voice-router-dev 0.8.8 → 0.9.0
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 +67 -0
- package/dist/constants.d.mts +23 -21
- package/dist/constants.d.ts +23 -21
- package/dist/constants.js +24 -24
- package/dist/constants.mjs +24 -24
- package/dist/{field-configs-BtR4uR2N.d.mts → field-configs-DYiUtRUz.d.mts} +5666 -6121
- package/dist/{field-configs-BtR4uR2N.d.ts → field-configs-DYiUtRUz.d.ts} +5666 -6121
- package/dist/field-configs.d.mts +1 -1
- package/dist/field-configs.d.ts +1 -1
- package/dist/field-configs.js +118 -196
- package/dist/field-configs.mjs +118 -196
- package/dist/index.d.mts +2006 -2105
- package/dist/index.d.ts +2006 -2105
- package/dist/index.js +267 -298
- package/dist/index.mjs +267 -298
- package/dist/{speechToTextChunkResponseModel-B4kVoFc3.d.ts → speechToTextChunkResponseModel-CI-Aqxcr.d.ts} +2015 -1846
- package/dist/{speechToTextChunkResponseModel-DmajV4F-.d.mts → speechToTextChunkResponseModel-D8VJ-wz6.d.mts} +2015 -1846
- package/dist/webhooks.d.mts +70 -2
- package/dist/webhooks.d.ts +70 -2
- package/dist/webhooks.js +113 -1
- package/dist/webhooks.mjs +111 -1
- package/package.json +1 -1
package/dist/index.js
CHANGED
|
@@ -983,60 +983,60 @@ var SonioxLanguage = {
|
|
|
983
983
|
// src/generated/soniox/models.ts
|
|
984
984
|
var SonioxModels = [
|
|
985
985
|
{ id: "stt-rt-v4", name: "Speech-to-Text Real-time v4", mode: "real_time" },
|
|
986
|
-
{ id: "stt-rt-v3", name: "Speech-to-Text Real-time v3", mode: "real_time" },
|
|
987
986
|
{ id: "stt-async-v4", name: "Speech-to-Text Async v4", mode: "async" },
|
|
988
|
-
{ id: "stt-
|
|
989
|
-
{ id: "stt-
|
|
990
|
-
{ id: "stt-
|
|
991
|
-
{ id: "stt-rt-
|
|
992
|
-
{ id: "stt-
|
|
993
|
-
{ id: "stt-
|
|
987
|
+
{ id: "stt-rt-preview", name: "Speech-to-Text Real-time Preview", mode: "real_time", aliasOf: "stt-rt-v4" },
|
|
988
|
+
{ id: "stt-async-preview", name: "Speech-to-Text Async Preview", mode: "async", aliasOf: "stt-async-v4" },
|
|
989
|
+
{ id: "stt-rt-v3-preview", name: "Speech-to-Text Real-time v3 Preview", mode: "real_time", aliasOf: "stt-rt-v4" },
|
|
990
|
+
{ id: "stt-rt-preview-v2", name: "Speech-to-Text Real-time Preview v2", mode: "real_time", aliasOf: "stt-rt-v4" },
|
|
991
|
+
{ id: "stt-async-preview-v1", name: "Speech-to-Text Async Preview v1", mode: "async", aliasOf: "stt-async-v4" },
|
|
992
|
+
{ id: "stt-rt-v3", name: "Speech-to-Text Real-time v3", mode: "real_time", aliasOf: "stt-rt-v4" },
|
|
993
|
+
{ id: "stt-async-v3", name: "Speech-to-Text Async v3", mode: "async", aliasOf: "stt-async-v4" }
|
|
994
994
|
];
|
|
995
995
|
var SonioxModelCodes = [
|
|
996
996
|
"stt-rt-v4",
|
|
997
|
-
"stt-rt-v3",
|
|
998
997
|
"stt-async-v4",
|
|
999
|
-
"stt-async-v3",
|
|
1000
998
|
"stt-rt-preview",
|
|
1001
999
|
"stt-async-preview",
|
|
1002
1000
|
"stt-rt-v3-preview",
|
|
1003
1001
|
"stt-rt-preview-v2",
|
|
1004
|
-
"stt-async-preview-v1"
|
|
1002
|
+
"stt-async-preview-v1",
|
|
1003
|
+
"stt-rt-v3",
|
|
1004
|
+
"stt-async-v3"
|
|
1005
1005
|
];
|
|
1006
1006
|
var SonioxModelLabels = {
|
|
1007
1007
|
"stt-rt-v4": "Speech-to-Text Real-time v4",
|
|
1008
|
-
"stt-rt-v3": "Speech-to-Text Real-time v3",
|
|
1009
1008
|
"stt-async-v4": "Speech-to-Text Async v4",
|
|
1010
|
-
"stt-async-v3": "Speech-to-Text Async v3",
|
|
1011
1009
|
"stt-rt-preview": "Speech-to-Text Real-time Preview",
|
|
1012
1010
|
"stt-async-preview": "Speech-to-Text Async Preview",
|
|
1013
1011
|
"stt-rt-v3-preview": "Speech-to-Text Real-time v3 Preview",
|
|
1014
1012
|
"stt-rt-preview-v2": "Speech-to-Text Real-time Preview v2",
|
|
1015
|
-
"stt-async-preview-v1": "Speech-to-Text Async Preview v1"
|
|
1013
|
+
"stt-async-preview-v1": "Speech-to-Text Async Preview v1",
|
|
1014
|
+
"stt-rt-v3": "Speech-to-Text Real-time v3",
|
|
1015
|
+
"stt-async-v3": "Speech-to-Text Async v3"
|
|
1016
1016
|
};
|
|
1017
1017
|
var SonioxModel = {
|
|
1018
1018
|
stt_rt_v4: "stt-rt-v4",
|
|
1019
|
-
stt_rt_v3: "stt-rt-v3",
|
|
1020
1019
|
stt_async_v4: "stt-async-v4",
|
|
1021
|
-
stt_async_v3: "stt-async-v3",
|
|
1022
1020
|
stt_rt_preview: "stt-rt-preview",
|
|
1023
1021
|
stt_async_preview: "stt-async-preview",
|
|
1024
1022
|
stt_rt_v3_preview: "stt-rt-v3-preview",
|
|
1025
1023
|
stt_rt_preview_v2: "stt-rt-preview-v2",
|
|
1026
|
-
stt_async_preview_v1: "stt-async-preview-v1"
|
|
1024
|
+
stt_async_preview_v1: "stt-async-preview-v1",
|
|
1025
|
+
stt_rt_v3: "stt-rt-v3",
|
|
1026
|
+
stt_async_v3: "stt-async-v3"
|
|
1027
1027
|
};
|
|
1028
1028
|
var SonioxRealtimeModel = {
|
|
1029
1029
|
stt_rt_v4: "stt-rt-v4",
|
|
1030
|
-
stt_rt_v3: "stt-rt-v3",
|
|
1031
1030
|
stt_rt_preview: "stt-rt-preview",
|
|
1032
1031
|
stt_rt_v3_preview: "stt-rt-v3-preview",
|
|
1033
|
-
stt_rt_preview_v2: "stt-rt-preview-v2"
|
|
1032
|
+
stt_rt_preview_v2: "stt-rt-preview-v2",
|
|
1033
|
+
stt_rt_v3: "stt-rt-v3"
|
|
1034
1034
|
};
|
|
1035
1035
|
var SonioxAsyncModel = {
|
|
1036
1036
|
stt_async_v4: "stt-async-v4",
|
|
1037
|
-
stt_async_v3: "stt-async-v3",
|
|
1038
1037
|
stt_async_preview: "stt-async-preview",
|
|
1039
|
-
stt_async_preview_v1: "stt-async-preview-v1"
|
|
1038
|
+
stt_async_preview_v1: "stt-async-preview-v1",
|
|
1039
|
+
stt_async_v3: "stt-async-v3"
|
|
1040
1040
|
};
|
|
1041
1041
|
|
|
1042
1042
|
// src/generated/speechmatics/languages.ts
|
|
@@ -4011,17 +4011,17 @@ var SummaryTypesEnum = {
|
|
|
4011
4011
|
concise: "concise"
|
|
4012
4012
|
};
|
|
4013
4013
|
|
|
4014
|
-
// src/generated/gladia/schema/transcriptMessageType.ts
|
|
4015
|
-
var TranscriptMessageType = {
|
|
4016
|
-
transcript: "transcript"
|
|
4017
|
-
};
|
|
4018
|
-
|
|
4019
4014
|
// src/generated/gladia/schema/transcriptionControllerListV2KindItem.ts
|
|
4020
4015
|
var TranscriptionControllerListV2KindItem = {
|
|
4021
4016
|
"pre-recorded": "pre-recorded",
|
|
4022
4017
|
live: "live"
|
|
4023
4018
|
};
|
|
4024
4019
|
|
|
4020
|
+
// src/generated/gladia/schema/transcriptMessageType.ts
|
|
4021
|
+
var TranscriptMessageType = {
|
|
4022
|
+
transcript: "transcript"
|
|
4023
|
+
};
|
|
4024
|
+
|
|
4025
4025
|
// src/generated/gladia/schema/translationMessageType.ts
|
|
4026
4026
|
var TranslationMessageType = {
|
|
4027
4027
|
translation: "translation"
|
|
@@ -4293,7 +4293,7 @@ var WebhookTranscriptionSuccessPayloadEvent = {
|
|
|
4293
4293
|
|
|
4294
4294
|
// src/generated/gladia/api/gladiaControlAPI.ts
|
|
4295
4295
|
var preRecordedControllerInitPreRecordedJobV2 = (initTranscriptionRequest, options) => {
|
|
4296
|
-
return import_axios.default.post(
|
|
4296
|
+
return import_axios.default.post("/v2/pre-recorded", initTranscriptionRequest, options);
|
|
4297
4297
|
};
|
|
4298
4298
|
var preRecordedControllerGetPreRecordedJobV2 = (id, options) => {
|
|
4299
4299
|
return import_axios.default.get(`/v2/pre-recorded/${id}`, options);
|
|
@@ -4308,13 +4308,13 @@ var preRecordedControllerGetAudioV2 = (id, options) => {
|
|
|
4308
4308
|
});
|
|
4309
4309
|
};
|
|
4310
4310
|
var transcriptionControllerListV2 = (params, options) => {
|
|
4311
|
-
return import_axios.default.get(
|
|
4311
|
+
return import_axios.default.get("/v2/transcription", {
|
|
4312
4312
|
...options,
|
|
4313
4313
|
params: { ...params, ...options?.params }
|
|
4314
4314
|
});
|
|
4315
4315
|
};
|
|
4316
4316
|
var streamingControllerInitStreamingSessionV2 = (streamingRequest, params, options) => {
|
|
4317
|
-
return import_axios.default.post(
|
|
4317
|
+
return import_axios.default.post("/v2/live", streamingRequest, {
|
|
4318
4318
|
...options,
|
|
4319
4319
|
params: { ...params, ...options?.params }
|
|
4320
4320
|
});
|
|
@@ -4580,7 +4580,6 @@ var GladiaAdapter = class extends BaseAdapter {
|
|
|
4580
4580
|
sentiment: result?.sentiment_analysis || void 0,
|
|
4581
4581
|
audioToLlm: result?.audio_to_llm || void 0,
|
|
4582
4582
|
chapters: result?.chapterization || void 0,
|
|
4583
|
-
speakerReidentification: result?.speaker_reidentification || void 0,
|
|
4584
4583
|
structuredData: result?.structured_data_extraction || void 0,
|
|
4585
4584
|
customMetadata: response.custom_metadata || void 0
|
|
4586
4585
|
},
|
|
@@ -5642,17 +5641,17 @@ var PiiPolicy = {
|
|
|
5642
5641
|
zodiac_sign: "zodiac_sign"
|
|
5643
5642
|
};
|
|
5644
5643
|
|
|
5644
|
+
// src/generated/assemblyai/schema/redactedAudioStatus.ts
|
|
5645
|
+
var RedactedAudioStatus = {
|
|
5646
|
+
redacted_audio_ready: "redacted_audio_ready"
|
|
5647
|
+
};
|
|
5648
|
+
|
|
5645
5649
|
// src/generated/assemblyai/schema/redactPiiAudioQuality.ts
|
|
5646
5650
|
var RedactPiiAudioQuality = {
|
|
5647
5651
|
mp3: "mp3",
|
|
5648
5652
|
wav: "wav"
|
|
5649
5653
|
};
|
|
5650
5654
|
|
|
5651
|
-
// src/generated/assemblyai/schema/redactedAudioStatus.ts
|
|
5652
|
-
var RedactedAudioStatus = {
|
|
5653
|
-
redacted_audio_ready: "redacted_audio_ready"
|
|
5654
|
-
};
|
|
5655
|
-
|
|
5656
5655
|
// src/generated/assemblyai/schema/sentiment.ts
|
|
5657
5656
|
var Sentiment = {
|
|
5658
5657
|
POSITIVE: "POSITIVE",
|
|
@@ -5716,10 +5715,10 @@ var TranscriptRemoveAudioTags = {
|
|
|
5716
5715
|
|
|
5717
5716
|
// src/generated/assemblyai/api/assemblyAIAPI.ts
|
|
5718
5717
|
var createTranscript = (transcriptParams, options) => {
|
|
5719
|
-
return import_axios2.default.post(
|
|
5718
|
+
return import_axios2.default.post("/v2/transcript", transcriptParams, options);
|
|
5720
5719
|
};
|
|
5721
5720
|
var listTranscripts = (params, options) => {
|
|
5722
|
-
return import_axios2.default.get(
|
|
5721
|
+
return import_axios2.default.get("/v2/transcript", {
|
|
5723
5722
|
...options,
|
|
5724
5723
|
params: { ...params, ...options?.params }
|
|
5725
5724
|
});
|
|
@@ -6129,22 +6128,22 @@ var AssemblyAIAdapter = class extends BaseAdapter {
|
|
|
6129
6128
|
normalizeResponse(response) {
|
|
6130
6129
|
let status;
|
|
6131
6130
|
switch (response.status) {
|
|
6132
|
-
case
|
|
6131
|
+
case TranscriptStatus.queued:
|
|
6133
6132
|
status = "queued";
|
|
6134
6133
|
break;
|
|
6135
|
-
case
|
|
6134
|
+
case TranscriptStatus.processing:
|
|
6136
6135
|
status = "processing";
|
|
6137
6136
|
break;
|
|
6138
|
-
case
|
|
6137
|
+
case TranscriptStatus.completed:
|
|
6139
6138
|
status = "completed";
|
|
6140
6139
|
break;
|
|
6141
|
-
case
|
|
6140
|
+
case TranscriptStatus.error:
|
|
6142
6141
|
status = "error";
|
|
6143
6142
|
break;
|
|
6144
6143
|
default:
|
|
6145
6144
|
status = "queued";
|
|
6146
6145
|
}
|
|
6147
|
-
if (response.status ===
|
|
6146
|
+
if (response.status === TranscriptStatus.error) {
|
|
6148
6147
|
return {
|
|
6149
6148
|
success: false,
|
|
6150
6149
|
provider: this.name,
|
|
@@ -7856,13 +7855,13 @@ var TextNormalizationKind = {
|
|
|
7856
7855
|
|
|
7857
7856
|
// src/generated/azure/api/speechServicesAPIVersion32.ts
|
|
7858
7857
|
var transcriptionsList = (params, options) => {
|
|
7859
|
-
return import_axios4.default.get(
|
|
7858
|
+
return import_axios4.default.get("/transcriptions", {
|
|
7860
7859
|
...options,
|
|
7861
7860
|
params: { ...params, ...options?.params }
|
|
7862
7861
|
});
|
|
7863
7862
|
};
|
|
7864
7863
|
var transcriptionsCreate = (transcription, options) => {
|
|
7865
|
-
return import_axios4.default.post(
|
|
7864
|
+
return import_axios4.default.post("/transcriptions", transcription, options);
|
|
7866
7865
|
};
|
|
7867
7866
|
var transcriptionsGet = (id, options) => {
|
|
7868
7867
|
return import_axios4.default.get(`/transcriptions/${id}`, options);
|
|
@@ -7877,13 +7876,13 @@ var transcriptionsListFiles = (id, params, options) => {
|
|
|
7877
7876
|
});
|
|
7878
7877
|
};
|
|
7879
7878
|
var webHooksList = (params, options) => {
|
|
7880
|
-
return import_axios4.default.get(
|
|
7879
|
+
return import_axios4.default.get("/webhooks", {
|
|
7881
7880
|
...options,
|
|
7882
7881
|
params: { ...params, ...options?.params }
|
|
7883
7882
|
});
|
|
7884
7883
|
};
|
|
7885
7884
|
var webHooksCreate = (webHook, options) => {
|
|
7886
|
-
return import_axios4.default.post(
|
|
7885
|
+
return import_axios4.default.post("/webhooks", webHook, options);
|
|
7887
7886
|
};
|
|
7888
7887
|
var webHooksDelete = (id, options) => {
|
|
7889
7888
|
return import_axios4.default.delete(`/webhooks/${id}`, options);
|
|
@@ -8011,7 +8010,7 @@ var AzureSTTAdapter = class extends BaseAdapter {
|
|
|
8011
8010
|
this.getAxiosConfig()
|
|
8012
8011
|
);
|
|
8013
8012
|
const files = filesResponse.data?.values || [];
|
|
8014
|
-
const resultFile = files.find((file) => file.kind ===
|
|
8013
|
+
const resultFile = files.find((file) => file.kind === FileKind.Transcription);
|
|
8015
8014
|
if (!resultFile?.links?.contentUrl) {
|
|
8016
8015
|
return {
|
|
8017
8016
|
success: false,
|
|
@@ -8235,15 +8234,20 @@ var AzureSTTAdapter = class extends BaseAdapter {
|
|
|
8235
8234
|
return properties;
|
|
8236
8235
|
}
|
|
8237
8236
|
/**
|
|
8238
|
-
* Normalize Azure status to unified status
|
|
8237
|
+
* Normalize Azure status to unified status using generated AzureStatus constants
|
|
8239
8238
|
*/
|
|
8240
8239
|
normalizeStatus(status) {
|
|
8241
|
-
|
|
8242
|
-
|
|
8243
|
-
|
|
8244
|
-
|
|
8245
|
-
|
|
8246
|
-
|
|
8240
|
+
switch (status) {
|
|
8241
|
+
case Status.Succeeded:
|
|
8242
|
+
return "completed";
|
|
8243
|
+
case Status.Running:
|
|
8244
|
+
return "processing";
|
|
8245
|
+
case Status.Failed:
|
|
8246
|
+
return "error";
|
|
8247
|
+
case Status.NotStarted:
|
|
8248
|
+
default:
|
|
8249
|
+
return "queued";
|
|
8250
|
+
}
|
|
8247
8251
|
}
|
|
8248
8252
|
/**
|
|
8249
8253
|
* Normalize Azure transcription response to unified format
|
|
@@ -8363,30 +8367,30 @@ function getAzureOpenAIRealtimeUrl(endpoint, deployment, apiVersion = "2024-10-0
|
|
|
8363
8367
|
var import_axios6 = __toESM(require("axios"));
|
|
8364
8368
|
var createTranscription = (createTranscriptionRequest, options) => {
|
|
8365
8369
|
const formData = new FormData();
|
|
8366
|
-
formData.append(
|
|
8367
|
-
formData.append(
|
|
8370
|
+
formData.append("file", createTranscriptionRequest.file);
|
|
8371
|
+
formData.append("model", createTranscriptionRequest.model);
|
|
8368
8372
|
if (createTranscriptionRequest.language !== void 0) {
|
|
8369
|
-
formData.append(
|
|
8373
|
+
formData.append("language", createTranscriptionRequest.language);
|
|
8370
8374
|
}
|
|
8371
8375
|
if (createTranscriptionRequest.prompt !== void 0) {
|
|
8372
|
-
formData.append(
|
|
8376
|
+
formData.append("prompt", createTranscriptionRequest.prompt);
|
|
8373
8377
|
}
|
|
8374
8378
|
if (createTranscriptionRequest.response_format !== void 0) {
|
|
8375
|
-
formData.append(
|
|
8379
|
+
formData.append("response_format", createTranscriptionRequest.response_format);
|
|
8376
8380
|
}
|
|
8377
8381
|
if (createTranscriptionRequest.temperature !== void 0) {
|
|
8378
|
-
formData.append(
|
|
8382
|
+
formData.append("temperature", createTranscriptionRequest.temperature.toString());
|
|
8379
8383
|
}
|
|
8380
8384
|
if (createTranscriptionRequest.include !== void 0) {
|
|
8381
|
-
createTranscriptionRequest.include.forEach((value) => formData.append(
|
|
8385
|
+
createTranscriptionRequest.include.forEach((value) => formData.append("include", value));
|
|
8382
8386
|
}
|
|
8383
8387
|
if (createTranscriptionRequest.timestamp_granularities !== void 0) {
|
|
8384
8388
|
createTranscriptionRequest.timestamp_granularities.forEach(
|
|
8385
|
-
(value) => formData.append(
|
|
8389
|
+
(value) => formData.append("timestamp_granularities", value)
|
|
8386
8390
|
);
|
|
8387
8391
|
}
|
|
8388
8392
|
if (createTranscriptionRequest.stream !== void 0 && createTranscriptionRequest.stream !== null) {
|
|
8389
|
-
formData.append(
|
|
8393
|
+
formData.append("stream", createTranscriptionRequest.stream.toString());
|
|
8390
8394
|
}
|
|
8391
8395
|
if (createTranscriptionRequest.chunking_strategy !== void 0 && createTranscriptionRequest.chunking_strategy !== null) {
|
|
8392
8396
|
formData.append(
|
|
@@ -8396,15 +8400,15 @@ var createTranscription = (createTranscriptionRequest, options) => {
|
|
|
8396
8400
|
}
|
|
8397
8401
|
if (createTranscriptionRequest.known_speaker_names !== void 0) {
|
|
8398
8402
|
createTranscriptionRequest.known_speaker_names.forEach(
|
|
8399
|
-
(value) => formData.append(
|
|
8403
|
+
(value) => formData.append("known_speaker_names", value)
|
|
8400
8404
|
);
|
|
8401
8405
|
}
|
|
8402
8406
|
if (createTranscriptionRequest.known_speaker_references !== void 0) {
|
|
8403
8407
|
createTranscriptionRequest.known_speaker_references.forEach(
|
|
8404
|
-
(value) => formData.append(
|
|
8408
|
+
(value) => formData.append("known_speaker_references", value)
|
|
8405
8409
|
);
|
|
8406
8410
|
}
|
|
8407
|
-
return import_axios6.default.post(
|
|
8411
|
+
return import_axios6.default.post("/audio/transcriptions", formData, options);
|
|
8408
8412
|
};
|
|
8409
8413
|
|
|
8410
8414
|
// src/generated/openai/schema/createTranscriptionRequestTimestampGranularitiesItem.ts
|
|
@@ -8493,7 +8497,7 @@ var OpenAIWhisperAdapter = class extends BaseAdapter {
|
|
|
8493
8497
|
const request = {
|
|
8494
8498
|
...options?.openai,
|
|
8495
8499
|
file: audioData,
|
|
8496
|
-
//
|
|
8500
|
+
// Buffer/Blob both accepted at runtime; generated type expects Blob
|
|
8497
8501
|
model
|
|
8498
8502
|
};
|
|
8499
8503
|
if (options?.language) {
|
|
@@ -8513,7 +8517,11 @@ var OpenAIWhisperAdapter = class extends BaseAdapter {
|
|
|
8513
8517
|
request.response_format = OpenAIResponseFormat.json;
|
|
8514
8518
|
}
|
|
8515
8519
|
const response = await createTranscription(request, this.getAxiosConfig());
|
|
8516
|
-
return this.normalizeResponse(
|
|
8520
|
+
return this.normalizeResponse(
|
|
8521
|
+
response.data,
|
|
8522
|
+
model,
|
|
8523
|
+
isDiarization
|
|
8524
|
+
);
|
|
8517
8525
|
} catch (error) {
|
|
8518
8526
|
return this.createErrorResponse(error);
|
|
8519
8527
|
}
|
|
@@ -9233,8 +9241,16 @@ var SpeechmaticsAdapter = class extends BaseAdapter {
|
|
|
9233
9241
|
if (this.config?.wsBaseUrl) {
|
|
9234
9242
|
return this.config.wsBaseUrl;
|
|
9235
9243
|
}
|
|
9236
|
-
const
|
|
9237
|
-
|
|
9244
|
+
const rtRegionMap = {
|
|
9245
|
+
eu1: "eu",
|
|
9246
|
+
eu2: "eu",
|
|
9247
|
+
us1: "us",
|
|
9248
|
+
us2: "us",
|
|
9249
|
+
au1: "eu"
|
|
9250
|
+
// No AU RT endpoint — fall back to EU
|
|
9251
|
+
};
|
|
9252
|
+
const rtPrefix = rtRegionMap[region || ""] || "eu";
|
|
9253
|
+
return `wss://${rtPrefix}.rt.speechmatics.com/v2`;
|
|
9238
9254
|
}
|
|
9239
9255
|
/**
|
|
9240
9256
|
* Stream audio for real-time transcription via WebSocket
|
|
@@ -9843,8 +9859,23 @@ var SonioxAdapter = class extends BaseAdapter {
|
|
|
9843
9859
|
terms: options.customVocabulary
|
|
9844
9860
|
};
|
|
9845
9861
|
}
|
|
9862
|
+
if (options?.webhookUrl) {
|
|
9863
|
+
requestBody.webhook_url = options.webhookUrl;
|
|
9864
|
+
}
|
|
9846
9865
|
const response = await this.client.post("/transcriptions", requestBody);
|
|
9847
9866
|
const transcriptionId = response.data.id;
|
|
9867
|
+
if (options?.webhookUrl) {
|
|
9868
|
+
return {
|
|
9869
|
+
success: true,
|
|
9870
|
+
provider: this.name,
|
|
9871
|
+
data: {
|
|
9872
|
+
id: transcriptionId,
|
|
9873
|
+
text: "",
|
|
9874
|
+
status: "queued"
|
|
9875
|
+
},
|
|
9876
|
+
raw: response.data
|
|
9877
|
+
};
|
|
9878
|
+
}
|
|
9848
9879
|
return await this.pollForCompletion(transcriptionId);
|
|
9849
9880
|
} catch (error) {
|
|
9850
9881
|
return this.createErrorResponse(error);
|
|
@@ -10189,7 +10220,7 @@ var SonioxAdapter = class extends BaseAdapter {
|
|
|
10189
10220
|
start: token.start_ms ? token.start_ms / 1e3 : 0,
|
|
10190
10221
|
end: token.end_ms ? token.end_ms / 1e3 : 0,
|
|
10191
10222
|
confidence: token.confidence,
|
|
10192
|
-
speaker: token.speaker
|
|
10223
|
+
speaker: token.speaker ?? void 0
|
|
10193
10224
|
}));
|
|
10194
10225
|
return buildUtterancesFromWords(words);
|
|
10195
10226
|
}
|
|
@@ -10197,29 +10228,24 @@ var SonioxAdapter = class extends BaseAdapter {
|
|
|
10197
10228
|
* Normalize Soniox response to unified format
|
|
10198
10229
|
*/
|
|
10199
10230
|
normalizeResponse(response) {
|
|
10200
|
-
const
|
|
10201
|
-
const words =
|
|
10202
|
-
(t) => t.is_final !== false && t.start_ms !== void 0 && t.end_ms !== void 0
|
|
10203
|
-
).map((token) => ({
|
|
10231
|
+
const { text, tokens } = response;
|
|
10232
|
+
const words = tokens.map((token) => ({
|
|
10204
10233
|
word: token.text,
|
|
10205
10234
|
start: token.start_ms / 1e3,
|
|
10206
10235
|
end: token.end_ms / 1e3,
|
|
10207
10236
|
confidence: token.confidence,
|
|
10208
|
-
speaker: token.speaker
|
|
10209
|
-
}))
|
|
10237
|
+
speaker: token.speaker ?? void 0
|
|
10238
|
+
}));
|
|
10210
10239
|
const speakerSet = /* @__PURE__ */ new Set();
|
|
10211
|
-
|
|
10212
|
-
|
|
10213
|
-
if (t.speaker) speakerSet.add(t.speaker);
|
|
10214
|
-
});
|
|
10240
|
+
for (const token of tokens) {
|
|
10241
|
+
if (token.speaker) speakerSet.add(token.speaker);
|
|
10215
10242
|
}
|
|
10216
10243
|
const speakers = speakerSet.size > 0 ? Array.from(speakerSet).map((id) => ({
|
|
10217
10244
|
id,
|
|
10218
10245
|
label: `Speaker ${id}`
|
|
10219
10246
|
})) : void 0;
|
|
10220
|
-
const tokens = response.tokens ? response.tokens.filter((t) => t.is_final !== false) : [];
|
|
10221
10247
|
const utterances = tokens.length > 0 ? this.buildUtterancesFromTokens(tokens) : [];
|
|
10222
|
-
const language =
|
|
10248
|
+
const language = tokens.find((t) => t.language)?.language ?? void 0;
|
|
10223
10249
|
return {
|
|
10224
10250
|
success: true,
|
|
10225
10251
|
provider: this.name,
|
|
@@ -10393,11 +10419,29 @@ var ElevenLabsAdapter = class extends BaseAdapter {
|
|
|
10393
10419
|
}
|
|
10394
10420
|
}
|
|
10395
10421
|
}
|
|
10422
|
+
if (options?.webhookUrl) {
|
|
10423
|
+
if (!formData.has("webhook")) {
|
|
10424
|
+
formData.append("webhook", "true");
|
|
10425
|
+
}
|
|
10426
|
+
}
|
|
10396
10427
|
const response = await this.client.post("/v1/speech-to-text", formData, {
|
|
10397
10428
|
headers: {
|
|
10398
10429
|
"Content-Type": "multipart/form-data"
|
|
10399
10430
|
}
|
|
10400
10431
|
});
|
|
10432
|
+
if (options?.webhookUrl) {
|
|
10433
|
+
const transcriptionId = response.data.transcription_id || response.data.id || `elevenlabs_${Date.now()}`;
|
|
10434
|
+
return {
|
|
10435
|
+
success: true,
|
|
10436
|
+
provider: this.name,
|
|
10437
|
+
data: {
|
|
10438
|
+
id: transcriptionId,
|
|
10439
|
+
text: "",
|
|
10440
|
+
status: "queued"
|
|
10441
|
+
},
|
|
10442
|
+
raw: response.data
|
|
10443
|
+
};
|
|
10444
|
+
}
|
|
10401
10445
|
return this.normalizeResponse(response.data);
|
|
10402
10446
|
} catch (error) {
|
|
10403
10447
|
return this.createErrorResponse(error);
|
|
@@ -10661,7 +10705,7 @@ var ElevenLabsAdapter = class extends BaseAdapter {
|
|
|
10661
10705
|
* - Multi-channel: `MultichannelSpeechToTextResponseModel` with `transcripts[]`
|
|
10662
10706
|
*/
|
|
10663
10707
|
normalizeResponse(response) {
|
|
10664
|
-
const chunks =
|
|
10708
|
+
const chunks = "transcripts" in response ? response.transcripts : [response];
|
|
10665
10709
|
const text = chunks.map((c) => c.text).join(" ");
|
|
10666
10710
|
const words = [];
|
|
10667
10711
|
const speakerSet = /* @__PURE__ */ new Set();
|
|
@@ -10711,7 +10755,7 @@ var ElevenLabsAdapter = class extends BaseAdapter {
|
|
|
10711
10755
|
}
|
|
10712
10756
|
}
|
|
10713
10757
|
}
|
|
10714
|
-
const transcriptionId = response.transcription_id || chunks[0]?.transcription_id || `elevenlabs_${Date.now()}`;
|
|
10758
|
+
const transcriptionId = ("transcription_id" in response ? response.transcription_id : response.transcription_id) || chunks[0]?.transcription_id || `elevenlabs_${Date.now()}`;
|
|
10715
10759
|
return {
|
|
10716
10760
|
success: true,
|
|
10717
10761
|
provider: this.name,
|
|
@@ -11055,9 +11099,7 @@ var listenTranscribeQueryParams = import_zod.z.object({
|
|
|
11055
11099
|
),
|
|
11056
11100
|
dictation: import_zod.z.boolean().optional().describe("Dictation mode for controlling formatting with dictated speech"),
|
|
11057
11101
|
encoding: import_zod.z.enum(["linear16", "flac", "mulaw", "amr-nb", "amr-wb", "opus", "speex", "g729"]).optional().describe("Specify the expected encoding of your submitted audio"),
|
|
11058
|
-
filler_words: import_zod.z.boolean().optional().describe(
|
|
11059
|
-
'Filler Words can help transcribe interruptions in your audio, like "uh" and "um"'
|
|
11060
|
-
),
|
|
11102
|
+
filler_words: import_zod.z.boolean().optional().describe('Filler Words can help transcribe interruptions in your audio, like "uh" and "um"'),
|
|
11061
11103
|
keyterm: import_zod.z.array(import_zod.z.string()).optional().describe(
|
|
11062
11104
|
"Key term prompting can boost or suppress specialized terminology and brands. Only compatible with Nova-3"
|
|
11063
11105
|
),
|
|
@@ -11761,6 +11803,7 @@ __export(assemblyAIAPI_zod_exports, {
|
|
|
11761
11803
|
createTranscriptBodySpeechUnderstandingRequestTranslationFormalDefault: () => createTranscriptBodySpeechUnderstandingRequestTranslationFormalDefault,
|
|
11762
11804
|
createTranscriptBodySpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault: () => createTranscriptBodySpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault,
|
|
11763
11805
|
createTranscriptBodySummarizationDefault: () => createTranscriptBodySummarizationDefault,
|
|
11806
|
+
createTranscriptBodyTemperatureDefault: () => createTranscriptBodyTemperatureDefault,
|
|
11764
11807
|
createTranscriptResponse: () => createTranscriptResponse,
|
|
11765
11808
|
createTranscriptResponseLanguageDetectionOptionsCodeSwitchingConfidenceThresholdDefault: () => createTranscriptResponseLanguageDetectionOptionsCodeSwitchingConfidenceThresholdDefault,
|
|
11766
11809
|
createTranscriptResponseLanguageDetectionOptionsCodeSwitchingDefault: () => createTranscriptResponseLanguageDetectionOptionsCodeSwitchingDefault,
|
|
@@ -11830,6 +11873,7 @@ var createTranscriptBodySpeakerOptionsMinSpeakersExpectedDefault = 1;
|
|
|
11830
11873
|
var createTranscriptBodySpeechUnderstandingRequestTranslationFormalDefault = true;
|
|
11831
11874
|
var createTranscriptBodySpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault = false;
|
|
11832
11875
|
var createTranscriptBodySummarizationDefault = false;
|
|
11876
|
+
var createTranscriptBodyTemperatureDefault = 0;
|
|
11833
11877
|
var createTranscriptBodyCustomTopicsDefault = false;
|
|
11834
11878
|
var createTranscriptBody = import_zod3.z.object({
|
|
11835
11879
|
audio_end_at: import_zod3.z.number().optional().describe(
|
|
@@ -11839,10 +11883,10 @@ var createTranscriptBody = import_zod3.z.object({
|
|
|
11839
11883
|
"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."
|
|
11840
11884
|
),
|
|
11841
11885
|
auto_chapters: import_zod3.z.boolean().optional().describe(
|
|
11842
|
-
"Enable [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/
|
|
11886
|
+
"Enable [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/create-summarized-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/create-summarized-chapters) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
11843
11887
|
),
|
|
11844
11888
|
auto_highlights: import_zod3.z.boolean().optional().describe(
|
|
11845
|
-
"Enable [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
11889
|
+
"Enable [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights), either true or false"
|
|
11846
11890
|
),
|
|
11847
11891
|
content_safety: import_zod3.z.boolean().optional().describe(
|
|
11848
11892
|
"Enable [Content Moderation](https://www.assemblyai.com/docs/content-moderation), can be true or false"
|
|
@@ -11858,16 +11902,16 @@ var createTranscriptBody = import_zod3.z.object({
|
|
|
11858
11902
|
"Object containing words or phrases to replace, and the word or phrase to replace with"
|
|
11859
11903
|
)
|
|
11860
11904
|
).optional().describe(
|
|
11861
|
-
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
11905
|
+
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/correct-spelling-of-terms) for more details."
|
|
11862
11906
|
),
|
|
11863
11907
|
disfluencies: import_zod3.z.boolean().optional().describe(
|
|
11864
|
-
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/filler-words), like "umm", in your media file; can be true or false'
|
|
11908
|
+
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/include-filler-words), like "umm", in your media file; can be true or false'
|
|
11865
11909
|
),
|
|
11866
11910
|
domain: import_zod3.z.string().nullish().describe(
|
|
11867
11911
|
'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'
|
|
11868
11912
|
),
|
|
11869
11913
|
entity_detection: import_zod3.z.boolean().optional().describe(
|
|
11870
|
-
"Enable [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
11914
|
+
"Enable [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/detect-entities-in-transcript), can be true or false"
|
|
11871
11915
|
),
|
|
11872
11916
|
filter_profanity: import_zod3.z.boolean().optional().describe(
|
|
11873
11917
|
"Filter profanity from the transcribed text, can be true or false. See [Profanity Filtering](https://www.assemblyai.com/docs/profanity-filtering) for more details."
|
|
@@ -11876,7 +11920,7 @@ var createTranscriptBody = import_zod3.z.object({
|
|
|
11876
11920
|
"Enable [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio), can be true or false"
|
|
11877
11921
|
),
|
|
11878
11922
|
iab_categories: import_zod3.z.boolean().optional().describe(
|
|
11879
|
-
"Enable [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
11923
|
+
"Enable [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics), can be true or false"
|
|
11880
11924
|
),
|
|
11881
11925
|
keyterms_prompt: import_zod3.z.array(import_zod3.z.string()).optional().describe(
|
|
11882
11926
|
"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"
|
|
@@ -12124,7 +12168,7 @@ var createTranscriptBody = import_zod3.z.object({
|
|
|
12124
12168
|
"Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection)."
|
|
12125
12169
|
),
|
|
12126
12170
|
multichannel: import_zod3.z.boolean().optional().describe(
|
|
12127
|
-
"Enable [Multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
12171
|
+
"Enable [Multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) transcription, can be true or false."
|
|
12128
12172
|
),
|
|
12129
12173
|
prompt: import_zod3.z.string().optional().describe(
|
|
12130
12174
|
"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"
|
|
@@ -12207,23 +12251,23 @@ var createTranscriptBody = import_zod3.z.object({
|
|
|
12207
12251
|
"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."
|
|
12208
12252
|
),
|
|
12209
12253
|
sentiment_analysis: import_zod3.z.boolean().optional().describe(
|
|
12210
|
-
"Enable [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-
|
|
12254
|
+
"Enable [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/analyze-sentiment-of-speech), can be true or false"
|
|
12211
12255
|
),
|
|
12212
12256
|
speaker_labels: import_zod3.z.boolean().optional().describe(
|
|
12213
|
-
"Enable [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
12257
|
+
"Enable [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers), can be true or false"
|
|
12214
12258
|
),
|
|
12215
12259
|
speaker_options: import_zod3.z.object({
|
|
12216
12260
|
min_speakers_expected: import_zod3.z.number().default(createTranscriptBodySpeakerOptionsMinSpeakersExpectedDefault).describe(
|
|
12217
|
-
"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/
|
|
12261
|
+
"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/label-speakers#set-a-range-of-possible-speakers) for more details."
|
|
12218
12262
|
),
|
|
12219
12263
|
max_speakers_expected: import_zod3.z.number().optional().describe(
|
|
12220
|
-
"<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/
|
|
12264
|
+
"<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/label-speakers#set-a-range-of-possible-speakers) for more details.\n"
|
|
12221
12265
|
)
|
|
12222
12266
|
}).optional().describe(
|
|
12223
|
-
"Specify options for [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
12267
|
+
"Specify options for [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#set-a-range-of-possible-speakers). Use this to set a range of possible speakers."
|
|
12224
12268
|
),
|
|
12225
12269
|
speakers_expected: import_zod3.z.number().nullish().describe(
|
|
12226
|
-
"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/
|
|
12270
|
+
"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/label-speakers#set-number-of-speakers-expected) for more details."
|
|
12227
12271
|
),
|
|
12228
12272
|
speech_models: import_zod3.z.array(
|
|
12229
12273
|
import_zod3.z.string().describe(
|
|
@@ -12299,7 +12343,7 @@ var createTranscriptBody = import_zod3.z.object({
|
|
|
12299
12343
|
"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"
|
|
12300
12344
|
),
|
|
12301
12345
|
summarization: import_zod3.z.boolean().optional().describe(
|
|
12302
|
-
"Enable [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
12346
|
+
"Enable [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts), 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/summarize-transcripts) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
12303
12347
|
),
|
|
12304
12348
|
summary_model: import_zod3.z.enum(["informative", "conversational", "catchy"]).optional().describe("The model to summarize the transcript"),
|
|
12305
12349
|
summary_type: import_zod3.z.enum(["bullets", "bullets_verbose", "gist", "headline", "paragraph"]).optional().describe("The type of summary"),
|
|
@@ -12308,6 +12352,9 @@ var createTranscriptBody = import_zod3.z.object({
|
|
|
12308
12352
|
).or(import_zod3.z.null()).optional().describe(
|
|
12309
12353
|
'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'
|
|
12310
12354
|
),
|
|
12355
|
+
temperature: import_zod3.z.number().optional().describe(
|
|
12356
|
+
"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"
|
|
12357
|
+
),
|
|
12311
12358
|
webhook_auth_header_name: import_zod3.z.string().nullish().describe(
|
|
12312
12359
|
"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"
|
|
12313
12360
|
),
|
|
@@ -12329,7 +12376,7 @@ var createTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault =
|
|
|
12329
12376
|
var createTranscriptResponseSpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault = false;
|
|
12330
12377
|
var createTranscriptResponse = import_zod3.z.object({
|
|
12331
12378
|
audio_channels: import_zod3.z.number().optional().describe(
|
|
12332
|
-
"The number of audio channels in the audio file. This is only present when [multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
12379
|
+
"The number of audio channels in the audio file. This is only present when [multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) is enabled."
|
|
12333
12380
|
),
|
|
12334
12381
|
audio_duration: import_zod3.z.number().nullish().describe("The duration of this transcript object's media file, in seconds"),
|
|
12335
12382
|
audio_end_at: import_zod3.z.number().nullish().describe(
|
|
@@ -12340,10 +12387,10 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
12340
12387
|
),
|
|
12341
12388
|
audio_url: import_zod3.z.string().describe("The URL of the media that was transcribed"),
|
|
12342
12389
|
auto_chapters: import_zod3.z.boolean().nullish().describe(
|
|
12343
|
-
"Whether [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/
|
|
12390
|
+
"Whether [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/create-summarized-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/create-summarized-chapters) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
12344
12391
|
),
|
|
12345
12392
|
auto_highlights: import_zod3.z.boolean().describe(
|
|
12346
|
-
"Whether [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
12393
|
+
"Whether [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights) is enabled, either true or false"
|
|
12347
12394
|
),
|
|
12348
12395
|
auto_highlights_result: import_zod3.z.object({
|
|
12349
12396
|
status: import_zod3.z.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -12363,9 +12410,9 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
12363
12410
|
})
|
|
12364
12411
|
).describe("A temporally-sequential array of Key Phrases")
|
|
12365
12412
|
}).describe(
|
|
12366
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
12413
|
+
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights) for more information.\n"
|
|
12367
12414
|
).or(import_zod3.z.null()).optional().describe(
|
|
12368
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
12415
|
+
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights) for more information.\n"
|
|
12369
12416
|
),
|
|
12370
12417
|
chapters: import_zod3.z.array(
|
|
12371
12418
|
import_zod3.z.object({
|
|
@@ -12378,7 +12425,7 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
12378
12425
|
end: import_zod3.z.number().describe("The starting time, in milliseconds, for the chapter")
|
|
12379
12426
|
}).describe("Chapter of the audio file")
|
|
12380
12427
|
).nullish().describe(
|
|
12381
|
-
"An array of temporally sequential chapters for the audio file. See [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/
|
|
12428
|
+
"An array of temporally sequential chapters for the audio file. See [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/create-summarized-chapters) for more information."
|
|
12382
12429
|
),
|
|
12383
12430
|
confidence: import_zod3.z.number().nullish().describe(
|
|
12384
12431
|
"The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence)"
|
|
@@ -12434,10 +12481,10 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
12434
12481
|
"Object containing words or phrases to replace, and the word or phrase to replace with"
|
|
12435
12482
|
)
|
|
12436
12483
|
).nullish().describe(
|
|
12437
|
-
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
12484
|
+
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/correct-spelling-of-terms) for more details."
|
|
12438
12485
|
),
|
|
12439
12486
|
disfluencies: import_zod3.z.boolean().nullish().describe(
|
|
12440
|
-
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/filler-words), like "umm", in your media file; can be true or false'
|
|
12487
|
+
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/include-filler-words), like "umm", in your media file; can be true or false'
|
|
12441
12488
|
),
|
|
12442
12489
|
domain: import_zod3.z.string().nullish().describe(
|
|
12443
12490
|
'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'
|
|
@@ -12499,10 +12546,10 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
12499
12546
|
)
|
|
12500
12547
|
}).describe("A detected entity")
|
|
12501
12548
|
).nullish().describe(
|
|
12502
|
-
"An array of results for the Entity Detection model, if it is enabled.\nSee [Entity detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
12549
|
+
"An array of results for the Entity Detection model, if it is enabled.\nSee [Entity detection](https://www.assemblyai.com/docs/speech-understanding/detect-entities-in-transcript) for more information.\n"
|
|
12503
12550
|
),
|
|
12504
12551
|
entity_detection: import_zod3.z.boolean().nullish().describe(
|
|
12505
|
-
"Whether [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
12552
|
+
"Whether [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/detect-entities-in-transcript) is enabled, can be true or false"
|
|
12506
12553
|
),
|
|
12507
12554
|
error: import_zod3.z.string().optional().describe("Error message of why the transcript failed"),
|
|
12508
12555
|
filter_profanity: import_zod3.z.boolean().nullish().describe(
|
|
@@ -12512,7 +12559,7 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
12512
12559
|
"Whether [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio) is enabled, either true or false"
|
|
12513
12560
|
),
|
|
12514
12561
|
iab_categories: import_zod3.z.boolean().nullish().describe(
|
|
12515
|
-
"Whether [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
12562
|
+
"Whether [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics) is enabled, can be true or false"
|
|
12516
12563
|
),
|
|
12517
12564
|
iab_categories_result: import_zod3.z.object({
|
|
12518
12565
|
status: import_zod3.z.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -12535,9 +12582,9 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
12535
12582
|
).describe("An array of results for the Topic Detection model"),
|
|
12536
12583
|
summary: import_zod3.z.record(import_zod3.z.string(), import_zod3.z.number()).describe("The overall relevance of topic to the entire audio file")
|
|
12537
12584
|
}).describe(
|
|
12538
|
-
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
12585
|
+
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics) for more information.\n"
|
|
12539
12586
|
).or(import_zod3.z.null()).optional().describe(
|
|
12540
|
-
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
12587
|
+
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics) for more information.\n"
|
|
12541
12588
|
),
|
|
12542
12589
|
id: import_zod3.z.string().uuid().describe("The unique identifier of your transcript"),
|
|
12543
12590
|
keyterms_prompt: import_zod3.z.array(import_zod3.z.string()).optional().describe(
|
|
@@ -12787,7 +12834,7 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
12787
12834
|
"Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection)."
|
|
12788
12835
|
),
|
|
12789
12836
|
multichannel: import_zod3.z.boolean().nullish().describe(
|
|
12790
|
-
"Whether [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
12837
|
+
"Whether [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) was enabled in the transcription request, either true or false"
|
|
12791
12838
|
),
|
|
12792
12839
|
prompt: import_zod3.z.string().optional().describe(
|
|
12793
12840
|
"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"
|
|
@@ -12870,7 +12917,7 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
12870
12917
|
"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."
|
|
12871
12918
|
),
|
|
12872
12919
|
sentiment_analysis: import_zod3.z.boolean().nullish().describe(
|
|
12873
|
-
"Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-
|
|
12920
|
+
"Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/analyze-sentiment-of-speech) is enabled, can be true or false"
|
|
12874
12921
|
),
|
|
12875
12922
|
sentiment_analysis_results: import_zod3.z.array(
|
|
12876
12923
|
import_zod3.z.object({
|
|
@@ -12885,17 +12932,17 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
12885
12932
|
"The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
12886
12933
|
),
|
|
12887
12934
|
speaker: import_zod3.z.string().nullable().describe(
|
|
12888
|
-
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
12935
|
+
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
12889
12936
|
)
|
|
12890
12937
|
}).describe("The result of the Sentiment Analysis model")
|
|
12891
12938
|
).nullish().describe(
|
|
12892
|
-
"An array of results for the Sentiment Analysis model, if it is enabled.\nSee [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-
|
|
12939
|
+
"An array of results for the Sentiment Analysis model, if it is enabled.\nSee [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/analyze-sentiment-of-speech) for more information.\n"
|
|
12893
12940
|
),
|
|
12894
12941
|
speaker_labels: import_zod3.z.boolean().nullish().describe(
|
|
12895
|
-
"Whether [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
12942
|
+
"Whether [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, can be true or false"
|
|
12896
12943
|
),
|
|
12897
12944
|
speakers_expected: import_zod3.z.number().nullish().describe(
|
|
12898
|
-
"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/
|
|
12945
|
+
"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/label-speakers#set-number-of-speakers-expected) for more details."
|
|
12899
12946
|
),
|
|
12900
12947
|
speech_model_used: import_zod3.z.string().optional().describe(
|
|
12901
12948
|
"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."
|
|
@@ -12998,22 +13045,25 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
12998
13045
|
"The status of your transcript. Possible values are queued, processing, completed, or error."
|
|
12999
13046
|
),
|
|
13000
13047
|
summarization: import_zod3.z.boolean().describe(
|
|
13001
|
-
"Whether [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
13048
|
+
"Whether [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) 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/summarize-transcripts) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
13002
13049
|
),
|
|
13003
13050
|
summary: import_zod3.z.string().nullish().describe(
|
|
13004
|
-
"The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
13051
|
+
"The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) 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/summarize-transcripts) for details."
|
|
13005
13052
|
),
|
|
13006
13053
|
summary_model: import_zod3.z.string().nullish().describe(
|
|
13007
|
-
"The Summarization model used to generate the summary,\nif [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
13054
|
+
"The Summarization model used to generate the summary,\nif [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts#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/summarize-transcripts) for details.\n"
|
|
13008
13055
|
),
|
|
13009
13056
|
summary_type: import_zod3.z.string().nullish().describe(
|
|
13010
|
-
"The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
13057
|
+
"The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts#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/summarize-transcripts) for details."
|
|
13011
13058
|
),
|
|
13012
13059
|
remove_audio_tags: import_zod3.z.enum(["all"]).describe(
|
|
13013
13060
|
"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"
|
|
13014
13061
|
).or(import_zod3.z.null()).optional().describe(
|
|
13015
13062
|
"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"
|
|
13016
13063
|
),
|
|
13064
|
+
temperature: import_zod3.z.number().nullish().describe(
|
|
13065
|
+
"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"
|
|
13066
|
+
),
|
|
13017
13067
|
text: import_zod3.z.string().nullish().describe("The textual transcript of your media file"),
|
|
13018
13068
|
throttled: import_zod3.z.boolean().nullish().describe(
|
|
13019
13069
|
"True while a request is throttled and false when a request is no longer throttled"
|
|
@@ -13034,7 +13084,7 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
13034
13084
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
13035
13085
|
),
|
|
13036
13086
|
speaker: import_zod3.z.string().nullable().describe(
|
|
13037
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
13087
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
13038
13088
|
)
|
|
13039
13089
|
})
|
|
13040
13090
|
).describe("The words in the utterance."),
|
|
@@ -13049,7 +13099,7 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
13049
13099
|
)
|
|
13050
13100
|
})
|
|
13051
13101
|
).nullish().describe(
|
|
13052
|
-
"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/
|
|
13102
|
+
"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/label-speakers) and [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) for more information.\n"
|
|
13053
13103
|
),
|
|
13054
13104
|
webhook_auth: import_zod3.z.boolean().describe(
|
|
13055
13105
|
"Whether [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) authentication details were provided"
|
|
@@ -13073,7 +13123,7 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
13073
13123
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
13074
13124
|
),
|
|
13075
13125
|
speaker: import_zod3.z.string().nullable().describe(
|
|
13076
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
13126
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
13077
13127
|
)
|
|
13078
13128
|
})
|
|
13079
13129
|
).nullish().describe(
|
|
@@ -13146,7 +13196,7 @@ var getTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault = tr
|
|
|
13146
13196
|
var getTranscriptResponseSpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault = false;
|
|
13147
13197
|
var getTranscriptResponse = import_zod3.z.object({
|
|
13148
13198
|
audio_channels: import_zod3.z.number().optional().describe(
|
|
13149
|
-
"The number of audio channels in the audio file. This is only present when [multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
13199
|
+
"The number of audio channels in the audio file. This is only present when [multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) is enabled."
|
|
13150
13200
|
),
|
|
13151
13201
|
audio_duration: import_zod3.z.number().nullish().describe("The duration of this transcript object's media file, in seconds"),
|
|
13152
13202
|
audio_end_at: import_zod3.z.number().nullish().describe(
|
|
@@ -13157,10 +13207,10 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13157
13207
|
),
|
|
13158
13208
|
audio_url: import_zod3.z.string().describe("The URL of the media that was transcribed"),
|
|
13159
13209
|
auto_chapters: import_zod3.z.boolean().nullish().describe(
|
|
13160
|
-
"Whether [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/
|
|
13210
|
+
"Whether [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/create-summarized-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/create-summarized-chapters) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
13161
13211
|
),
|
|
13162
13212
|
auto_highlights: import_zod3.z.boolean().describe(
|
|
13163
|
-
"Whether [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
13213
|
+
"Whether [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights) is enabled, either true or false"
|
|
13164
13214
|
),
|
|
13165
13215
|
auto_highlights_result: import_zod3.z.object({
|
|
13166
13216
|
status: import_zod3.z.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -13180,9 +13230,9 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13180
13230
|
})
|
|
13181
13231
|
).describe("A temporally-sequential array of Key Phrases")
|
|
13182
13232
|
}).describe(
|
|
13183
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
13233
|
+
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights) for more information.\n"
|
|
13184
13234
|
).or(import_zod3.z.null()).optional().describe(
|
|
13185
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
13235
|
+
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights) for more information.\n"
|
|
13186
13236
|
),
|
|
13187
13237
|
chapters: import_zod3.z.array(
|
|
13188
13238
|
import_zod3.z.object({
|
|
@@ -13195,7 +13245,7 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13195
13245
|
end: import_zod3.z.number().describe("The starting time, in milliseconds, for the chapter")
|
|
13196
13246
|
}).describe("Chapter of the audio file")
|
|
13197
13247
|
).nullish().describe(
|
|
13198
|
-
"An array of temporally sequential chapters for the audio file. See [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/
|
|
13248
|
+
"An array of temporally sequential chapters for the audio file. See [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/create-summarized-chapters) for more information."
|
|
13199
13249
|
),
|
|
13200
13250
|
confidence: import_zod3.z.number().nullish().describe(
|
|
13201
13251
|
"The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence)"
|
|
@@ -13251,10 +13301,10 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13251
13301
|
"Object containing words or phrases to replace, and the word or phrase to replace with"
|
|
13252
13302
|
)
|
|
13253
13303
|
).nullish().describe(
|
|
13254
|
-
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
13304
|
+
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/correct-spelling-of-terms) for more details."
|
|
13255
13305
|
),
|
|
13256
13306
|
disfluencies: import_zod3.z.boolean().nullish().describe(
|
|
13257
|
-
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/filler-words), like "umm", in your media file; can be true or false'
|
|
13307
|
+
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/include-filler-words), like "umm", in your media file; can be true or false'
|
|
13258
13308
|
),
|
|
13259
13309
|
domain: import_zod3.z.string().nullish().describe(
|
|
13260
13310
|
'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'
|
|
@@ -13316,10 +13366,10 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13316
13366
|
)
|
|
13317
13367
|
}).describe("A detected entity")
|
|
13318
13368
|
).nullish().describe(
|
|
13319
|
-
"An array of results for the Entity Detection model, if it is enabled.\nSee [Entity detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
13369
|
+
"An array of results for the Entity Detection model, if it is enabled.\nSee [Entity detection](https://www.assemblyai.com/docs/speech-understanding/detect-entities-in-transcript) for more information.\n"
|
|
13320
13370
|
),
|
|
13321
13371
|
entity_detection: import_zod3.z.boolean().nullish().describe(
|
|
13322
|
-
"Whether [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
13372
|
+
"Whether [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/detect-entities-in-transcript) is enabled, can be true or false"
|
|
13323
13373
|
),
|
|
13324
13374
|
error: import_zod3.z.string().optional().describe("Error message of why the transcript failed"),
|
|
13325
13375
|
filter_profanity: import_zod3.z.boolean().nullish().describe(
|
|
@@ -13329,7 +13379,7 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13329
13379
|
"Whether [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio) is enabled, either true or false"
|
|
13330
13380
|
),
|
|
13331
13381
|
iab_categories: import_zod3.z.boolean().nullish().describe(
|
|
13332
|
-
"Whether [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
13382
|
+
"Whether [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics) is enabled, can be true or false"
|
|
13333
13383
|
),
|
|
13334
13384
|
iab_categories_result: import_zod3.z.object({
|
|
13335
13385
|
status: import_zod3.z.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -13352,9 +13402,9 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13352
13402
|
).describe("An array of results for the Topic Detection model"),
|
|
13353
13403
|
summary: import_zod3.z.record(import_zod3.z.string(), import_zod3.z.number()).describe("The overall relevance of topic to the entire audio file")
|
|
13354
13404
|
}).describe(
|
|
13355
|
-
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
13405
|
+
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics) for more information.\n"
|
|
13356
13406
|
).or(import_zod3.z.null()).optional().describe(
|
|
13357
|
-
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
13407
|
+
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics) for more information.\n"
|
|
13358
13408
|
),
|
|
13359
13409
|
id: import_zod3.z.string().uuid().describe("The unique identifier of your transcript"),
|
|
13360
13410
|
keyterms_prompt: import_zod3.z.array(import_zod3.z.string()).optional().describe(
|
|
@@ -13604,7 +13654,7 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13604
13654
|
"Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection)."
|
|
13605
13655
|
),
|
|
13606
13656
|
multichannel: import_zod3.z.boolean().nullish().describe(
|
|
13607
|
-
"Whether [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
13657
|
+
"Whether [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) was enabled in the transcription request, either true or false"
|
|
13608
13658
|
),
|
|
13609
13659
|
prompt: import_zod3.z.string().optional().describe(
|
|
13610
13660
|
"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"
|
|
@@ -13687,7 +13737,7 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13687
13737
|
"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."
|
|
13688
13738
|
),
|
|
13689
13739
|
sentiment_analysis: import_zod3.z.boolean().nullish().describe(
|
|
13690
|
-
"Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-
|
|
13740
|
+
"Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/analyze-sentiment-of-speech) is enabled, can be true or false"
|
|
13691
13741
|
),
|
|
13692
13742
|
sentiment_analysis_results: import_zod3.z.array(
|
|
13693
13743
|
import_zod3.z.object({
|
|
@@ -13702,17 +13752,17 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13702
13752
|
"The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
13703
13753
|
),
|
|
13704
13754
|
speaker: import_zod3.z.string().nullable().describe(
|
|
13705
|
-
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
13755
|
+
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
13706
13756
|
)
|
|
13707
13757
|
}).describe("The result of the Sentiment Analysis model")
|
|
13708
13758
|
).nullish().describe(
|
|
13709
|
-
"An array of results for the Sentiment Analysis model, if it is enabled.\nSee [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-
|
|
13759
|
+
"An array of results for the Sentiment Analysis model, if it is enabled.\nSee [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/analyze-sentiment-of-speech) for more information.\n"
|
|
13710
13760
|
),
|
|
13711
13761
|
speaker_labels: import_zod3.z.boolean().nullish().describe(
|
|
13712
|
-
"Whether [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
13762
|
+
"Whether [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, can be true or false"
|
|
13713
13763
|
),
|
|
13714
13764
|
speakers_expected: import_zod3.z.number().nullish().describe(
|
|
13715
|
-
"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/
|
|
13765
|
+
"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/label-speakers#set-number-of-speakers-expected) for more details."
|
|
13716
13766
|
),
|
|
13717
13767
|
speech_model_used: import_zod3.z.string().optional().describe(
|
|
13718
13768
|
"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."
|
|
@@ -13815,22 +13865,25 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13815
13865
|
"The status of your transcript. Possible values are queued, processing, completed, or error."
|
|
13816
13866
|
),
|
|
13817
13867
|
summarization: import_zod3.z.boolean().describe(
|
|
13818
|
-
"Whether [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
13868
|
+
"Whether [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) 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/summarize-transcripts) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
13819
13869
|
),
|
|
13820
13870
|
summary: import_zod3.z.string().nullish().describe(
|
|
13821
|
-
"The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
13871
|
+
"The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) 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/summarize-transcripts) for details."
|
|
13822
13872
|
),
|
|
13823
13873
|
summary_model: import_zod3.z.string().nullish().describe(
|
|
13824
|
-
"The Summarization model used to generate the summary,\nif [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
13874
|
+
"The Summarization model used to generate the summary,\nif [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts#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/summarize-transcripts) for details.\n"
|
|
13825
13875
|
),
|
|
13826
13876
|
summary_type: import_zod3.z.string().nullish().describe(
|
|
13827
|
-
"The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
13877
|
+
"The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts#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/summarize-transcripts) for details."
|
|
13828
13878
|
),
|
|
13829
13879
|
remove_audio_tags: import_zod3.z.enum(["all"]).describe(
|
|
13830
13880
|
"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"
|
|
13831
13881
|
).or(import_zod3.z.null()).optional().describe(
|
|
13832
13882
|
"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"
|
|
13833
13883
|
),
|
|
13884
|
+
temperature: import_zod3.z.number().nullish().describe(
|
|
13885
|
+
"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"
|
|
13886
|
+
),
|
|
13834
13887
|
text: import_zod3.z.string().nullish().describe("The textual transcript of your media file"),
|
|
13835
13888
|
throttled: import_zod3.z.boolean().nullish().describe(
|
|
13836
13889
|
"True while a request is throttled and false when a request is no longer throttled"
|
|
@@ -13851,7 +13904,7 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13851
13904
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
13852
13905
|
),
|
|
13853
13906
|
speaker: import_zod3.z.string().nullable().describe(
|
|
13854
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
13907
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
13855
13908
|
)
|
|
13856
13909
|
})
|
|
13857
13910
|
).describe("The words in the utterance."),
|
|
@@ -13866,7 +13919,7 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13866
13919
|
)
|
|
13867
13920
|
})
|
|
13868
13921
|
).nullish().describe(
|
|
13869
|
-
"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/
|
|
13922
|
+
"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/label-speakers) and [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) for more information.\n"
|
|
13870
13923
|
),
|
|
13871
13924
|
webhook_auth: import_zod3.z.boolean().describe(
|
|
13872
13925
|
"Whether [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) authentication details were provided"
|
|
@@ -13890,7 +13943,7 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13890
13943
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
13891
13944
|
),
|
|
13892
13945
|
speaker: import_zod3.z.string().nullable().describe(
|
|
13893
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
13946
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
13894
13947
|
)
|
|
13895
13948
|
})
|
|
13896
13949
|
).nullish().describe(
|
|
@@ -13923,7 +13976,7 @@ var deleteTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault =
|
|
|
13923
13976
|
var deleteTranscriptResponseSpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault = false;
|
|
13924
13977
|
var deleteTranscriptResponse = import_zod3.z.object({
|
|
13925
13978
|
audio_channels: import_zod3.z.number().optional().describe(
|
|
13926
|
-
"The number of audio channels in the audio file. This is only present when [multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
13979
|
+
"The number of audio channels in the audio file. This is only present when [multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) is enabled."
|
|
13927
13980
|
),
|
|
13928
13981
|
audio_duration: import_zod3.z.number().nullish().describe("The duration of this transcript object's media file, in seconds"),
|
|
13929
13982
|
audio_end_at: import_zod3.z.number().nullish().describe(
|
|
@@ -13934,10 +13987,10 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
13934
13987
|
),
|
|
13935
13988
|
audio_url: import_zod3.z.string().describe("The URL of the media that was transcribed"),
|
|
13936
13989
|
auto_chapters: import_zod3.z.boolean().nullish().describe(
|
|
13937
|
-
"Whether [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/
|
|
13990
|
+
"Whether [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/create-summarized-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/create-summarized-chapters) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
13938
13991
|
),
|
|
13939
13992
|
auto_highlights: import_zod3.z.boolean().describe(
|
|
13940
|
-
"Whether [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
13993
|
+
"Whether [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights) is enabled, either true or false"
|
|
13941
13994
|
),
|
|
13942
13995
|
auto_highlights_result: import_zod3.z.object({
|
|
13943
13996
|
status: import_zod3.z.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -13957,9 +14010,9 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
13957
14010
|
})
|
|
13958
14011
|
).describe("A temporally-sequential array of Key Phrases")
|
|
13959
14012
|
}).describe(
|
|
13960
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
14013
|
+
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights) for more information.\n"
|
|
13961
14014
|
).or(import_zod3.z.null()).optional().describe(
|
|
13962
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
14015
|
+
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights) for more information.\n"
|
|
13963
14016
|
),
|
|
13964
14017
|
chapters: import_zod3.z.array(
|
|
13965
14018
|
import_zod3.z.object({
|
|
@@ -13972,7 +14025,7 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
13972
14025
|
end: import_zod3.z.number().describe("The starting time, in milliseconds, for the chapter")
|
|
13973
14026
|
}).describe("Chapter of the audio file")
|
|
13974
14027
|
).nullish().describe(
|
|
13975
|
-
"An array of temporally sequential chapters for the audio file. See [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/
|
|
14028
|
+
"An array of temporally sequential chapters for the audio file. See [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/create-summarized-chapters) for more information."
|
|
13976
14029
|
),
|
|
13977
14030
|
confidence: import_zod3.z.number().nullish().describe(
|
|
13978
14031
|
"The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence)"
|
|
@@ -14028,10 +14081,10 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
14028
14081
|
"Object containing words or phrases to replace, and the word or phrase to replace with"
|
|
14029
14082
|
)
|
|
14030
14083
|
).nullish().describe(
|
|
14031
|
-
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
14084
|
+
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/correct-spelling-of-terms) for more details."
|
|
14032
14085
|
),
|
|
14033
14086
|
disfluencies: import_zod3.z.boolean().nullish().describe(
|
|
14034
|
-
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/filler-words), like "umm", in your media file; can be true or false'
|
|
14087
|
+
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/include-filler-words), like "umm", in your media file; can be true or false'
|
|
14035
14088
|
),
|
|
14036
14089
|
domain: import_zod3.z.string().nullish().describe(
|
|
14037
14090
|
'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'
|
|
@@ -14093,10 +14146,10 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
14093
14146
|
)
|
|
14094
14147
|
}).describe("A detected entity")
|
|
14095
14148
|
).nullish().describe(
|
|
14096
|
-
"An array of results for the Entity Detection model, if it is enabled.\nSee [Entity detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
14149
|
+
"An array of results for the Entity Detection model, if it is enabled.\nSee [Entity detection](https://www.assemblyai.com/docs/speech-understanding/detect-entities-in-transcript) for more information.\n"
|
|
14097
14150
|
),
|
|
14098
14151
|
entity_detection: import_zod3.z.boolean().nullish().describe(
|
|
14099
|
-
"Whether [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
14152
|
+
"Whether [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/detect-entities-in-transcript) is enabled, can be true or false"
|
|
14100
14153
|
),
|
|
14101
14154
|
error: import_zod3.z.string().optional().describe("Error message of why the transcript failed"),
|
|
14102
14155
|
filter_profanity: import_zod3.z.boolean().nullish().describe(
|
|
@@ -14106,7 +14159,7 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
14106
14159
|
"Whether [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio) is enabled, either true or false"
|
|
14107
14160
|
),
|
|
14108
14161
|
iab_categories: import_zod3.z.boolean().nullish().describe(
|
|
14109
|
-
"Whether [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
14162
|
+
"Whether [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics) is enabled, can be true or false"
|
|
14110
14163
|
),
|
|
14111
14164
|
iab_categories_result: import_zod3.z.object({
|
|
14112
14165
|
status: import_zod3.z.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -14129,9 +14182,9 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
14129
14182
|
).describe("An array of results for the Topic Detection model"),
|
|
14130
14183
|
summary: import_zod3.z.record(import_zod3.z.string(), import_zod3.z.number()).describe("The overall relevance of topic to the entire audio file")
|
|
14131
14184
|
}).describe(
|
|
14132
|
-
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
14185
|
+
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics) for more information.\n"
|
|
14133
14186
|
).or(import_zod3.z.null()).optional().describe(
|
|
14134
|
-
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
14187
|
+
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics) for more information.\n"
|
|
14135
14188
|
),
|
|
14136
14189
|
id: import_zod3.z.string().uuid().describe("The unique identifier of your transcript"),
|
|
14137
14190
|
keyterms_prompt: import_zod3.z.array(import_zod3.z.string()).optional().describe(
|
|
@@ -14381,7 +14434,7 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
14381
14434
|
"Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection)."
|
|
14382
14435
|
),
|
|
14383
14436
|
multichannel: import_zod3.z.boolean().nullish().describe(
|
|
14384
|
-
"Whether [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
14437
|
+
"Whether [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) was enabled in the transcription request, either true or false"
|
|
14385
14438
|
),
|
|
14386
14439
|
prompt: import_zod3.z.string().optional().describe(
|
|
14387
14440
|
"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"
|
|
@@ -14464,7 +14517,7 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
14464
14517
|
"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."
|
|
14465
14518
|
),
|
|
14466
14519
|
sentiment_analysis: import_zod3.z.boolean().nullish().describe(
|
|
14467
|
-
"Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-
|
|
14520
|
+
"Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/analyze-sentiment-of-speech) is enabled, can be true or false"
|
|
14468
14521
|
),
|
|
14469
14522
|
sentiment_analysis_results: import_zod3.z.array(
|
|
14470
14523
|
import_zod3.z.object({
|
|
@@ -14479,17 +14532,17 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
14479
14532
|
"The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
14480
14533
|
),
|
|
14481
14534
|
speaker: import_zod3.z.string().nullable().describe(
|
|
14482
|
-
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
14535
|
+
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
14483
14536
|
)
|
|
14484
14537
|
}).describe("The result of the Sentiment Analysis model")
|
|
14485
14538
|
).nullish().describe(
|
|
14486
|
-
"An array of results for the Sentiment Analysis model, if it is enabled.\nSee [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-
|
|
14539
|
+
"An array of results for the Sentiment Analysis model, if it is enabled.\nSee [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/analyze-sentiment-of-speech) for more information.\n"
|
|
14487
14540
|
),
|
|
14488
14541
|
speaker_labels: import_zod3.z.boolean().nullish().describe(
|
|
14489
|
-
"Whether [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
14542
|
+
"Whether [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, can be true or false"
|
|
14490
14543
|
),
|
|
14491
14544
|
speakers_expected: import_zod3.z.number().nullish().describe(
|
|
14492
|
-
"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/
|
|
14545
|
+
"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/label-speakers#set-number-of-speakers-expected) for more details."
|
|
14493
14546
|
),
|
|
14494
14547
|
speech_model_used: import_zod3.z.string().optional().describe(
|
|
14495
14548
|
"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."
|
|
@@ -14592,22 +14645,25 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
14592
14645
|
"The status of your transcript. Possible values are queued, processing, completed, or error."
|
|
14593
14646
|
),
|
|
14594
14647
|
summarization: import_zod3.z.boolean().describe(
|
|
14595
|
-
"Whether [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
14648
|
+
"Whether [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) 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/summarize-transcripts) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
14596
14649
|
),
|
|
14597
14650
|
summary: import_zod3.z.string().nullish().describe(
|
|
14598
|
-
"The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
14651
|
+
"The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) 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/summarize-transcripts) for details."
|
|
14599
14652
|
),
|
|
14600
14653
|
summary_model: import_zod3.z.string().nullish().describe(
|
|
14601
|
-
"The Summarization model used to generate the summary,\nif [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
14654
|
+
"The Summarization model used to generate the summary,\nif [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts#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/summarize-transcripts) for details.\n"
|
|
14602
14655
|
),
|
|
14603
14656
|
summary_type: import_zod3.z.string().nullish().describe(
|
|
14604
|
-
"The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
14657
|
+
"The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts#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/summarize-transcripts) for details."
|
|
14605
14658
|
),
|
|
14606
14659
|
remove_audio_tags: import_zod3.z.enum(["all"]).describe(
|
|
14607
14660
|
"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"
|
|
14608
14661
|
).or(import_zod3.z.null()).optional().describe(
|
|
14609
14662
|
"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"
|
|
14610
14663
|
),
|
|
14664
|
+
temperature: import_zod3.z.number().nullish().describe(
|
|
14665
|
+
"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"
|
|
14666
|
+
),
|
|
14611
14667
|
text: import_zod3.z.string().nullish().describe("The textual transcript of your media file"),
|
|
14612
14668
|
throttled: import_zod3.z.boolean().nullish().describe(
|
|
14613
14669
|
"True while a request is throttled and false when a request is no longer throttled"
|
|
@@ -14628,7 +14684,7 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
14628
14684
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
14629
14685
|
),
|
|
14630
14686
|
speaker: import_zod3.z.string().nullable().describe(
|
|
14631
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
14687
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
14632
14688
|
)
|
|
14633
14689
|
})
|
|
14634
14690
|
).describe("The words in the utterance."),
|
|
@@ -14643,7 +14699,7 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
14643
14699
|
)
|
|
14644
14700
|
})
|
|
14645
14701
|
).nullish().describe(
|
|
14646
|
-
"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/
|
|
14702
|
+
"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/label-speakers) and [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) for more information.\n"
|
|
14647
14703
|
),
|
|
14648
14704
|
webhook_auth: import_zod3.z.boolean().describe(
|
|
14649
14705
|
"Whether [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) authentication details were provided"
|
|
@@ -14667,7 +14723,7 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
14667
14723
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
14668
14724
|
),
|
|
14669
14725
|
speaker: import_zod3.z.string().nullable().describe(
|
|
14670
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
14726
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
14671
14727
|
)
|
|
14672
14728
|
})
|
|
14673
14729
|
).nullish().describe(
|
|
@@ -14712,7 +14768,7 @@ var getTranscriptSentencesResponse = import_zod3.z.object({
|
|
|
14712
14768
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
14713
14769
|
),
|
|
14714
14770
|
speaker: import_zod3.z.string().nullable().describe(
|
|
14715
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
14771
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
14716
14772
|
)
|
|
14717
14773
|
})
|
|
14718
14774
|
).describe("An array of words in the sentence"),
|
|
@@ -14720,7 +14776,7 @@ var getTranscriptSentencesResponse = import_zod3.z.object({
|
|
|
14720
14776
|
"The channel of the sentence. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
14721
14777
|
),
|
|
14722
14778
|
speaker: import_zod3.z.string().nullable().describe(
|
|
14723
|
-
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
14779
|
+
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
14724
14780
|
)
|
|
14725
14781
|
})
|
|
14726
14782
|
).describe("An array of sentences in the transcript")
|
|
@@ -14748,7 +14804,7 @@ var getTranscriptParagraphsResponse = import_zod3.z.object({
|
|
|
14748
14804
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
14749
14805
|
),
|
|
14750
14806
|
speaker: import_zod3.z.string().nullable().describe(
|
|
14751
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
14807
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
14752
14808
|
)
|
|
14753
14809
|
})
|
|
14754
14810
|
).describe("An array of words in the paragraph")
|
|
@@ -17360,23 +17416,6 @@ var preRecordedControllerGetPreRecordedJobsV2Response = import_zod5.z.object({
|
|
|
17360
17416
|
}).optional().describe(
|
|
17361
17417
|
"If `name_consistency` has been enabled, Gladia will improve consistency of the names accross the transcription"
|
|
17362
17418
|
),
|
|
17363
|
-
speaker_reidentification: import_zod5.z.object({
|
|
17364
|
-
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
17365
|
-
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
17366
|
-
exec_time: import_zod5.z.number().describe("Time audio intelligence model took to complete the task"),
|
|
17367
|
-
error: import_zod5.z.object({
|
|
17368
|
-
status_code: import_zod5.z.number().describe("Status code of the addon error"),
|
|
17369
|
-
exception: import_zod5.z.string().describe("Reason of the addon error"),
|
|
17370
|
-
message: import_zod5.z.string().describe("Detailed message of the addon error")
|
|
17371
|
-
}).nullable().describe(
|
|
17372
|
-
"`null` if `success` is `true`. Contains the error details of the failed model"
|
|
17373
|
-
),
|
|
17374
|
-
results: import_zod5.z.string().describe(
|
|
17375
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
17376
|
-
)
|
|
17377
|
-
}).optional().describe(
|
|
17378
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
17379
|
-
),
|
|
17380
17419
|
structured_data_extraction: import_zod5.z.object({
|
|
17381
17420
|
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
17382
17421
|
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
@@ -18857,23 +18896,6 @@ var preRecordedControllerGetPreRecordedJobV2Response = import_zod5.z.object({
|
|
|
18857
18896
|
}).optional().describe(
|
|
18858
18897
|
"If `name_consistency` has been enabled, Gladia will improve consistency of the names accross the transcription"
|
|
18859
18898
|
),
|
|
18860
|
-
speaker_reidentification: import_zod5.z.object({
|
|
18861
|
-
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
18862
|
-
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
18863
|
-
exec_time: import_zod5.z.number().describe("Time audio intelligence model took to complete the task"),
|
|
18864
|
-
error: import_zod5.z.object({
|
|
18865
|
-
status_code: import_zod5.z.number().describe("Status code of the addon error"),
|
|
18866
|
-
exception: import_zod5.z.string().describe("Reason of the addon error"),
|
|
18867
|
-
message: import_zod5.z.string().describe("Detailed message of the addon error")
|
|
18868
|
-
}).nullable().describe(
|
|
18869
|
-
"`null` if `success` is `true`. Contains the error details of the failed model"
|
|
18870
|
-
),
|
|
18871
|
-
results: import_zod5.z.string().describe(
|
|
18872
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
18873
|
-
)
|
|
18874
|
-
}).optional().describe(
|
|
18875
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
18876
|
-
),
|
|
18877
18899
|
structured_data_extraction: import_zod5.z.object({
|
|
18878
18900
|
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
18879
18901
|
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
@@ -21011,23 +21033,6 @@ var transcriptionControllerListV2Response = import_zod5.z.object({
|
|
|
21011
21033
|
}).optional().describe(
|
|
21012
21034
|
"If `name_consistency` has been enabled, Gladia will improve consistency of the names accross the transcription"
|
|
21013
21035
|
),
|
|
21014
|
-
speaker_reidentification: import_zod5.z.object({
|
|
21015
|
-
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
21016
|
-
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
21017
|
-
exec_time: import_zod5.z.number().describe("Time audio intelligence model took to complete the task"),
|
|
21018
|
-
error: import_zod5.z.object({
|
|
21019
|
-
status_code: import_zod5.z.number().describe("Status code of the addon error"),
|
|
21020
|
-
exception: import_zod5.z.string().describe("Reason of the addon error"),
|
|
21021
|
-
message: import_zod5.z.string().describe("Detailed message of the addon error")
|
|
21022
|
-
}).nullable().describe(
|
|
21023
|
-
"`null` if `success` is `true`. Contains the error details of the failed model"
|
|
21024
|
-
),
|
|
21025
|
-
results: import_zod5.z.string().describe(
|
|
21026
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
21027
|
-
)
|
|
21028
|
-
}).optional().describe(
|
|
21029
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
21030
|
-
),
|
|
21031
21036
|
structured_data_extraction: import_zod5.z.object({
|
|
21032
21037
|
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
21033
21038
|
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
@@ -21327,11 +21332,7 @@ var transcriptionControllerListV2Response = import_zod5.z.object({
|
|
|
21327
21332
|
channels: import_zod5.z.number().min(1).max(transcriptionControllerListV2ResponseItemsItemRequestParamsChannelsMax).default(
|
|
21328
21333
|
transcriptionControllerListV2ResponseItemsItemRequestParamsChannelsDefault
|
|
21329
21334
|
).describe("The number of channels of the audio stream"),
|
|
21330
|
-
model: import_zod5.z.enum(["solaria-1"]).describe(
|
|
21331
|
-
'The model used to process the audio. "solaria-1" is used by default.'
|
|
21332
|
-
).default(transcriptionControllerListV2ResponseItemsItemRequestParamsModelDefault).describe(
|
|
21333
|
-
'The model used to process the audio. "solaria-1" is used by default.'
|
|
21334
|
-
),
|
|
21335
|
+
model: import_zod5.z.enum(["solaria-1"]).describe('The model used to process the audio. "solaria-1" is used by default.').default(transcriptionControllerListV2ResponseItemsItemRequestParamsModelDefault).describe('The model used to process the audio. "solaria-1" is used by default.'),
|
|
21335
21336
|
endpointing: import_zod5.z.number().min(transcriptionControllerListV2ResponseItemsItemRequestParamsEndpointingMin).max(transcriptionControllerListV2ResponseItemsItemRequestParamsEndpointingMax).default(
|
|
21336
21337
|
transcriptionControllerListV2ResponseItemsItemRequestParamsEndpointingDefault
|
|
21337
21338
|
).describe(
|
|
@@ -23755,23 +23756,6 @@ var transcriptionControllerGetTranscriptV2Response = import_zod5.z.discriminated
|
|
|
23755
23756
|
}).optional().describe(
|
|
23756
23757
|
"If `name_consistency` has been enabled, Gladia will improve consistency of the names accross the transcription"
|
|
23757
23758
|
),
|
|
23758
|
-
speaker_reidentification: import_zod5.z.object({
|
|
23759
|
-
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
23760
|
-
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
23761
|
-
exec_time: import_zod5.z.number().describe("Time audio intelligence model took to complete the task"),
|
|
23762
|
-
error: import_zod5.z.object({
|
|
23763
|
-
status_code: import_zod5.z.number().describe("Status code of the addon error"),
|
|
23764
|
-
exception: import_zod5.z.string().describe("Reason of the addon error"),
|
|
23765
|
-
message: import_zod5.z.string().describe("Detailed message of the addon error")
|
|
23766
|
-
}).nullable().describe(
|
|
23767
|
-
"`null` if `success` is `true`. Contains the error details of the failed model"
|
|
23768
|
-
),
|
|
23769
|
-
results: import_zod5.z.string().describe(
|
|
23770
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
23771
|
-
)
|
|
23772
|
-
}).optional().describe(
|
|
23773
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
23774
|
-
),
|
|
23775
23759
|
structured_data_extraction: import_zod5.z.object({
|
|
23776
23760
|
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
23777
23761
|
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
@@ -26937,23 +26921,6 @@ var historyControllerGetListV1Response = import_zod5.z.object({
|
|
|
26937
26921
|
}).optional().describe(
|
|
26938
26922
|
"If `name_consistency` has been enabled, Gladia will improve consistency of the names accross the transcription"
|
|
26939
26923
|
),
|
|
26940
|
-
speaker_reidentification: import_zod5.z.object({
|
|
26941
|
-
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
26942
|
-
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
26943
|
-
exec_time: import_zod5.z.number().describe("Time audio intelligence model took to complete the task"),
|
|
26944
|
-
error: import_zod5.z.object({
|
|
26945
|
-
status_code: import_zod5.z.number().describe("Status code of the addon error"),
|
|
26946
|
-
exception: import_zod5.z.string().describe("Reason of the addon error"),
|
|
26947
|
-
message: import_zod5.z.string().describe("Detailed message of the addon error")
|
|
26948
|
-
}).nullable().describe(
|
|
26949
|
-
"`null` if `success` is `true`. Contains the error details of the failed model"
|
|
26950
|
-
),
|
|
26951
|
-
results: import_zod5.z.string().describe(
|
|
26952
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
26953
|
-
)
|
|
26954
|
-
}).optional().describe(
|
|
26955
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
26956
|
-
),
|
|
26957
26924
|
structured_data_extraction: import_zod5.z.object({
|
|
26958
26925
|
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
26959
26926
|
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
@@ -27247,11 +27214,7 @@ var historyControllerGetListV1Response = import_zod5.z.object({
|
|
|
27247
27214
|
historyControllerGetListV1ResponseItemsItemRequestParamsSampleRateDefault
|
|
27248
27215
|
).describe("The sample rate of the audio stream"),
|
|
27249
27216
|
channels: import_zod5.z.number().min(1).max(historyControllerGetListV1ResponseItemsItemRequestParamsChannelsMax).default(historyControllerGetListV1ResponseItemsItemRequestParamsChannelsDefault).describe("The number of channels of the audio stream"),
|
|
27250
|
-
model: import_zod5.z.enum(["solaria-1"]).describe(
|
|
27251
|
-
'The model used to process the audio. "solaria-1" is used by default.'
|
|
27252
|
-
).default(historyControllerGetListV1ResponseItemsItemRequestParamsModelDefault).describe(
|
|
27253
|
-
'The model used to process the audio. "solaria-1" is used by default.'
|
|
27254
|
-
),
|
|
27217
|
+
model: import_zod5.z.enum(["solaria-1"]).describe('The model used to process the audio. "solaria-1" is used by default.').default(historyControllerGetListV1ResponseItemsItemRequestParamsModelDefault).describe('The model used to process the audio. "solaria-1" is used by default.'),
|
|
27255
27218
|
endpointing: import_zod5.z.number().min(historyControllerGetListV1ResponseItemsItemRequestParamsEndpointingMin).max(historyControllerGetListV1ResponseItemsItemRequestParamsEndpointingMax).default(
|
|
27256
27219
|
historyControllerGetListV1ResponseItemsItemRequestParamsEndpointingDefault
|
|
27257
27220
|
).describe(
|
|
@@ -36412,6 +36375,7 @@ __export(sonioxPublicAPI_zod_exports, {
|
|
|
36412
36375
|
createTemporaryApiKeyBody: () => createTemporaryApiKeyBody,
|
|
36413
36376
|
createTemporaryApiKeyBodyClientReferenceIdMaxOne: () => createTemporaryApiKeyBodyClientReferenceIdMaxOne,
|
|
36414
36377
|
createTemporaryApiKeyBodyExpiresInSecondsMax: () => createTemporaryApiKeyBodyExpiresInSecondsMax,
|
|
36378
|
+
createTemporaryApiKeyBodyMaxSessionDurationSecondsMaxOne: () => createTemporaryApiKeyBodyMaxSessionDurationSecondsMaxOne,
|
|
36415
36379
|
createTranscriptionBody: () => createTranscriptionBody2,
|
|
36416
36380
|
createTranscriptionBodyAudioUrlMaxOne: () => createTranscriptionBodyAudioUrlMaxOne,
|
|
36417
36381
|
createTranscriptionBodyAudioUrlRegExpOne: () => createTranscriptionBodyAudioUrlRegExpOne,
|
|
@@ -36542,11 +36506,11 @@ var getTranscriptionsResponse = import_zod10.z.object({
|
|
|
36542
36506
|
});
|
|
36543
36507
|
var createTranscriptionBodyModelMaxThree = 32;
|
|
36544
36508
|
var createTranscriptionBodyAudioUrlMaxOne = 4096;
|
|
36545
|
-
var createTranscriptionBodyAudioUrlRegExpOne =
|
|
36509
|
+
var createTranscriptionBodyAudioUrlRegExpOne = /^https?:\/\/[^\s]+$/;
|
|
36546
36510
|
var createTranscriptionBodyLanguageHintsItemMax = 10;
|
|
36547
36511
|
var createTranscriptionBodyLanguageHintsMaxOne = 100;
|
|
36548
36512
|
var createTranscriptionBodyWebhookUrlMaxOne = 256;
|
|
36549
|
-
var createTranscriptionBodyWebhookUrlRegExpOne =
|
|
36513
|
+
var createTranscriptionBodyWebhookUrlRegExpOne = /^https?:\/\/[^\s]+$/;
|
|
36550
36514
|
var createTranscriptionBodyWebhookAuthHeaderNameMaxOne = 256;
|
|
36551
36515
|
var createTranscriptionBodyWebhookAuthHeaderValueMaxOne = 256;
|
|
36552
36516
|
var createTranscriptionBodyClientReferenceIdMaxOne = 256;
|
|
@@ -36694,10 +36658,15 @@ var getModelsResponse = import_zod10.z.object({
|
|
|
36694
36658
|
});
|
|
36695
36659
|
var createTemporaryApiKeyBodyExpiresInSecondsMax = 3600;
|
|
36696
36660
|
var createTemporaryApiKeyBodyClientReferenceIdMaxOne = 256;
|
|
36661
|
+
var createTemporaryApiKeyBodyMaxSessionDurationSecondsMaxOne = 18e3;
|
|
36697
36662
|
var createTemporaryApiKeyBody = import_zod10.z.object({
|
|
36698
36663
|
usage_type: import_zod10.z.enum(["transcribe_websocket"]),
|
|
36699
36664
|
expires_in_seconds: import_zod10.z.number().min(1).max(createTemporaryApiKeyBodyExpiresInSecondsMax).describe("Duration in seconds until the temporary API key expires."),
|
|
36700
|
-
client_reference_id: import_zod10.z.string().max(createTemporaryApiKeyBodyClientReferenceIdMaxOne).or(import_zod10.z.null()).optional().describe("Optional tracking identifier string. Does not need to be unique.")
|
|
36665
|
+
client_reference_id: import_zod10.z.string().max(createTemporaryApiKeyBodyClientReferenceIdMaxOne).or(import_zod10.z.null()).optional().describe("Optional tracking identifier string. Does not need to be unique."),
|
|
36666
|
+
single_use: import_zod10.z.boolean().or(import_zod10.z.null()).optional().describe("If true, the temporary API key can be used only once."),
|
|
36667
|
+
max_session_duration_seconds: import_zod10.z.number().min(1).max(createTemporaryApiKeyBodyMaxSessionDurationSecondsMaxOne).or(import_zod10.z.null()).optional().describe(
|
|
36668
|
+
"Maximum WebSocket connection duration in seconds. If exceeded, the connection will be dropped. If not set, no limit is applied."
|
|
36669
|
+
)
|
|
36701
36670
|
});
|
|
36702
36671
|
|
|
36703
36672
|
// src/generated/soniox/streaming-types.zod.ts
|
|
@@ -37948,6 +37917,16 @@ var ToolChoiceOptions = {
|
|
|
37948
37917
|
required: "required"
|
|
37949
37918
|
};
|
|
37950
37919
|
|
|
37920
|
+
// src/generated/openai/schema/transcriptionDiarizedSegmentType.ts
|
|
37921
|
+
var TranscriptionDiarizedSegmentType = {
|
|
37922
|
+
transcripttextsegment: "transcript.text.segment"
|
|
37923
|
+
};
|
|
37924
|
+
|
|
37925
|
+
// src/generated/openai/schema/transcriptionInclude.ts
|
|
37926
|
+
var TranscriptionInclude = {
|
|
37927
|
+
logprobs: "logprobs"
|
|
37928
|
+
};
|
|
37929
|
+
|
|
37951
37930
|
// src/generated/openai/schema/transcriptTextDeltaEventType.ts
|
|
37952
37931
|
var TranscriptTextDeltaEventType = {
|
|
37953
37932
|
transcripttextdelta: "transcript.text.delta"
|
|
@@ -37973,16 +37952,6 @@ var TranscriptTextUsageTokensType = {
|
|
|
37973
37952
|
tokens: "tokens"
|
|
37974
37953
|
};
|
|
37975
37954
|
|
|
37976
|
-
// src/generated/openai/schema/transcriptionDiarizedSegmentType.ts
|
|
37977
|
-
var TranscriptionDiarizedSegmentType = {
|
|
37978
|
-
transcripttextsegment: "transcript.text.segment"
|
|
37979
|
-
};
|
|
37980
|
-
|
|
37981
|
-
// src/generated/openai/schema/transcriptionInclude.ts
|
|
37982
|
-
var TranscriptionInclude = {
|
|
37983
|
-
logprobs: "logprobs"
|
|
37984
|
-
};
|
|
37985
|
-
|
|
37986
37955
|
// src/generated/openai/schema/vadConfigType.ts
|
|
37987
37956
|
var VadConfigType = {
|
|
37988
37957
|
server_vad: "server_vad"
|
|
@@ -38364,8 +38333,8 @@ var getJobsQueryParams = import_zod12.z.object({
|
|
|
38364
38333
|
var getJobsResponseJobsItemDurationMin = 0;
|
|
38365
38334
|
var getJobsResponseJobsItemConfigTranscriptionConfigPunctuationOverridesSensitivityMin = 0;
|
|
38366
38335
|
var getJobsResponseJobsItemConfigTranscriptionConfigPunctuationOverridesSensitivityMax = 1;
|
|
38367
|
-
var getJobsResponseJobsItemConfigTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp =
|
|
38368
|
-
var getJobsResponseJobsItemConfigTranscriptionConfigChannelDiarizationLabelsItemRegExp =
|
|
38336
|
+
var getJobsResponseJobsItemConfigTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp = /^(.|all)$/;
|
|
38337
|
+
var getJobsResponseJobsItemConfigTranscriptionConfigChannelDiarizationLabelsItemRegExp = /^[A-Za-z0-9._]+$/;
|
|
38369
38338
|
var getJobsResponseJobsItemConfigTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMin = 0;
|
|
38370
38339
|
var getJobsResponseJobsItemConfigTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMax = 1;
|
|
38371
38340
|
var getJobsResponseJobsItemConfigTranslationConfigTargetLanguagesMax = 5;
|
|
@@ -38563,8 +38532,8 @@ var getJobsJobidParams = import_zod12.z.object({
|
|
|
38563
38532
|
var getJobsJobidResponseJobDurationMin = 0;
|
|
38564
38533
|
var getJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesSensitivityMin = 0;
|
|
38565
38534
|
var getJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesSensitivityMax = 1;
|
|
38566
|
-
var getJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp =
|
|
38567
|
-
var getJobsJobidResponseJobConfigTranscriptionConfigChannelDiarizationLabelsItemRegExp =
|
|
38535
|
+
var getJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp = /^(.|all)$/;
|
|
38536
|
+
var getJobsJobidResponseJobConfigTranscriptionConfigChannelDiarizationLabelsItemRegExp = /^[A-Za-z0-9._]+$/;
|
|
38568
38537
|
var getJobsJobidResponseJobConfigTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMin = 0;
|
|
38569
38538
|
var getJobsJobidResponseJobConfigTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMax = 1;
|
|
38570
38539
|
var getJobsJobidResponseJobConfigTranslationConfigTargetLanguagesMax = 5;
|
|
@@ -38761,8 +38730,8 @@ var deleteJobsJobidQueryParams = import_zod12.z.object({
|
|
|
38761
38730
|
var deleteJobsJobidResponseJobDurationMin = 0;
|
|
38762
38731
|
var deleteJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesSensitivityMin = 0;
|
|
38763
38732
|
var deleteJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesSensitivityMax = 1;
|
|
38764
|
-
var deleteJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp =
|
|
38765
|
-
var deleteJobsJobidResponseJobConfigTranscriptionConfigChannelDiarizationLabelsItemRegExp =
|
|
38733
|
+
var deleteJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp = /^(.|all)$/;
|
|
38734
|
+
var deleteJobsJobidResponseJobConfigTranscriptionConfigChannelDiarizationLabelsItemRegExp = /^[A-Za-z0-9._]+$/;
|
|
38766
38735
|
var deleteJobsJobidResponseJobConfigTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMin = 0;
|
|
38767
38736
|
var deleteJobsJobidResponseJobConfigTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMax = 1;
|
|
38768
38737
|
var deleteJobsJobidResponseJobConfigTranslationConfigTargetLanguagesMax = 5;
|
|
@@ -38965,8 +38934,8 @@ var getJobsJobidTranscriptQueryParams = import_zod12.z.object({
|
|
|
38965
38934
|
var getJobsJobidTranscriptResponseJobDurationMin = 0;
|
|
38966
38935
|
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigPunctuationOverridesSensitivityMin = 0;
|
|
38967
38936
|
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigPunctuationOverridesSensitivityMax = 1;
|
|
38968
|
-
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp =
|
|
38969
|
-
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigChannelDiarizationLabelsItemRegExp =
|
|
38937
|
+
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp = /^(.|all)$/;
|
|
38938
|
+
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigChannelDiarizationLabelsItemRegExp = /^[A-Za-z0-9._]+$/;
|
|
38970
38939
|
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMin = 0;
|
|
38971
38940
|
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMax = 1;
|
|
38972
38941
|
var getJobsJobidTranscriptResponseResultsItemVolumeMin = 0;
|