voice-router-dev 0.8.9 → 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 +22 -20
- package/dist/constants.d.ts +22 -20
- package/dist/constants.js +24 -24
- package/dist/constants.mjs +24 -24
- package/dist/{field-configs-CSOt3yc9.d.mts → field-configs-DYiUtRUz.d.mts} +50 -505
- package/dist/{field-configs-CSOt3yc9.d.ts → field-configs-DYiUtRUz.d.ts} +50 -505
- 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 +1655 -1754
- package/dist/index.d.ts +1655 -1754
- package/dist/index.js +257 -296
- package/dist/index.mjs +257 -296
- 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
|
}
|
|
@@ -9851,8 +9859,23 @@ var SonioxAdapter = class extends BaseAdapter {
|
|
|
9851
9859
|
terms: options.customVocabulary
|
|
9852
9860
|
};
|
|
9853
9861
|
}
|
|
9862
|
+
if (options?.webhookUrl) {
|
|
9863
|
+
requestBody.webhook_url = options.webhookUrl;
|
|
9864
|
+
}
|
|
9854
9865
|
const response = await this.client.post("/transcriptions", requestBody);
|
|
9855
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
|
+
}
|
|
9856
9879
|
return await this.pollForCompletion(transcriptionId);
|
|
9857
9880
|
} catch (error) {
|
|
9858
9881
|
return this.createErrorResponse(error);
|
|
@@ -10197,7 +10220,7 @@ var SonioxAdapter = class extends BaseAdapter {
|
|
|
10197
10220
|
start: token.start_ms ? token.start_ms / 1e3 : 0,
|
|
10198
10221
|
end: token.end_ms ? token.end_ms / 1e3 : 0,
|
|
10199
10222
|
confidence: token.confidence,
|
|
10200
|
-
speaker: token.speaker
|
|
10223
|
+
speaker: token.speaker ?? void 0
|
|
10201
10224
|
}));
|
|
10202
10225
|
return buildUtterancesFromWords(words);
|
|
10203
10226
|
}
|
|
@@ -10205,29 +10228,24 @@ var SonioxAdapter = class extends BaseAdapter {
|
|
|
10205
10228
|
* Normalize Soniox response to unified format
|
|
10206
10229
|
*/
|
|
10207
10230
|
normalizeResponse(response) {
|
|
10208
|
-
const
|
|
10209
|
-
const words =
|
|
10210
|
-
(t) => t.is_final !== false && t.start_ms !== void 0 && t.end_ms !== void 0
|
|
10211
|
-
).map((token) => ({
|
|
10231
|
+
const { text, tokens } = response;
|
|
10232
|
+
const words = tokens.map((token) => ({
|
|
10212
10233
|
word: token.text,
|
|
10213
10234
|
start: token.start_ms / 1e3,
|
|
10214
10235
|
end: token.end_ms / 1e3,
|
|
10215
10236
|
confidence: token.confidence,
|
|
10216
|
-
speaker: token.speaker
|
|
10217
|
-
}))
|
|
10237
|
+
speaker: token.speaker ?? void 0
|
|
10238
|
+
}));
|
|
10218
10239
|
const speakerSet = /* @__PURE__ */ new Set();
|
|
10219
|
-
|
|
10220
|
-
|
|
10221
|
-
if (t.speaker) speakerSet.add(t.speaker);
|
|
10222
|
-
});
|
|
10240
|
+
for (const token of tokens) {
|
|
10241
|
+
if (token.speaker) speakerSet.add(token.speaker);
|
|
10223
10242
|
}
|
|
10224
10243
|
const speakers = speakerSet.size > 0 ? Array.from(speakerSet).map((id) => ({
|
|
10225
10244
|
id,
|
|
10226
10245
|
label: `Speaker ${id}`
|
|
10227
10246
|
})) : void 0;
|
|
10228
|
-
const tokens = response.tokens ? response.tokens.filter((t) => t.is_final !== false) : [];
|
|
10229
10247
|
const utterances = tokens.length > 0 ? this.buildUtterancesFromTokens(tokens) : [];
|
|
10230
|
-
const language =
|
|
10248
|
+
const language = tokens.find((t) => t.language)?.language ?? void 0;
|
|
10231
10249
|
return {
|
|
10232
10250
|
success: true,
|
|
10233
10251
|
provider: this.name,
|
|
@@ -10401,11 +10419,29 @@ var ElevenLabsAdapter = class extends BaseAdapter {
|
|
|
10401
10419
|
}
|
|
10402
10420
|
}
|
|
10403
10421
|
}
|
|
10422
|
+
if (options?.webhookUrl) {
|
|
10423
|
+
if (!formData.has("webhook")) {
|
|
10424
|
+
formData.append("webhook", "true");
|
|
10425
|
+
}
|
|
10426
|
+
}
|
|
10404
10427
|
const response = await this.client.post("/v1/speech-to-text", formData, {
|
|
10405
10428
|
headers: {
|
|
10406
10429
|
"Content-Type": "multipart/form-data"
|
|
10407
10430
|
}
|
|
10408
10431
|
});
|
|
10432
|
+
if (options?.webhookUrl) {
|
|
10433
|
+
const transcriptionId = response.data.transcription_id || response.data.id || `elevenlabs_${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
|
+
}
|
|
10409
10445
|
return this.normalizeResponse(response.data);
|
|
10410
10446
|
} catch (error) {
|
|
10411
10447
|
return this.createErrorResponse(error);
|
|
@@ -10669,7 +10705,7 @@ var ElevenLabsAdapter = class extends BaseAdapter {
|
|
|
10669
10705
|
* - Multi-channel: `MultichannelSpeechToTextResponseModel` with `transcripts[]`
|
|
10670
10706
|
*/
|
|
10671
10707
|
normalizeResponse(response) {
|
|
10672
|
-
const chunks =
|
|
10708
|
+
const chunks = "transcripts" in response ? response.transcripts : [response];
|
|
10673
10709
|
const text = chunks.map((c) => c.text).join(" ");
|
|
10674
10710
|
const words = [];
|
|
10675
10711
|
const speakerSet = /* @__PURE__ */ new Set();
|
|
@@ -10719,7 +10755,7 @@ var ElevenLabsAdapter = class extends BaseAdapter {
|
|
|
10719
10755
|
}
|
|
10720
10756
|
}
|
|
10721
10757
|
}
|
|
10722
|
-
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()}`;
|
|
10723
10759
|
return {
|
|
10724
10760
|
success: true,
|
|
10725
10761
|
provider: this.name,
|
|
@@ -11063,9 +11099,7 @@ var listenTranscribeQueryParams = import_zod.z.object({
|
|
|
11063
11099
|
),
|
|
11064
11100
|
dictation: import_zod.z.boolean().optional().describe("Dictation mode for controlling formatting with dictated speech"),
|
|
11065
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"),
|
|
11066
|
-
filler_words: import_zod.z.boolean().optional().describe(
|
|
11067
|
-
'Filler Words can help transcribe interruptions in your audio, like "uh" and "um"'
|
|
11068
|
-
),
|
|
11102
|
+
filler_words: import_zod.z.boolean().optional().describe('Filler Words can help transcribe interruptions in your audio, like "uh" and "um"'),
|
|
11069
11103
|
keyterm: import_zod.z.array(import_zod.z.string()).optional().describe(
|
|
11070
11104
|
"Key term prompting can boost or suppress specialized terminology and brands. Only compatible with Nova-3"
|
|
11071
11105
|
),
|
|
@@ -11769,6 +11803,7 @@ __export(assemblyAIAPI_zod_exports, {
|
|
|
11769
11803
|
createTranscriptBodySpeechUnderstandingRequestTranslationFormalDefault: () => createTranscriptBodySpeechUnderstandingRequestTranslationFormalDefault,
|
|
11770
11804
|
createTranscriptBodySpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault: () => createTranscriptBodySpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault,
|
|
11771
11805
|
createTranscriptBodySummarizationDefault: () => createTranscriptBodySummarizationDefault,
|
|
11806
|
+
createTranscriptBodyTemperatureDefault: () => createTranscriptBodyTemperatureDefault,
|
|
11772
11807
|
createTranscriptResponse: () => createTranscriptResponse,
|
|
11773
11808
|
createTranscriptResponseLanguageDetectionOptionsCodeSwitchingConfidenceThresholdDefault: () => createTranscriptResponseLanguageDetectionOptionsCodeSwitchingConfidenceThresholdDefault,
|
|
11774
11809
|
createTranscriptResponseLanguageDetectionOptionsCodeSwitchingDefault: () => createTranscriptResponseLanguageDetectionOptionsCodeSwitchingDefault,
|
|
@@ -11838,6 +11873,7 @@ var createTranscriptBodySpeakerOptionsMinSpeakersExpectedDefault = 1;
|
|
|
11838
11873
|
var createTranscriptBodySpeechUnderstandingRequestTranslationFormalDefault = true;
|
|
11839
11874
|
var createTranscriptBodySpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault = false;
|
|
11840
11875
|
var createTranscriptBodySummarizationDefault = false;
|
|
11876
|
+
var createTranscriptBodyTemperatureDefault = 0;
|
|
11841
11877
|
var createTranscriptBodyCustomTopicsDefault = false;
|
|
11842
11878
|
var createTranscriptBody = import_zod3.z.object({
|
|
11843
11879
|
audio_end_at: import_zod3.z.number().optional().describe(
|
|
@@ -11847,10 +11883,10 @@ var createTranscriptBody = import_zod3.z.object({
|
|
|
11847
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."
|
|
11848
11884
|
),
|
|
11849
11885
|
auto_chapters: import_zod3.z.boolean().optional().describe(
|
|
11850
|
-
"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"
|
|
11851
11887
|
),
|
|
11852
11888
|
auto_highlights: import_zod3.z.boolean().optional().describe(
|
|
11853
|
-
"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"
|
|
11854
11890
|
),
|
|
11855
11891
|
content_safety: import_zod3.z.boolean().optional().describe(
|
|
11856
11892
|
"Enable [Content Moderation](https://www.assemblyai.com/docs/content-moderation), can be true or false"
|
|
@@ -11866,16 +11902,16 @@ var createTranscriptBody = import_zod3.z.object({
|
|
|
11866
11902
|
"Object containing words or phrases to replace, and the word or phrase to replace with"
|
|
11867
11903
|
)
|
|
11868
11904
|
).optional().describe(
|
|
11869
|
-
"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."
|
|
11870
11906
|
),
|
|
11871
11907
|
disfluencies: import_zod3.z.boolean().optional().describe(
|
|
11872
|
-
'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'
|
|
11873
11909
|
),
|
|
11874
11910
|
domain: import_zod3.z.string().nullish().describe(
|
|
11875
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'
|
|
11876
11912
|
),
|
|
11877
11913
|
entity_detection: import_zod3.z.boolean().optional().describe(
|
|
11878
|
-
"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"
|
|
11879
11915
|
),
|
|
11880
11916
|
filter_profanity: import_zod3.z.boolean().optional().describe(
|
|
11881
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."
|
|
@@ -11884,7 +11920,7 @@ var createTranscriptBody = import_zod3.z.object({
|
|
|
11884
11920
|
"Enable [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio), can be true or false"
|
|
11885
11921
|
),
|
|
11886
11922
|
iab_categories: import_zod3.z.boolean().optional().describe(
|
|
11887
|
-
"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"
|
|
11888
11924
|
),
|
|
11889
11925
|
keyterms_prompt: import_zod3.z.array(import_zod3.z.string()).optional().describe(
|
|
11890
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"
|
|
@@ -12132,7 +12168,7 @@ var createTranscriptBody = import_zod3.z.object({
|
|
|
12132
12168
|
"Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection)."
|
|
12133
12169
|
),
|
|
12134
12170
|
multichannel: import_zod3.z.boolean().optional().describe(
|
|
12135
|
-
"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."
|
|
12136
12172
|
),
|
|
12137
12173
|
prompt: import_zod3.z.string().optional().describe(
|
|
12138
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"
|
|
@@ -12215,23 +12251,23 @@ var createTranscriptBody = import_zod3.z.object({
|
|
|
12215
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."
|
|
12216
12252
|
),
|
|
12217
12253
|
sentiment_analysis: import_zod3.z.boolean().optional().describe(
|
|
12218
|
-
"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"
|
|
12219
12255
|
),
|
|
12220
12256
|
speaker_labels: import_zod3.z.boolean().optional().describe(
|
|
12221
|
-
"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"
|
|
12222
12258
|
),
|
|
12223
12259
|
speaker_options: import_zod3.z.object({
|
|
12224
12260
|
min_speakers_expected: import_zod3.z.number().default(createTranscriptBodySpeakerOptionsMinSpeakersExpectedDefault).describe(
|
|
12225
|
-
"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."
|
|
12226
12262
|
),
|
|
12227
12263
|
max_speakers_expected: import_zod3.z.number().optional().describe(
|
|
12228
|
-
"<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"
|
|
12229
12265
|
)
|
|
12230
12266
|
}).optional().describe(
|
|
12231
|
-
"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."
|
|
12232
12268
|
),
|
|
12233
12269
|
speakers_expected: import_zod3.z.number().nullish().describe(
|
|
12234
|
-
"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."
|
|
12235
12271
|
),
|
|
12236
12272
|
speech_models: import_zod3.z.array(
|
|
12237
12273
|
import_zod3.z.string().describe(
|
|
@@ -12307,7 +12343,7 @@ var createTranscriptBody = import_zod3.z.object({
|
|
|
12307
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"
|
|
12308
12344
|
),
|
|
12309
12345
|
summarization: import_zod3.z.boolean().optional().describe(
|
|
12310
|
-
"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"
|
|
12311
12347
|
),
|
|
12312
12348
|
summary_model: import_zod3.z.enum(["informative", "conversational", "catchy"]).optional().describe("The model to summarize the transcript"),
|
|
12313
12349
|
summary_type: import_zod3.z.enum(["bullets", "bullets_verbose", "gist", "headline", "paragraph"]).optional().describe("The type of summary"),
|
|
@@ -12316,6 +12352,9 @@ var createTranscriptBody = import_zod3.z.object({
|
|
|
12316
12352
|
).or(import_zod3.z.null()).optional().describe(
|
|
12317
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'
|
|
12318
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
|
+
),
|
|
12319
12358
|
webhook_auth_header_name: import_zod3.z.string().nullish().describe(
|
|
12320
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"
|
|
12321
12360
|
),
|
|
@@ -12337,7 +12376,7 @@ var createTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault =
|
|
|
12337
12376
|
var createTranscriptResponseSpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault = false;
|
|
12338
12377
|
var createTranscriptResponse = import_zod3.z.object({
|
|
12339
12378
|
audio_channels: import_zod3.z.number().optional().describe(
|
|
12340
|
-
"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."
|
|
12341
12380
|
),
|
|
12342
12381
|
audio_duration: import_zod3.z.number().nullish().describe("The duration of this transcript object's media file, in seconds"),
|
|
12343
12382
|
audio_end_at: import_zod3.z.number().nullish().describe(
|
|
@@ -12348,10 +12387,10 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
12348
12387
|
),
|
|
12349
12388
|
audio_url: import_zod3.z.string().describe("The URL of the media that was transcribed"),
|
|
12350
12389
|
auto_chapters: import_zod3.z.boolean().nullish().describe(
|
|
12351
|
-
"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"
|
|
12352
12391
|
),
|
|
12353
12392
|
auto_highlights: import_zod3.z.boolean().describe(
|
|
12354
|
-
"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"
|
|
12355
12394
|
),
|
|
12356
12395
|
auto_highlights_result: import_zod3.z.object({
|
|
12357
12396
|
status: import_zod3.z.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -12371,9 +12410,9 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
12371
12410
|
})
|
|
12372
12411
|
).describe("A temporally-sequential array of Key Phrases")
|
|
12373
12412
|
}).describe(
|
|
12374
|
-
"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"
|
|
12375
12414
|
).or(import_zod3.z.null()).optional().describe(
|
|
12376
|
-
"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"
|
|
12377
12416
|
),
|
|
12378
12417
|
chapters: import_zod3.z.array(
|
|
12379
12418
|
import_zod3.z.object({
|
|
@@ -12386,7 +12425,7 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
12386
12425
|
end: import_zod3.z.number().describe("The starting time, in milliseconds, for the chapter")
|
|
12387
12426
|
}).describe("Chapter of the audio file")
|
|
12388
12427
|
).nullish().describe(
|
|
12389
|
-
"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."
|
|
12390
12429
|
),
|
|
12391
12430
|
confidence: import_zod3.z.number().nullish().describe(
|
|
12392
12431
|
"The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence)"
|
|
@@ -12442,10 +12481,10 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
12442
12481
|
"Object containing words or phrases to replace, and the word or phrase to replace with"
|
|
12443
12482
|
)
|
|
12444
12483
|
).nullish().describe(
|
|
12445
|
-
"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."
|
|
12446
12485
|
),
|
|
12447
12486
|
disfluencies: import_zod3.z.boolean().nullish().describe(
|
|
12448
|
-
'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'
|
|
12449
12488
|
),
|
|
12450
12489
|
domain: import_zod3.z.string().nullish().describe(
|
|
12451
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'
|
|
@@ -12507,10 +12546,10 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
12507
12546
|
)
|
|
12508
12547
|
}).describe("A detected entity")
|
|
12509
12548
|
).nullish().describe(
|
|
12510
|
-
"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"
|
|
12511
12550
|
),
|
|
12512
12551
|
entity_detection: import_zod3.z.boolean().nullish().describe(
|
|
12513
|
-
"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"
|
|
12514
12553
|
),
|
|
12515
12554
|
error: import_zod3.z.string().optional().describe("Error message of why the transcript failed"),
|
|
12516
12555
|
filter_profanity: import_zod3.z.boolean().nullish().describe(
|
|
@@ -12520,7 +12559,7 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
12520
12559
|
"Whether [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio) is enabled, either true or false"
|
|
12521
12560
|
),
|
|
12522
12561
|
iab_categories: import_zod3.z.boolean().nullish().describe(
|
|
12523
|
-
"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"
|
|
12524
12563
|
),
|
|
12525
12564
|
iab_categories_result: import_zod3.z.object({
|
|
12526
12565
|
status: import_zod3.z.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -12543,9 +12582,9 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
12543
12582
|
).describe("An array of results for the Topic Detection model"),
|
|
12544
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")
|
|
12545
12584
|
}).describe(
|
|
12546
|
-
"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"
|
|
12547
12586
|
).or(import_zod3.z.null()).optional().describe(
|
|
12548
|
-
"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"
|
|
12549
12588
|
),
|
|
12550
12589
|
id: import_zod3.z.string().uuid().describe("The unique identifier of your transcript"),
|
|
12551
12590
|
keyterms_prompt: import_zod3.z.array(import_zod3.z.string()).optional().describe(
|
|
@@ -12795,7 +12834,7 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
12795
12834
|
"Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection)."
|
|
12796
12835
|
),
|
|
12797
12836
|
multichannel: import_zod3.z.boolean().nullish().describe(
|
|
12798
|
-
"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"
|
|
12799
12838
|
),
|
|
12800
12839
|
prompt: import_zod3.z.string().optional().describe(
|
|
12801
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"
|
|
@@ -12878,7 +12917,7 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
12878
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."
|
|
12879
12918
|
),
|
|
12880
12919
|
sentiment_analysis: import_zod3.z.boolean().nullish().describe(
|
|
12881
|
-
"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"
|
|
12882
12921
|
),
|
|
12883
12922
|
sentiment_analysis_results: import_zod3.z.array(
|
|
12884
12923
|
import_zod3.z.object({
|
|
@@ -12893,17 +12932,17 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
12893
12932
|
"The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
12894
12933
|
),
|
|
12895
12934
|
speaker: import_zod3.z.string().nullable().describe(
|
|
12896
|
-
"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"
|
|
12897
12936
|
)
|
|
12898
12937
|
}).describe("The result of the Sentiment Analysis model")
|
|
12899
12938
|
).nullish().describe(
|
|
12900
|
-
"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"
|
|
12901
12940
|
),
|
|
12902
12941
|
speaker_labels: import_zod3.z.boolean().nullish().describe(
|
|
12903
|
-
"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"
|
|
12904
12943
|
),
|
|
12905
12944
|
speakers_expected: import_zod3.z.number().nullish().describe(
|
|
12906
|
-
"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."
|
|
12907
12946
|
),
|
|
12908
12947
|
speech_model_used: import_zod3.z.string().optional().describe(
|
|
12909
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."
|
|
@@ -13006,22 +13045,25 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
13006
13045
|
"The status of your transcript. Possible values are queued, processing, completed, or error."
|
|
13007
13046
|
),
|
|
13008
13047
|
summarization: import_zod3.z.boolean().describe(
|
|
13009
|
-
"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"
|
|
13010
13049
|
),
|
|
13011
13050
|
summary: import_zod3.z.string().nullish().describe(
|
|
13012
|
-
"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."
|
|
13013
13052
|
),
|
|
13014
13053
|
summary_model: import_zod3.z.string().nullish().describe(
|
|
13015
|
-
"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"
|
|
13016
13055
|
),
|
|
13017
13056
|
summary_type: import_zod3.z.string().nullish().describe(
|
|
13018
|
-
"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."
|
|
13019
13058
|
),
|
|
13020
13059
|
remove_audio_tags: import_zod3.z.enum(["all"]).describe(
|
|
13021
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"
|
|
13022
13061
|
).or(import_zod3.z.null()).optional().describe(
|
|
13023
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"
|
|
13024
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
|
+
),
|
|
13025
13067
|
text: import_zod3.z.string().nullish().describe("The textual transcript of your media file"),
|
|
13026
13068
|
throttled: import_zod3.z.boolean().nullish().describe(
|
|
13027
13069
|
"True while a request is throttled and false when a request is no longer throttled"
|
|
@@ -13042,7 +13084,7 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
13042
13084
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
13043
13085
|
),
|
|
13044
13086
|
speaker: import_zod3.z.string().nullable().describe(
|
|
13045
|
-
"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"
|
|
13046
13088
|
)
|
|
13047
13089
|
})
|
|
13048
13090
|
).describe("The words in the utterance."),
|
|
@@ -13057,7 +13099,7 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
13057
13099
|
)
|
|
13058
13100
|
})
|
|
13059
13101
|
).nullish().describe(
|
|
13060
|
-
"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"
|
|
13061
13103
|
),
|
|
13062
13104
|
webhook_auth: import_zod3.z.boolean().describe(
|
|
13063
13105
|
"Whether [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) authentication details were provided"
|
|
@@ -13081,7 +13123,7 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
13081
13123
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
13082
13124
|
),
|
|
13083
13125
|
speaker: import_zod3.z.string().nullable().describe(
|
|
13084
|
-
"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"
|
|
13085
13127
|
)
|
|
13086
13128
|
})
|
|
13087
13129
|
).nullish().describe(
|
|
@@ -13154,7 +13196,7 @@ var getTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault = tr
|
|
|
13154
13196
|
var getTranscriptResponseSpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault = false;
|
|
13155
13197
|
var getTranscriptResponse = import_zod3.z.object({
|
|
13156
13198
|
audio_channels: import_zod3.z.number().optional().describe(
|
|
13157
|
-
"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."
|
|
13158
13200
|
),
|
|
13159
13201
|
audio_duration: import_zod3.z.number().nullish().describe("The duration of this transcript object's media file, in seconds"),
|
|
13160
13202
|
audio_end_at: import_zod3.z.number().nullish().describe(
|
|
@@ -13165,10 +13207,10 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13165
13207
|
),
|
|
13166
13208
|
audio_url: import_zod3.z.string().describe("The URL of the media that was transcribed"),
|
|
13167
13209
|
auto_chapters: import_zod3.z.boolean().nullish().describe(
|
|
13168
|
-
"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"
|
|
13169
13211
|
),
|
|
13170
13212
|
auto_highlights: import_zod3.z.boolean().describe(
|
|
13171
|
-
"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"
|
|
13172
13214
|
),
|
|
13173
13215
|
auto_highlights_result: import_zod3.z.object({
|
|
13174
13216
|
status: import_zod3.z.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -13188,9 +13230,9 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13188
13230
|
})
|
|
13189
13231
|
).describe("A temporally-sequential array of Key Phrases")
|
|
13190
13232
|
}).describe(
|
|
13191
|
-
"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"
|
|
13192
13234
|
).or(import_zod3.z.null()).optional().describe(
|
|
13193
|
-
"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"
|
|
13194
13236
|
),
|
|
13195
13237
|
chapters: import_zod3.z.array(
|
|
13196
13238
|
import_zod3.z.object({
|
|
@@ -13203,7 +13245,7 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13203
13245
|
end: import_zod3.z.number().describe("The starting time, in milliseconds, for the chapter")
|
|
13204
13246
|
}).describe("Chapter of the audio file")
|
|
13205
13247
|
).nullish().describe(
|
|
13206
|
-
"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."
|
|
13207
13249
|
),
|
|
13208
13250
|
confidence: import_zod3.z.number().nullish().describe(
|
|
13209
13251
|
"The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence)"
|
|
@@ -13259,10 +13301,10 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13259
13301
|
"Object containing words or phrases to replace, and the word or phrase to replace with"
|
|
13260
13302
|
)
|
|
13261
13303
|
).nullish().describe(
|
|
13262
|
-
"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."
|
|
13263
13305
|
),
|
|
13264
13306
|
disfluencies: import_zod3.z.boolean().nullish().describe(
|
|
13265
|
-
'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'
|
|
13266
13308
|
),
|
|
13267
13309
|
domain: import_zod3.z.string().nullish().describe(
|
|
13268
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'
|
|
@@ -13324,10 +13366,10 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13324
13366
|
)
|
|
13325
13367
|
}).describe("A detected entity")
|
|
13326
13368
|
).nullish().describe(
|
|
13327
|
-
"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"
|
|
13328
13370
|
),
|
|
13329
13371
|
entity_detection: import_zod3.z.boolean().nullish().describe(
|
|
13330
|
-
"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"
|
|
13331
13373
|
),
|
|
13332
13374
|
error: import_zod3.z.string().optional().describe("Error message of why the transcript failed"),
|
|
13333
13375
|
filter_profanity: import_zod3.z.boolean().nullish().describe(
|
|
@@ -13337,7 +13379,7 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13337
13379
|
"Whether [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio) is enabled, either true or false"
|
|
13338
13380
|
),
|
|
13339
13381
|
iab_categories: import_zod3.z.boolean().nullish().describe(
|
|
13340
|
-
"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"
|
|
13341
13383
|
),
|
|
13342
13384
|
iab_categories_result: import_zod3.z.object({
|
|
13343
13385
|
status: import_zod3.z.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -13360,9 +13402,9 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13360
13402
|
).describe("An array of results for the Topic Detection model"),
|
|
13361
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")
|
|
13362
13404
|
}).describe(
|
|
13363
|
-
"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"
|
|
13364
13406
|
).or(import_zod3.z.null()).optional().describe(
|
|
13365
|
-
"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"
|
|
13366
13408
|
),
|
|
13367
13409
|
id: import_zod3.z.string().uuid().describe("The unique identifier of your transcript"),
|
|
13368
13410
|
keyterms_prompt: import_zod3.z.array(import_zod3.z.string()).optional().describe(
|
|
@@ -13612,7 +13654,7 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13612
13654
|
"Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection)."
|
|
13613
13655
|
),
|
|
13614
13656
|
multichannel: import_zod3.z.boolean().nullish().describe(
|
|
13615
|
-
"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"
|
|
13616
13658
|
),
|
|
13617
13659
|
prompt: import_zod3.z.string().optional().describe(
|
|
13618
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"
|
|
@@ -13695,7 +13737,7 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13695
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."
|
|
13696
13738
|
),
|
|
13697
13739
|
sentiment_analysis: import_zod3.z.boolean().nullish().describe(
|
|
13698
|
-
"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"
|
|
13699
13741
|
),
|
|
13700
13742
|
sentiment_analysis_results: import_zod3.z.array(
|
|
13701
13743
|
import_zod3.z.object({
|
|
@@ -13710,17 +13752,17 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13710
13752
|
"The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
13711
13753
|
),
|
|
13712
13754
|
speaker: import_zod3.z.string().nullable().describe(
|
|
13713
|
-
"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"
|
|
13714
13756
|
)
|
|
13715
13757
|
}).describe("The result of the Sentiment Analysis model")
|
|
13716
13758
|
).nullish().describe(
|
|
13717
|
-
"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"
|
|
13718
13760
|
),
|
|
13719
13761
|
speaker_labels: import_zod3.z.boolean().nullish().describe(
|
|
13720
|
-
"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"
|
|
13721
13763
|
),
|
|
13722
13764
|
speakers_expected: import_zod3.z.number().nullish().describe(
|
|
13723
|
-
"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."
|
|
13724
13766
|
),
|
|
13725
13767
|
speech_model_used: import_zod3.z.string().optional().describe(
|
|
13726
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."
|
|
@@ -13823,22 +13865,25 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13823
13865
|
"The status of your transcript. Possible values are queued, processing, completed, or error."
|
|
13824
13866
|
),
|
|
13825
13867
|
summarization: import_zod3.z.boolean().describe(
|
|
13826
|
-
"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"
|
|
13827
13869
|
),
|
|
13828
13870
|
summary: import_zod3.z.string().nullish().describe(
|
|
13829
|
-
"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."
|
|
13830
13872
|
),
|
|
13831
13873
|
summary_model: import_zod3.z.string().nullish().describe(
|
|
13832
|
-
"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"
|
|
13833
13875
|
),
|
|
13834
13876
|
summary_type: import_zod3.z.string().nullish().describe(
|
|
13835
|
-
"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."
|
|
13836
13878
|
),
|
|
13837
13879
|
remove_audio_tags: import_zod3.z.enum(["all"]).describe(
|
|
13838
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"
|
|
13839
13881
|
).or(import_zod3.z.null()).optional().describe(
|
|
13840
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"
|
|
13841
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
|
+
),
|
|
13842
13887
|
text: import_zod3.z.string().nullish().describe("The textual transcript of your media file"),
|
|
13843
13888
|
throttled: import_zod3.z.boolean().nullish().describe(
|
|
13844
13889
|
"True while a request is throttled and false when a request is no longer throttled"
|
|
@@ -13859,7 +13904,7 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13859
13904
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
13860
13905
|
),
|
|
13861
13906
|
speaker: import_zod3.z.string().nullable().describe(
|
|
13862
|
-
"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"
|
|
13863
13908
|
)
|
|
13864
13909
|
})
|
|
13865
13910
|
).describe("The words in the utterance."),
|
|
@@ -13874,7 +13919,7 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13874
13919
|
)
|
|
13875
13920
|
})
|
|
13876
13921
|
).nullish().describe(
|
|
13877
|
-
"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"
|
|
13878
13923
|
),
|
|
13879
13924
|
webhook_auth: import_zod3.z.boolean().describe(
|
|
13880
13925
|
"Whether [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) authentication details were provided"
|
|
@@ -13898,7 +13943,7 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
13898
13943
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
13899
13944
|
),
|
|
13900
13945
|
speaker: import_zod3.z.string().nullable().describe(
|
|
13901
|
-
"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"
|
|
13902
13947
|
)
|
|
13903
13948
|
})
|
|
13904
13949
|
).nullish().describe(
|
|
@@ -13931,7 +13976,7 @@ var deleteTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault =
|
|
|
13931
13976
|
var deleteTranscriptResponseSpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault = false;
|
|
13932
13977
|
var deleteTranscriptResponse = import_zod3.z.object({
|
|
13933
13978
|
audio_channels: import_zod3.z.number().optional().describe(
|
|
13934
|
-
"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."
|
|
13935
13980
|
),
|
|
13936
13981
|
audio_duration: import_zod3.z.number().nullish().describe("The duration of this transcript object's media file, in seconds"),
|
|
13937
13982
|
audio_end_at: import_zod3.z.number().nullish().describe(
|
|
@@ -13942,10 +13987,10 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
13942
13987
|
),
|
|
13943
13988
|
audio_url: import_zod3.z.string().describe("The URL of the media that was transcribed"),
|
|
13944
13989
|
auto_chapters: import_zod3.z.boolean().nullish().describe(
|
|
13945
|
-
"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"
|
|
13946
13991
|
),
|
|
13947
13992
|
auto_highlights: import_zod3.z.boolean().describe(
|
|
13948
|
-
"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"
|
|
13949
13994
|
),
|
|
13950
13995
|
auto_highlights_result: import_zod3.z.object({
|
|
13951
13996
|
status: import_zod3.z.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -13965,9 +14010,9 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
13965
14010
|
})
|
|
13966
14011
|
).describe("A temporally-sequential array of Key Phrases")
|
|
13967
14012
|
}).describe(
|
|
13968
|
-
"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"
|
|
13969
14014
|
).or(import_zod3.z.null()).optional().describe(
|
|
13970
|
-
"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"
|
|
13971
14016
|
),
|
|
13972
14017
|
chapters: import_zod3.z.array(
|
|
13973
14018
|
import_zod3.z.object({
|
|
@@ -13980,7 +14025,7 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
13980
14025
|
end: import_zod3.z.number().describe("The starting time, in milliseconds, for the chapter")
|
|
13981
14026
|
}).describe("Chapter of the audio file")
|
|
13982
14027
|
).nullish().describe(
|
|
13983
|
-
"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."
|
|
13984
14029
|
),
|
|
13985
14030
|
confidence: import_zod3.z.number().nullish().describe(
|
|
13986
14031
|
"The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence)"
|
|
@@ -14036,10 +14081,10 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
14036
14081
|
"Object containing words or phrases to replace, and the word or phrase to replace with"
|
|
14037
14082
|
)
|
|
14038
14083
|
).nullish().describe(
|
|
14039
|
-
"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."
|
|
14040
14085
|
),
|
|
14041
14086
|
disfluencies: import_zod3.z.boolean().nullish().describe(
|
|
14042
|
-
'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'
|
|
14043
14088
|
),
|
|
14044
14089
|
domain: import_zod3.z.string().nullish().describe(
|
|
14045
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'
|
|
@@ -14101,10 +14146,10 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
14101
14146
|
)
|
|
14102
14147
|
}).describe("A detected entity")
|
|
14103
14148
|
).nullish().describe(
|
|
14104
|
-
"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"
|
|
14105
14150
|
),
|
|
14106
14151
|
entity_detection: import_zod3.z.boolean().nullish().describe(
|
|
14107
|
-
"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"
|
|
14108
14153
|
),
|
|
14109
14154
|
error: import_zod3.z.string().optional().describe("Error message of why the transcript failed"),
|
|
14110
14155
|
filter_profanity: import_zod3.z.boolean().nullish().describe(
|
|
@@ -14114,7 +14159,7 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
14114
14159
|
"Whether [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio) is enabled, either true or false"
|
|
14115
14160
|
),
|
|
14116
14161
|
iab_categories: import_zod3.z.boolean().nullish().describe(
|
|
14117
|
-
"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"
|
|
14118
14163
|
),
|
|
14119
14164
|
iab_categories_result: import_zod3.z.object({
|
|
14120
14165
|
status: import_zod3.z.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -14137,9 +14182,9 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
14137
14182
|
).describe("An array of results for the Topic Detection model"),
|
|
14138
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")
|
|
14139
14184
|
}).describe(
|
|
14140
|
-
"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"
|
|
14141
14186
|
).or(import_zod3.z.null()).optional().describe(
|
|
14142
|
-
"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"
|
|
14143
14188
|
),
|
|
14144
14189
|
id: import_zod3.z.string().uuid().describe("The unique identifier of your transcript"),
|
|
14145
14190
|
keyterms_prompt: import_zod3.z.array(import_zod3.z.string()).optional().describe(
|
|
@@ -14389,7 +14434,7 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
14389
14434
|
"Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection)."
|
|
14390
14435
|
),
|
|
14391
14436
|
multichannel: import_zod3.z.boolean().nullish().describe(
|
|
14392
|
-
"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"
|
|
14393
14438
|
),
|
|
14394
14439
|
prompt: import_zod3.z.string().optional().describe(
|
|
14395
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"
|
|
@@ -14472,7 +14517,7 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
14472
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."
|
|
14473
14518
|
),
|
|
14474
14519
|
sentiment_analysis: import_zod3.z.boolean().nullish().describe(
|
|
14475
|
-
"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"
|
|
14476
14521
|
),
|
|
14477
14522
|
sentiment_analysis_results: import_zod3.z.array(
|
|
14478
14523
|
import_zod3.z.object({
|
|
@@ -14487,17 +14532,17 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
14487
14532
|
"The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
14488
14533
|
),
|
|
14489
14534
|
speaker: import_zod3.z.string().nullable().describe(
|
|
14490
|
-
"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"
|
|
14491
14536
|
)
|
|
14492
14537
|
}).describe("The result of the Sentiment Analysis model")
|
|
14493
14538
|
).nullish().describe(
|
|
14494
|
-
"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"
|
|
14495
14540
|
),
|
|
14496
14541
|
speaker_labels: import_zod3.z.boolean().nullish().describe(
|
|
14497
|
-
"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"
|
|
14498
14543
|
),
|
|
14499
14544
|
speakers_expected: import_zod3.z.number().nullish().describe(
|
|
14500
|
-
"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."
|
|
14501
14546
|
),
|
|
14502
14547
|
speech_model_used: import_zod3.z.string().optional().describe(
|
|
14503
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."
|
|
@@ -14600,22 +14645,25 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
14600
14645
|
"The status of your transcript. Possible values are queued, processing, completed, or error."
|
|
14601
14646
|
),
|
|
14602
14647
|
summarization: import_zod3.z.boolean().describe(
|
|
14603
|
-
"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"
|
|
14604
14649
|
),
|
|
14605
14650
|
summary: import_zod3.z.string().nullish().describe(
|
|
14606
|
-
"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."
|
|
14607
14652
|
),
|
|
14608
14653
|
summary_model: import_zod3.z.string().nullish().describe(
|
|
14609
|
-
"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"
|
|
14610
14655
|
),
|
|
14611
14656
|
summary_type: import_zod3.z.string().nullish().describe(
|
|
14612
|
-
"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."
|
|
14613
14658
|
),
|
|
14614
14659
|
remove_audio_tags: import_zod3.z.enum(["all"]).describe(
|
|
14615
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"
|
|
14616
14661
|
).or(import_zod3.z.null()).optional().describe(
|
|
14617
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"
|
|
14618
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
|
+
),
|
|
14619
14667
|
text: import_zod3.z.string().nullish().describe("The textual transcript of your media file"),
|
|
14620
14668
|
throttled: import_zod3.z.boolean().nullish().describe(
|
|
14621
14669
|
"True while a request is throttled and false when a request is no longer throttled"
|
|
@@ -14636,7 +14684,7 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
14636
14684
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
14637
14685
|
),
|
|
14638
14686
|
speaker: import_zod3.z.string().nullable().describe(
|
|
14639
|
-
"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"
|
|
14640
14688
|
)
|
|
14641
14689
|
})
|
|
14642
14690
|
).describe("The words in the utterance."),
|
|
@@ -14651,7 +14699,7 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
14651
14699
|
)
|
|
14652
14700
|
})
|
|
14653
14701
|
).nullish().describe(
|
|
14654
|
-
"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"
|
|
14655
14703
|
),
|
|
14656
14704
|
webhook_auth: import_zod3.z.boolean().describe(
|
|
14657
14705
|
"Whether [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) authentication details were provided"
|
|
@@ -14675,7 +14723,7 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
14675
14723
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
14676
14724
|
),
|
|
14677
14725
|
speaker: import_zod3.z.string().nullable().describe(
|
|
14678
|
-
"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"
|
|
14679
14727
|
)
|
|
14680
14728
|
})
|
|
14681
14729
|
).nullish().describe(
|
|
@@ -14720,7 +14768,7 @@ var getTranscriptSentencesResponse = import_zod3.z.object({
|
|
|
14720
14768
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
14721
14769
|
),
|
|
14722
14770
|
speaker: import_zod3.z.string().nullable().describe(
|
|
14723
|
-
"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"
|
|
14724
14772
|
)
|
|
14725
14773
|
})
|
|
14726
14774
|
).describe("An array of words in the sentence"),
|
|
@@ -14728,7 +14776,7 @@ var getTranscriptSentencesResponse = import_zod3.z.object({
|
|
|
14728
14776
|
"The channel of the sentence. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
14729
14777
|
),
|
|
14730
14778
|
speaker: import_zod3.z.string().nullable().describe(
|
|
14731
|
-
"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"
|
|
14732
14780
|
)
|
|
14733
14781
|
})
|
|
14734
14782
|
).describe("An array of sentences in the transcript")
|
|
@@ -14756,7 +14804,7 @@ var getTranscriptParagraphsResponse = import_zod3.z.object({
|
|
|
14756
14804
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
14757
14805
|
),
|
|
14758
14806
|
speaker: import_zod3.z.string().nullable().describe(
|
|
14759
|
-
"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"
|
|
14760
14808
|
)
|
|
14761
14809
|
})
|
|
14762
14810
|
).describe("An array of words in the paragraph")
|
|
@@ -17368,23 +17416,6 @@ var preRecordedControllerGetPreRecordedJobsV2Response = import_zod5.z.object({
|
|
|
17368
17416
|
}).optional().describe(
|
|
17369
17417
|
"If `name_consistency` has been enabled, Gladia will improve consistency of the names accross the transcription"
|
|
17370
17418
|
),
|
|
17371
|
-
speaker_reidentification: import_zod5.z.object({
|
|
17372
|
-
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
17373
|
-
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
17374
|
-
exec_time: import_zod5.z.number().describe("Time audio intelligence model took to complete the task"),
|
|
17375
|
-
error: import_zod5.z.object({
|
|
17376
|
-
status_code: import_zod5.z.number().describe("Status code of the addon error"),
|
|
17377
|
-
exception: import_zod5.z.string().describe("Reason of the addon error"),
|
|
17378
|
-
message: import_zod5.z.string().describe("Detailed message of the addon error")
|
|
17379
|
-
}).nullable().describe(
|
|
17380
|
-
"`null` if `success` is `true`. Contains the error details of the failed model"
|
|
17381
|
-
),
|
|
17382
|
-
results: import_zod5.z.string().describe(
|
|
17383
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
17384
|
-
)
|
|
17385
|
-
}).optional().describe(
|
|
17386
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
17387
|
-
),
|
|
17388
17419
|
structured_data_extraction: import_zod5.z.object({
|
|
17389
17420
|
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
17390
17421
|
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
@@ -18865,23 +18896,6 @@ var preRecordedControllerGetPreRecordedJobV2Response = import_zod5.z.object({
|
|
|
18865
18896
|
}).optional().describe(
|
|
18866
18897
|
"If `name_consistency` has been enabled, Gladia will improve consistency of the names accross the transcription"
|
|
18867
18898
|
),
|
|
18868
|
-
speaker_reidentification: import_zod5.z.object({
|
|
18869
|
-
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
18870
|
-
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
18871
|
-
exec_time: import_zod5.z.number().describe("Time audio intelligence model took to complete the task"),
|
|
18872
|
-
error: import_zod5.z.object({
|
|
18873
|
-
status_code: import_zod5.z.number().describe("Status code of the addon error"),
|
|
18874
|
-
exception: import_zod5.z.string().describe("Reason of the addon error"),
|
|
18875
|
-
message: import_zod5.z.string().describe("Detailed message of the addon error")
|
|
18876
|
-
}).nullable().describe(
|
|
18877
|
-
"`null` if `success` is `true`. Contains the error details of the failed model"
|
|
18878
|
-
),
|
|
18879
|
-
results: import_zod5.z.string().describe(
|
|
18880
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
18881
|
-
)
|
|
18882
|
-
}).optional().describe(
|
|
18883
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
18884
|
-
),
|
|
18885
18899
|
structured_data_extraction: import_zod5.z.object({
|
|
18886
18900
|
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
18887
18901
|
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
@@ -21019,23 +21033,6 @@ var transcriptionControllerListV2Response = import_zod5.z.object({
|
|
|
21019
21033
|
}).optional().describe(
|
|
21020
21034
|
"If `name_consistency` has been enabled, Gladia will improve consistency of the names accross the transcription"
|
|
21021
21035
|
),
|
|
21022
|
-
speaker_reidentification: import_zod5.z.object({
|
|
21023
|
-
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
21024
|
-
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
21025
|
-
exec_time: import_zod5.z.number().describe("Time audio intelligence model took to complete the task"),
|
|
21026
|
-
error: import_zod5.z.object({
|
|
21027
|
-
status_code: import_zod5.z.number().describe("Status code of the addon error"),
|
|
21028
|
-
exception: import_zod5.z.string().describe("Reason of the addon error"),
|
|
21029
|
-
message: import_zod5.z.string().describe("Detailed message of the addon error")
|
|
21030
|
-
}).nullable().describe(
|
|
21031
|
-
"`null` if `success` is `true`. Contains the error details of the failed model"
|
|
21032
|
-
),
|
|
21033
|
-
results: import_zod5.z.string().describe(
|
|
21034
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
21035
|
-
)
|
|
21036
|
-
}).optional().describe(
|
|
21037
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
21038
|
-
),
|
|
21039
21036
|
structured_data_extraction: import_zod5.z.object({
|
|
21040
21037
|
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
21041
21038
|
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
@@ -21335,11 +21332,7 @@ var transcriptionControllerListV2Response = import_zod5.z.object({
|
|
|
21335
21332
|
channels: import_zod5.z.number().min(1).max(transcriptionControllerListV2ResponseItemsItemRequestParamsChannelsMax).default(
|
|
21336
21333
|
transcriptionControllerListV2ResponseItemsItemRequestParamsChannelsDefault
|
|
21337
21334
|
).describe("The number of channels of the audio stream"),
|
|
21338
|
-
model: import_zod5.z.enum(["solaria-1"]).describe(
|
|
21339
|
-
'The model used to process the audio. "solaria-1" is used by default.'
|
|
21340
|
-
).default(transcriptionControllerListV2ResponseItemsItemRequestParamsModelDefault).describe(
|
|
21341
|
-
'The model used to process the audio. "solaria-1" is used by default.'
|
|
21342
|
-
),
|
|
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.'),
|
|
21343
21336
|
endpointing: import_zod5.z.number().min(transcriptionControllerListV2ResponseItemsItemRequestParamsEndpointingMin).max(transcriptionControllerListV2ResponseItemsItemRequestParamsEndpointingMax).default(
|
|
21344
21337
|
transcriptionControllerListV2ResponseItemsItemRequestParamsEndpointingDefault
|
|
21345
21338
|
).describe(
|
|
@@ -23763,23 +23756,6 @@ var transcriptionControllerGetTranscriptV2Response = import_zod5.z.discriminated
|
|
|
23763
23756
|
}).optional().describe(
|
|
23764
23757
|
"If `name_consistency` has been enabled, Gladia will improve consistency of the names accross the transcription"
|
|
23765
23758
|
),
|
|
23766
|
-
speaker_reidentification: import_zod5.z.object({
|
|
23767
|
-
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
23768
|
-
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
23769
|
-
exec_time: import_zod5.z.number().describe("Time audio intelligence model took to complete the task"),
|
|
23770
|
-
error: import_zod5.z.object({
|
|
23771
|
-
status_code: import_zod5.z.number().describe("Status code of the addon error"),
|
|
23772
|
-
exception: import_zod5.z.string().describe("Reason of the addon error"),
|
|
23773
|
-
message: import_zod5.z.string().describe("Detailed message of the addon error")
|
|
23774
|
-
}).nullable().describe(
|
|
23775
|
-
"`null` if `success` is `true`. Contains the error details of the failed model"
|
|
23776
|
-
),
|
|
23777
|
-
results: import_zod5.z.string().describe(
|
|
23778
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
23779
|
-
)
|
|
23780
|
-
}).optional().describe(
|
|
23781
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
23782
|
-
),
|
|
23783
23759
|
structured_data_extraction: import_zod5.z.object({
|
|
23784
23760
|
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
23785
23761
|
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
@@ -26945,23 +26921,6 @@ var historyControllerGetListV1Response = import_zod5.z.object({
|
|
|
26945
26921
|
}).optional().describe(
|
|
26946
26922
|
"If `name_consistency` has been enabled, Gladia will improve consistency of the names accross the transcription"
|
|
26947
26923
|
),
|
|
26948
|
-
speaker_reidentification: import_zod5.z.object({
|
|
26949
|
-
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
26950
|
-
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
26951
|
-
exec_time: import_zod5.z.number().describe("Time audio intelligence model took to complete the task"),
|
|
26952
|
-
error: import_zod5.z.object({
|
|
26953
|
-
status_code: import_zod5.z.number().describe("Status code of the addon error"),
|
|
26954
|
-
exception: import_zod5.z.string().describe("Reason of the addon error"),
|
|
26955
|
-
message: import_zod5.z.string().describe("Detailed message of the addon error")
|
|
26956
|
-
}).nullable().describe(
|
|
26957
|
-
"`null` if `success` is `true`. Contains the error details of the failed model"
|
|
26958
|
-
),
|
|
26959
|
-
results: import_zod5.z.string().describe(
|
|
26960
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
26961
|
-
)
|
|
26962
|
-
}).optional().describe(
|
|
26963
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
26964
|
-
),
|
|
26965
26924
|
structured_data_extraction: import_zod5.z.object({
|
|
26966
26925
|
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
26967
26926
|
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
@@ -27255,11 +27214,7 @@ var historyControllerGetListV1Response = import_zod5.z.object({
|
|
|
27255
27214
|
historyControllerGetListV1ResponseItemsItemRequestParamsSampleRateDefault
|
|
27256
27215
|
).describe("The sample rate of the audio stream"),
|
|
27257
27216
|
channels: import_zod5.z.number().min(1).max(historyControllerGetListV1ResponseItemsItemRequestParamsChannelsMax).default(historyControllerGetListV1ResponseItemsItemRequestParamsChannelsDefault).describe("The number of channels of the audio stream"),
|
|
27258
|
-
model: import_zod5.z.enum(["solaria-1"]).describe(
|
|
27259
|
-
'The model used to process the audio. "solaria-1" is used by default.'
|
|
27260
|
-
).default(historyControllerGetListV1ResponseItemsItemRequestParamsModelDefault).describe(
|
|
27261
|
-
'The model used to process the audio. "solaria-1" is used by default.'
|
|
27262
|
-
),
|
|
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.'),
|
|
27263
27218
|
endpointing: import_zod5.z.number().min(historyControllerGetListV1ResponseItemsItemRequestParamsEndpointingMin).max(historyControllerGetListV1ResponseItemsItemRequestParamsEndpointingMax).default(
|
|
27264
27219
|
historyControllerGetListV1ResponseItemsItemRequestParamsEndpointingDefault
|
|
27265
27220
|
).describe(
|
|
@@ -36420,6 +36375,7 @@ __export(sonioxPublicAPI_zod_exports, {
|
|
|
36420
36375
|
createTemporaryApiKeyBody: () => createTemporaryApiKeyBody,
|
|
36421
36376
|
createTemporaryApiKeyBodyClientReferenceIdMaxOne: () => createTemporaryApiKeyBodyClientReferenceIdMaxOne,
|
|
36422
36377
|
createTemporaryApiKeyBodyExpiresInSecondsMax: () => createTemporaryApiKeyBodyExpiresInSecondsMax,
|
|
36378
|
+
createTemporaryApiKeyBodyMaxSessionDurationSecondsMaxOne: () => createTemporaryApiKeyBodyMaxSessionDurationSecondsMaxOne,
|
|
36423
36379
|
createTranscriptionBody: () => createTranscriptionBody2,
|
|
36424
36380
|
createTranscriptionBodyAudioUrlMaxOne: () => createTranscriptionBodyAudioUrlMaxOne,
|
|
36425
36381
|
createTranscriptionBodyAudioUrlRegExpOne: () => createTranscriptionBodyAudioUrlRegExpOne,
|
|
@@ -36550,11 +36506,11 @@ var getTranscriptionsResponse = import_zod10.z.object({
|
|
|
36550
36506
|
});
|
|
36551
36507
|
var createTranscriptionBodyModelMaxThree = 32;
|
|
36552
36508
|
var createTranscriptionBodyAudioUrlMaxOne = 4096;
|
|
36553
|
-
var createTranscriptionBodyAudioUrlRegExpOne =
|
|
36509
|
+
var createTranscriptionBodyAudioUrlRegExpOne = /^https?:\/\/[^\s]+$/;
|
|
36554
36510
|
var createTranscriptionBodyLanguageHintsItemMax = 10;
|
|
36555
36511
|
var createTranscriptionBodyLanguageHintsMaxOne = 100;
|
|
36556
36512
|
var createTranscriptionBodyWebhookUrlMaxOne = 256;
|
|
36557
|
-
var createTranscriptionBodyWebhookUrlRegExpOne =
|
|
36513
|
+
var createTranscriptionBodyWebhookUrlRegExpOne = /^https?:\/\/[^\s]+$/;
|
|
36558
36514
|
var createTranscriptionBodyWebhookAuthHeaderNameMaxOne = 256;
|
|
36559
36515
|
var createTranscriptionBodyWebhookAuthHeaderValueMaxOne = 256;
|
|
36560
36516
|
var createTranscriptionBodyClientReferenceIdMaxOne = 256;
|
|
@@ -36702,10 +36658,15 @@ var getModelsResponse = import_zod10.z.object({
|
|
|
36702
36658
|
});
|
|
36703
36659
|
var createTemporaryApiKeyBodyExpiresInSecondsMax = 3600;
|
|
36704
36660
|
var createTemporaryApiKeyBodyClientReferenceIdMaxOne = 256;
|
|
36661
|
+
var createTemporaryApiKeyBodyMaxSessionDurationSecondsMaxOne = 18e3;
|
|
36705
36662
|
var createTemporaryApiKeyBody = import_zod10.z.object({
|
|
36706
36663
|
usage_type: import_zod10.z.enum(["transcribe_websocket"]),
|
|
36707
36664
|
expires_in_seconds: import_zod10.z.number().min(1).max(createTemporaryApiKeyBodyExpiresInSecondsMax).describe("Duration in seconds until the temporary API key expires."),
|
|
36708
|
-
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
|
+
)
|
|
36709
36670
|
});
|
|
36710
36671
|
|
|
36711
36672
|
// src/generated/soniox/streaming-types.zod.ts
|
|
@@ -37956,6 +37917,16 @@ var ToolChoiceOptions = {
|
|
|
37956
37917
|
required: "required"
|
|
37957
37918
|
};
|
|
37958
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
|
+
|
|
37959
37930
|
// src/generated/openai/schema/transcriptTextDeltaEventType.ts
|
|
37960
37931
|
var TranscriptTextDeltaEventType = {
|
|
37961
37932
|
transcripttextdelta: "transcript.text.delta"
|
|
@@ -37981,16 +37952,6 @@ var TranscriptTextUsageTokensType = {
|
|
|
37981
37952
|
tokens: "tokens"
|
|
37982
37953
|
};
|
|
37983
37954
|
|
|
37984
|
-
// src/generated/openai/schema/transcriptionDiarizedSegmentType.ts
|
|
37985
|
-
var TranscriptionDiarizedSegmentType = {
|
|
37986
|
-
transcripttextsegment: "transcript.text.segment"
|
|
37987
|
-
};
|
|
37988
|
-
|
|
37989
|
-
// src/generated/openai/schema/transcriptionInclude.ts
|
|
37990
|
-
var TranscriptionInclude = {
|
|
37991
|
-
logprobs: "logprobs"
|
|
37992
|
-
};
|
|
37993
|
-
|
|
37994
37955
|
// src/generated/openai/schema/vadConfigType.ts
|
|
37995
37956
|
var VadConfigType = {
|
|
37996
37957
|
server_vad: "server_vad"
|
|
@@ -38372,8 +38333,8 @@ var getJobsQueryParams = import_zod12.z.object({
|
|
|
38372
38333
|
var getJobsResponseJobsItemDurationMin = 0;
|
|
38373
38334
|
var getJobsResponseJobsItemConfigTranscriptionConfigPunctuationOverridesSensitivityMin = 0;
|
|
38374
38335
|
var getJobsResponseJobsItemConfigTranscriptionConfigPunctuationOverridesSensitivityMax = 1;
|
|
38375
|
-
var getJobsResponseJobsItemConfigTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp =
|
|
38376
|
-
var getJobsResponseJobsItemConfigTranscriptionConfigChannelDiarizationLabelsItemRegExp =
|
|
38336
|
+
var getJobsResponseJobsItemConfigTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp = /^(.|all)$/;
|
|
38337
|
+
var getJobsResponseJobsItemConfigTranscriptionConfigChannelDiarizationLabelsItemRegExp = /^[A-Za-z0-9._]+$/;
|
|
38377
38338
|
var getJobsResponseJobsItemConfigTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMin = 0;
|
|
38378
38339
|
var getJobsResponseJobsItemConfigTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMax = 1;
|
|
38379
38340
|
var getJobsResponseJobsItemConfigTranslationConfigTargetLanguagesMax = 5;
|
|
@@ -38571,8 +38532,8 @@ var getJobsJobidParams = import_zod12.z.object({
|
|
|
38571
38532
|
var getJobsJobidResponseJobDurationMin = 0;
|
|
38572
38533
|
var getJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesSensitivityMin = 0;
|
|
38573
38534
|
var getJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesSensitivityMax = 1;
|
|
38574
|
-
var getJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp =
|
|
38575
|
-
var getJobsJobidResponseJobConfigTranscriptionConfigChannelDiarizationLabelsItemRegExp =
|
|
38535
|
+
var getJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp = /^(.|all)$/;
|
|
38536
|
+
var getJobsJobidResponseJobConfigTranscriptionConfigChannelDiarizationLabelsItemRegExp = /^[A-Za-z0-9._]+$/;
|
|
38576
38537
|
var getJobsJobidResponseJobConfigTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMin = 0;
|
|
38577
38538
|
var getJobsJobidResponseJobConfigTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMax = 1;
|
|
38578
38539
|
var getJobsJobidResponseJobConfigTranslationConfigTargetLanguagesMax = 5;
|
|
@@ -38769,8 +38730,8 @@ var deleteJobsJobidQueryParams = import_zod12.z.object({
|
|
|
38769
38730
|
var deleteJobsJobidResponseJobDurationMin = 0;
|
|
38770
38731
|
var deleteJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesSensitivityMin = 0;
|
|
38771
38732
|
var deleteJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesSensitivityMax = 1;
|
|
38772
|
-
var deleteJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp =
|
|
38773
|
-
var deleteJobsJobidResponseJobConfigTranscriptionConfigChannelDiarizationLabelsItemRegExp =
|
|
38733
|
+
var deleteJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp = /^(.|all)$/;
|
|
38734
|
+
var deleteJobsJobidResponseJobConfigTranscriptionConfigChannelDiarizationLabelsItemRegExp = /^[A-Za-z0-9._]+$/;
|
|
38774
38735
|
var deleteJobsJobidResponseJobConfigTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMin = 0;
|
|
38775
38736
|
var deleteJobsJobidResponseJobConfigTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMax = 1;
|
|
38776
38737
|
var deleteJobsJobidResponseJobConfigTranslationConfigTargetLanguagesMax = 5;
|
|
@@ -38973,8 +38934,8 @@ var getJobsJobidTranscriptQueryParams = import_zod12.z.object({
|
|
|
38973
38934
|
var getJobsJobidTranscriptResponseJobDurationMin = 0;
|
|
38974
38935
|
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigPunctuationOverridesSensitivityMin = 0;
|
|
38975
38936
|
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigPunctuationOverridesSensitivityMax = 1;
|
|
38976
|
-
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp =
|
|
38977
|
-
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigChannelDiarizationLabelsItemRegExp =
|
|
38937
|
+
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp = /^(.|all)$/;
|
|
38938
|
+
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigChannelDiarizationLabelsItemRegExp = /^[A-Za-z0-9._]+$/;
|
|
38978
38939
|
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMin = 0;
|
|
38979
38940
|
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMax = 1;
|
|
38980
38941
|
var getJobsJobidTranscriptResponseResultsItemVolumeMin = 0;
|