).optional().describe(
|
|
13835
|
-
"A list of completed transcripts with text. Up to a maximum of 100 hours of audio.\nUse either transcript_ids or input_text as input into LeMUR.\n"
|
|
13836
|
-
),
|
|
13837
|
-
input_text: zod3.string().optional().describe(
|
|
13838
|
-
"Custom formatted transcript data. Maximum size is the context limit of the selected model.\nUse either transcript_ids or input_text as input into LeMUR.\n"
|
|
13839
|
-
),
|
|
13840
|
-
context: zod3.string().or(zod3.record(zod3.string(), zod3.any())).optional().describe("Context to provide the model. This can be a string or a free-form JSON value."),
|
|
13841
|
-
final_model: zod3.enum(["anthropic/claude-3-5-sonnet", "anthropic/claude-3-opus", "anthropic/claude-3-haiku"]).describe("The model that is used for the final prompt after compression is performed.\n").or(zod3.string()).describe("The model that is used for the final prompt after compression is performed.\n"),
|
|
13842
|
-
max_output_size: zod3.number().default(lemurQuestionAnswerBodyMaxOutputSizeDefault).describe("Max output size in tokens."),
|
|
13843
|
-
temperature: zod3.number().min(lemurQuestionAnswerBodyTemperatureMin).max(lemurQuestionAnswerBodyTemperatureMax).optional().describe(
|
|
13844
|
-
"The temperature to use for the model.\nHigher values result in answers that are more creative, lower values are more conservative.\nCan be any value between 0.0 and 1.0 inclusive.\n"
|
|
13845
|
-
)
|
|
13846
|
-
}).and(
|
|
13847
|
-
zod3.object({
|
|
13848
|
-
questions: zod3.array(
|
|
13849
|
-
zod3.object({
|
|
13850
|
-
question: zod3.string().describe(
|
|
13851
|
-
"The question you wish to ask. For more complex questions use default model."
|
|
13852
|
-
),
|
|
13853
|
-
context: zod3.string().or(zod3.record(zod3.string(), zod3.any())).optional().describe(
|
|
13854
|
-
"Any context about the transcripts you wish to provide. This can be a string or any object."
|
|
13855
|
-
),
|
|
13856
|
-
answer_format: zod3.string().optional().describe(
|
|
13857
|
-
`How you want the answer to be returned. This can be any text. Can't be used with answer_options. Examples: "short sentence", "bullet points"
|
|
13858
|
-
`
|
|
13859
|
-
),
|
|
13860
|
-
answer_options: zod3.array(zod3.string()).optional().describe(
|
|
13861
|
-
`What discrete options to return. Useful for precise responses. Can't be used with answer_format. Example: ["Yes", "No"]
|
|
13862
|
-
`
|
|
13863
|
-
)
|
|
13864
|
-
})
|
|
13865
|
-
).describe("A list of questions to ask")
|
|
13866
|
-
})
|
|
13867
|
-
);
|
|
13868
|
-
var lemurQuestionAnswerResponseUsageInputTokensMin = 0;
|
|
13869
|
-
var lemurQuestionAnswerResponseUsageOutputTokensMin = 0;
|
|
13870
|
-
var lemurQuestionAnswerResponse = zod3.object({
|
|
13871
|
-
request_id: zod3.string().uuid().describe("The ID of the LeMUR request"),
|
|
13872
|
-
usage: zod3.object({
|
|
13873
|
-
input_tokens: zod3.number().min(lemurQuestionAnswerResponseUsageInputTokensMin).describe("The number of input tokens used by the model"),
|
|
13874
|
-
output_tokens: zod3.number().min(lemurQuestionAnswerResponseUsageOutputTokensMin).describe("The number of output tokens generated by the model")
|
|
13875
|
-
}).describe("The usage numbers for the LeMUR request")
|
|
13876
|
-
}).and(
|
|
13877
|
-
zod3.object({
|
|
13878
|
-
response: zod3.array(
|
|
13879
|
-
zod3.object({
|
|
13880
|
-
question: zod3.string().describe("The question for LeMUR to answer"),
|
|
13881
|
-
answer: zod3.string().describe("The answer generated by LeMUR")
|
|
13882
|
-
}).describe("An answer generated by LeMUR and its question")
|
|
13883
|
-
).describe("The answers generated by LeMUR and their questions")
|
|
13884
|
-
})
|
|
13885
|
-
);
|
|
13886
|
-
var getLemurResponseParams = zod3.object({
|
|
13887
|
-
request_id: zod3.string().describe(
|
|
13888
|
-
"The ID of the LeMUR request you previously made.\nThis would be found in the response of the original request.\n"
|
|
13889
|
-
)
|
|
13890
|
-
});
|
|
13891
|
-
var getLemurResponseResponseUsageInputTokensMin = 0;
|
|
13892
|
-
var getLemurResponseResponseUsageOutputTokensMin = 0;
|
|
13893
|
-
var getLemurResponseResponseUsageInputTokensMinOne = 0;
|
|
13894
|
-
var getLemurResponseResponseUsageOutputTokensMinOne = 0;
|
|
13895
|
-
var getLemurResponseResponse = zod3.object({
|
|
13896
|
-
response: zod3.string().describe("The response generated by LeMUR.")
|
|
13897
|
-
}).and(
|
|
13898
|
-
zod3.object({
|
|
13899
|
-
request_id: zod3.string().uuid().describe("The ID of the LeMUR request"),
|
|
13900
|
-
usage: zod3.object({
|
|
13901
|
-
input_tokens: zod3.number().min(getLemurResponseResponseUsageInputTokensMin).describe("The number of input tokens used by the model"),
|
|
13902
|
-
output_tokens: zod3.number().min(getLemurResponseResponseUsageOutputTokensMin).describe("The number of output tokens generated by the model")
|
|
13903
|
-
}).describe("The usage numbers for the LeMUR request")
|
|
13904
|
-
})
|
|
13905
|
-
).or(
|
|
13906
|
-
zod3.object({
|
|
13907
|
-
request_id: zod3.string().uuid().describe("The ID of the LeMUR request"),
|
|
13908
|
-
usage: zod3.object({
|
|
13909
|
-
input_tokens: zod3.number().min(getLemurResponseResponseUsageInputTokensMinOne).describe("The number of input tokens used by the model"),
|
|
13910
|
-
output_tokens: zod3.number().min(getLemurResponseResponseUsageOutputTokensMinOne).describe("The number of output tokens generated by the model")
|
|
13911
|
-
}).describe("The usage numbers for the LeMUR request")
|
|
13912
|
-
}).and(
|
|
13913
|
-
zod3.object({
|
|
13914
|
-
response: zod3.array(
|
|
13915
|
-
zod3.object({
|
|
13916
|
-
question: zod3.string().describe("The question for LeMUR to answer"),
|
|
13917
|
-
answer: zod3.string().describe("The answer generated by LeMUR")
|
|
13918
|
-
}).describe("An answer generated by LeMUR and its question")
|
|
13919
|
-
).describe("The answers generated by LeMUR and their questions")
|
|
13920
|
-
})
|
|
13921
|
-
)
|
|
13922
|
-
);
|
|
13923
|
-
var purgeLemurRequestDataParams = zod3.object({
|
|
13924
|
-
request_id: zod3.string().describe(
|
|
13925
|
-
"The ID of the LeMUR request whose data you want to delete. This would be found in the response of the original request."
|
|
13926
|
-
)
|
|
13927
|
-
});
|
|
13928
|
-
var purgeLemurRequestDataResponse = zod3.object({
|
|
13929
|
-
request_id: zod3.string().uuid().describe("The ID of the deletion request of the LeMUR request"),
|
|
13930
|
-
request_id_to_purge: zod3.string().uuid().describe("The ID of the LeMUR request to purge the data for"),
|
|
13931
|
-
deleted: zod3.boolean().describe("Whether the request data was deleted")
|
|
13932
|
-
});
|
|
13933
14627
|
|
|
13934
14628
|
// src/generated/assemblyai/streaming-types.zod.ts
|
|
13935
14629
|
import { z as zod4 } from "zod";
|
|
@@ -13944,25 +14638,37 @@ var streamingTranscriberParams = zod4.object({
|
|
|
13944
14638
|
enableExtraSessionInformation: zod4.boolean().optional().describe(
|
|
13945
14639
|
"Set to true to receive the SessionInformation message before the session ends. Defaults to false."
|
|
13946
14640
|
),
|
|
14641
|
+
domain: zod4.string().optional().describe(
|
|
14642
|
+
'Enable domain-specific transcription models to improve accuracy for specialized terminology. Set to `"medical-v1"` to enable [Medical Mode](https://www.assemblyai.com/docs/streaming/medical-mode) for improved accuracy of medical terms such as medications, procedures, conditions, and dosages. Supported languages: English (`en`), Spanish (`es`), German (`de`), French (`fr`). If used with an unsupported language, the parameter is ignored and a warning is returned.'
|
|
14643
|
+
),
|
|
13947
14644
|
endOfTurnConfidenceThreshold: zod4.number().optional().describe("From SDK v3"),
|
|
13948
14645
|
minEndOfTurnSilenceWhenConfident: zod4.number().optional().describe("From SDK v3"),
|
|
14646
|
+
minTurnSilence: zod4.number().optional().describe("From SDK v3"),
|
|
13949
14647
|
maxTurnSilence: zod4.number().optional().describe("From SDK v3"),
|
|
13950
14648
|
vadThreshold: zod4.number().optional().describe("From SDK v3"),
|
|
13951
14649
|
formatTurns: zod4.boolean().optional().describe("From SDK v3"),
|
|
13952
14650
|
filterProfanity: zod4.boolean().optional().describe("From SDK v3"),
|
|
13953
14651
|
keyterms: zod4.array(zod4.string()).optional().describe("From SDK v3"),
|
|
13954
14652
|
keytermsPrompt: zod4.array(zod4.string()).optional().describe("From SDK v3"),
|
|
13955
|
-
|
|
14653
|
+
prompt: zod4.string().optional().describe("From SDK v3"),
|
|
14654
|
+
speechModel: zod4.enum(["universal-streaming-english", "universal-streaming-multilingual"]).describe("From SDK v3"),
|
|
13956
14655
|
languageDetection: zod4.boolean().optional().describe("From SDK v3"),
|
|
13957
|
-
inactivityTimeout: zod4.number().optional().describe("From SDK v3")
|
|
14656
|
+
inactivityTimeout: zod4.number().optional().describe("From SDK v3"),
|
|
14657
|
+
speakerLabels: zod4.boolean().optional().describe("From SDK v3"),
|
|
14658
|
+
maxSpeakers: zod4.number().optional().describe("From SDK v3"),
|
|
14659
|
+
llmGateway: zod4.unknown().optional().describe("From SDK v3")
|
|
13958
14660
|
});
|
|
13959
14661
|
var streamingUpdateConfigParams = zod4.object({
|
|
13960
14662
|
end_utterance_silence_threshold: zod4.number().min(0).max(2e4).optional().describe("The duration threshold in milliseconds"),
|
|
13961
14663
|
end_of_turn_confidence_threshold: zod4.number().optional().describe("From SDK v3"),
|
|
13962
14664
|
min_end_of_turn_silence_when_confident: zod4.number().optional().describe("From SDK v3"),
|
|
14665
|
+
min_turn_silence: zod4.number().optional().describe("From SDK v3"),
|
|
13963
14666
|
max_turn_silence: zod4.number().optional().describe("From SDK v3"),
|
|
13964
14667
|
vad_threshold: zod4.number().optional().describe("From SDK v3"),
|
|
13965
|
-
format_turns: zod4.boolean().optional().describe("From SDK v3")
|
|
14668
|
+
format_turns: zod4.boolean().optional().describe("From SDK v3"),
|
|
14669
|
+
keyterms_prompt: zod4.array(zod4.string()).optional().describe("From SDK v3"),
|
|
14670
|
+
prompt: zod4.string().optional().describe("From SDK v3"),
|
|
14671
|
+
filter_profanity: zod4.boolean().optional().describe("From SDK v3")
|
|
13966
14672
|
});
|
|
13967
14673
|
|
|
13968
14674
|
// src/generated/gladia/api/gladiaControlAPI.zod.ts
|
|
@@ -31938,7 +32644,7 @@ var createRealtimeClientSecretBody = zod6.object({
|
|
|
31938
32644
|
format: zod6.discriminatedUnion("type", [
|
|
31939
32645
|
zod6.object({
|
|
31940
32646
|
type: zod6.enum(["audio/pcm"]).describe("The audio format. Always `audio/pcm`."),
|
|
31941
|
-
rate: zod6.literal(24e3).
|
|
32647
|
+
rate: zod6.literal(24e3).describe("The sample rate of the audio. Always `24000`.")
|
|
31942
32648
|
}).describe("The PCM audio format. Only a 24kHz sample rate is supported."),
|
|
31943
32649
|
zod6.object({
|
|
31944
32650
|
type: zod6.enum(["audio/pcmu"]).describe("The audio format. Always `audio/pcmu`.")
|
|
@@ -32037,7 +32743,7 @@ var createRealtimeClientSecretBody = zod6.object({
|
|
|
32037
32743
|
format: zod6.discriminatedUnion("type", [
|
|
32038
32744
|
zod6.object({
|
|
32039
32745
|
type: zod6.enum(["audio/pcm"]).describe("The audio format. Always `audio/pcm`."),
|
|
32040
|
-
rate: zod6.literal(24e3).
|
|
32746
|
+
rate: zod6.literal(24e3).describe("The sample rate of the audio. Always `24000`.")
|
|
32041
32747
|
}).describe("The PCM audio format. Only a 24kHz sample rate is supported."),
|
|
32042
32748
|
zod6.object({
|
|
32043
32749
|
type: zod6.enum(["audio/pcmu"]).describe("The audio format. Always `audio/pcmu`.")
|
|
@@ -32247,7 +32953,7 @@ var createRealtimeClientSecretBody = zod6.object({
|
|
|
32247
32953
|
format: zod6.discriminatedUnion("type", [
|
|
32248
32954
|
zod6.object({
|
|
32249
32955
|
type: zod6.enum(["audio/pcm"]).describe("The audio format. Always `audio/pcm`."),
|
|
32250
|
-
rate: zod6.literal(24e3).
|
|
32956
|
+
rate: zod6.literal(24e3).describe("The sample rate of the audio. Always `24000`.")
|
|
32251
32957
|
}).describe("The PCM audio format. Only a 24kHz sample rate is supported."),
|
|
32252
32958
|
zod6.object({
|
|
32253
32959
|
type: zod6.enum(["audio/pcmu"]).describe("The audio format. Always `audio/pcmu`.")
|
|
@@ -32417,7 +33123,7 @@ var createRealtimeClientSecretResponse = zod6.object({
|
|
|
32417
33123
|
format: zod6.discriminatedUnion("type", [
|
|
32418
33124
|
zod6.object({
|
|
32419
33125
|
type: zod6.enum(["audio/pcm"]).describe("The audio format. Always `audio/pcm`."),
|
|
32420
|
-
rate: zod6.literal(24e3).
|
|
33126
|
+
rate: zod6.literal(24e3).describe("The sample rate of the audio. Always `24000`.")
|
|
32421
33127
|
}).describe("The PCM audio format. Only a 24kHz sample rate is supported."),
|
|
32422
33128
|
zod6.object({
|
|
32423
33129
|
type: zod6.enum(["audio/pcmu"]).describe("The audio format. Always `audio/pcmu`.")
|
|
@@ -32516,7 +33222,7 @@ var createRealtimeClientSecretResponse = zod6.object({
|
|
|
32516
33222
|
format: zod6.discriminatedUnion("type", [
|
|
32517
33223
|
zod6.object({
|
|
32518
33224
|
type: zod6.enum(["audio/pcm"]).describe("The audio format. Always `audio/pcm`."),
|
|
32519
|
-
rate: zod6.literal(24e3).
|
|
33225
|
+
rate: zod6.literal(24e3).describe("The sample rate of the audio. Always `24000`.")
|
|
32520
33226
|
}).describe("The PCM audio format. Only a 24kHz sample rate is supported."),
|
|
32521
33227
|
zod6.object({
|
|
32522
33228
|
type: zod6.enum(["audio/pcmu"]).describe("The audio format. Always `audio/pcmu`.")
|
|
@@ -32735,7 +33441,7 @@ var createRealtimeClientSecretResponse = zod6.object({
|
|
|
32735
33441
|
format: zod6.discriminatedUnion("type", [
|
|
32736
33442
|
zod6.object({
|
|
32737
33443
|
type: zod6.enum(["audio/pcm"]).describe("The audio format. Always `audio/pcm`."),
|
|
32738
|
-
rate: zod6.literal(24e3).
|
|
33444
|
+
rate: zod6.literal(24e3).describe("The sample rate of the audio. Always `24000`.")
|
|
32739
33445
|
}).describe("The PCM audio format. Only a 24kHz sample rate is supported."),
|
|
32740
33446
|
zod6.object({
|
|
32741
33447
|
type: zod6.enum(["audio/pcmu"]).describe("The audio format. Always `audio/pcmu`.")
|
|
@@ -32964,7 +33670,7 @@ var createRealtimeSessionResponse = zod6.object({
|
|
|
32964
33670
|
format: zod6.discriminatedUnion("type", [
|
|
32965
33671
|
zod6.object({
|
|
32966
33672
|
type: zod6.enum(["audio/pcm"]).describe("The audio format. Always `audio/pcm`."),
|
|
32967
|
-
rate: zod6.literal(24e3).
|
|
33673
|
+
rate: zod6.literal(24e3).describe("The sample rate of the audio. Always `24000`.")
|
|
32968
33674
|
}).describe("The PCM audio format. Only a 24kHz sample rate is supported."),
|
|
32969
33675
|
zod6.object({
|
|
32970
33676
|
type: zod6.enum(["audio/pcmu"]).describe("The audio format. Always `audio/pcmu`.")
|
|
@@ -33008,7 +33714,7 @@ var createRealtimeSessionResponse = zod6.object({
|
|
|
33008
33714
|
format: zod6.discriminatedUnion("type", [
|
|
33009
33715
|
zod6.object({
|
|
33010
33716
|
type: zod6.enum(["audio/pcm"]).describe("The audio format. Always `audio/pcm`."),
|
|
33011
|
-
rate: zod6.literal(24e3).
|
|
33717
|
+
rate: zod6.literal(24e3).describe("The sample rate of the audio. Always `24000`.")
|
|
33012
33718
|
}).describe("The PCM audio format. Only a 24kHz sample rate is supported."),
|
|
33013
33719
|
zod6.object({
|
|
33014
33720
|
type: zod6.enum(["audio/pcmu"]).describe("The audio format. Always `audio/pcmu`.")
|
|
@@ -38106,20 +38812,6 @@ var LanguagePackInfoWritingDirection = {
|
|
|
38106
38812
|
"right-to-left": "right-to-left"
|
|
38107
38813
|
};
|
|
38108
38814
|
|
|
38109
|
-
// src/generated/speechmatics/schema/notificationConfigContentsItem.ts
|
|
38110
|
-
var NotificationConfigContentsItem = {
|
|
38111
|
-
jobinfo: "jobinfo",
|
|
38112
|
-
transcript: "transcript",
|
|
38113
|
-
"transcriptjson-v2": "transcript.json-v2",
|
|
38114
|
-
transcripttxt: "transcript.txt",
|
|
38115
|
-
transcriptsrt: "transcript.srt",
|
|
38116
|
-
alignment: "alignment",
|
|
38117
|
-
alignmentword_start_and_end: "alignment.word_start_and_end",
|
|
38118
|
-
alignmentone_per_line: "alignment.one_per_line",
|
|
38119
|
-
data: "data",
|
|
38120
|
-
text: "text"
|
|
38121
|
-
};
|
|
38122
|
-
|
|
38123
38815
|
// src/generated/speechmatics/schema/notificationConfigMethod.ts
|
|
38124
38816
|
var NotificationConfigMethod = {
|
|
38125
38817
|
post: "post",
|
|
@@ -39999,7 +40691,6 @@ export {
|
|
|
39999
40691
|
createOpenAIWhisperAdapter,
|
|
40000
40692
|
createSonioxAdapter,
|
|
40001
40693
|
createSpeechmaticsAdapter,
|
|
40002
|
-
createTemporaryToken,
|
|
40003
40694
|
createTranscript,
|
|
40004
40695
|
createTranscription,
|
|
40005
40696
|
createVoiceRouter,
|
|
@@ -40051,6 +40742,9 @@ export {
|
|
|
40051
40742
|
transcriptionsGet,
|
|
40052
40743
|
transcriptionsList,
|
|
40053
40744
|
transcriptionsListFiles,
|
|
40745
|
+
webHooksCreate,
|
|
40746
|
+
webHooksDelete,
|
|
40747
|
+
webHooksList,
|
|
40054
40748
|
zodToFieldConfigs
|
|
40055
40749
|
};
|
|
40056
40750
|
//# sourceMappingURL=index.mjs.map
|