voice-router-dev 0.8.8 → 0.9.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +67 -0
- package/dist/constants.d.mts +23 -21
- package/dist/constants.d.ts +23 -21
- package/dist/constants.js +24 -24
- package/dist/constants.mjs +24 -24
- package/dist/{field-configs-BtR4uR2N.d.mts → field-configs-DYiUtRUz.d.mts} +5666 -6121
- package/dist/{field-configs-BtR4uR2N.d.ts → field-configs-DYiUtRUz.d.ts} +5666 -6121
- package/dist/field-configs.d.mts +1 -1
- package/dist/field-configs.d.ts +1 -1
- package/dist/field-configs.js +118 -196
- package/dist/field-configs.mjs +118 -196
- package/dist/index.d.mts +2006 -2105
- package/dist/index.d.ts +2006 -2105
- package/dist/index.js +267 -298
- package/dist/index.mjs +267 -298
- package/dist/{speechToTextChunkResponseModel-B4kVoFc3.d.ts → speechToTextChunkResponseModel-CI-Aqxcr.d.ts} +2015 -1846
- package/dist/{speechToTextChunkResponseModel-DmajV4F-.d.mts → speechToTextChunkResponseModel-D8VJ-wz6.d.mts} +2015 -1846
- package/dist/webhooks.d.mts +70 -2
- package/dist/webhooks.d.ts +70 -2
- package/dist/webhooks.js +113 -1
- package/dist/webhooks.mjs +111 -1
- package/package.json +1 -1
package/dist/index.mjs
CHANGED
|
@@ -754,60 +754,60 @@ var SonioxLanguage = {
|
|
|
754
754
|
// src/generated/soniox/models.ts
|
|
755
755
|
var SonioxModels = [
|
|
756
756
|
{ id: "stt-rt-v4", name: "Speech-to-Text Real-time v4", mode: "real_time" },
|
|
757
|
-
{ id: "stt-rt-v3", name: "Speech-to-Text Real-time v3", mode: "real_time" },
|
|
758
757
|
{ id: "stt-async-v4", name: "Speech-to-Text Async v4", mode: "async" },
|
|
759
|
-
{ id: "stt-
|
|
760
|
-
{ id: "stt-
|
|
761
|
-
{ id: "stt-
|
|
762
|
-
{ id: "stt-rt-
|
|
763
|
-
{ id: "stt-
|
|
764
|
-
{ id: "stt-
|
|
758
|
+
{ id: "stt-rt-preview", name: "Speech-to-Text Real-time Preview", mode: "real_time", aliasOf: "stt-rt-v4" },
|
|
759
|
+
{ id: "stt-async-preview", name: "Speech-to-Text Async Preview", mode: "async", aliasOf: "stt-async-v4" },
|
|
760
|
+
{ id: "stt-rt-v3-preview", name: "Speech-to-Text Real-time v3 Preview", mode: "real_time", aliasOf: "stt-rt-v4" },
|
|
761
|
+
{ id: "stt-rt-preview-v2", name: "Speech-to-Text Real-time Preview v2", mode: "real_time", aliasOf: "stt-rt-v4" },
|
|
762
|
+
{ id: "stt-async-preview-v1", name: "Speech-to-Text Async Preview v1", mode: "async", aliasOf: "stt-async-v4" },
|
|
763
|
+
{ id: "stt-rt-v3", name: "Speech-to-Text Real-time v3", mode: "real_time", aliasOf: "stt-rt-v4" },
|
|
764
|
+
{ id: "stt-async-v3", name: "Speech-to-Text Async v3", mode: "async", aliasOf: "stt-async-v4" }
|
|
765
765
|
];
|
|
766
766
|
var SonioxModelCodes = [
|
|
767
767
|
"stt-rt-v4",
|
|
768
|
-
"stt-rt-v3",
|
|
769
768
|
"stt-async-v4",
|
|
770
|
-
"stt-async-v3",
|
|
771
769
|
"stt-rt-preview",
|
|
772
770
|
"stt-async-preview",
|
|
773
771
|
"stt-rt-v3-preview",
|
|
774
772
|
"stt-rt-preview-v2",
|
|
775
|
-
"stt-async-preview-v1"
|
|
773
|
+
"stt-async-preview-v1",
|
|
774
|
+
"stt-rt-v3",
|
|
775
|
+
"stt-async-v3"
|
|
776
776
|
];
|
|
777
777
|
var SonioxModelLabels = {
|
|
778
778
|
"stt-rt-v4": "Speech-to-Text Real-time v4",
|
|
779
|
-
"stt-rt-v3": "Speech-to-Text Real-time v3",
|
|
780
779
|
"stt-async-v4": "Speech-to-Text Async v4",
|
|
781
|
-
"stt-async-v3": "Speech-to-Text Async v3",
|
|
782
780
|
"stt-rt-preview": "Speech-to-Text Real-time Preview",
|
|
783
781
|
"stt-async-preview": "Speech-to-Text Async Preview",
|
|
784
782
|
"stt-rt-v3-preview": "Speech-to-Text Real-time v3 Preview",
|
|
785
783
|
"stt-rt-preview-v2": "Speech-to-Text Real-time Preview v2",
|
|
786
|
-
"stt-async-preview-v1": "Speech-to-Text Async Preview v1"
|
|
784
|
+
"stt-async-preview-v1": "Speech-to-Text Async Preview v1",
|
|
785
|
+
"stt-rt-v3": "Speech-to-Text Real-time v3",
|
|
786
|
+
"stt-async-v3": "Speech-to-Text Async v3"
|
|
787
787
|
};
|
|
788
788
|
var SonioxModel = {
|
|
789
789
|
stt_rt_v4: "stt-rt-v4",
|
|
790
|
-
stt_rt_v3: "stt-rt-v3",
|
|
791
790
|
stt_async_v4: "stt-async-v4",
|
|
792
|
-
stt_async_v3: "stt-async-v3",
|
|
793
791
|
stt_rt_preview: "stt-rt-preview",
|
|
794
792
|
stt_async_preview: "stt-async-preview",
|
|
795
793
|
stt_rt_v3_preview: "stt-rt-v3-preview",
|
|
796
794
|
stt_rt_preview_v2: "stt-rt-preview-v2",
|
|
797
|
-
stt_async_preview_v1: "stt-async-preview-v1"
|
|
795
|
+
stt_async_preview_v1: "stt-async-preview-v1",
|
|
796
|
+
stt_rt_v3: "stt-rt-v3",
|
|
797
|
+
stt_async_v3: "stt-async-v3"
|
|
798
798
|
};
|
|
799
799
|
var SonioxRealtimeModel = {
|
|
800
800
|
stt_rt_v4: "stt-rt-v4",
|
|
801
|
-
stt_rt_v3: "stt-rt-v3",
|
|
802
801
|
stt_rt_preview: "stt-rt-preview",
|
|
803
802
|
stt_rt_v3_preview: "stt-rt-v3-preview",
|
|
804
|
-
stt_rt_preview_v2: "stt-rt-preview-v2"
|
|
803
|
+
stt_rt_preview_v2: "stt-rt-preview-v2",
|
|
804
|
+
stt_rt_v3: "stt-rt-v3"
|
|
805
805
|
};
|
|
806
806
|
var SonioxAsyncModel = {
|
|
807
807
|
stt_async_v4: "stt-async-v4",
|
|
808
|
-
stt_async_v3: "stt-async-v3",
|
|
809
808
|
stt_async_preview: "stt-async-preview",
|
|
810
|
-
stt_async_preview_v1: "stt-async-preview-v1"
|
|
809
|
+
stt_async_preview_v1: "stt-async-preview-v1",
|
|
810
|
+
stt_async_v3: "stt-async-v3"
|
|
811
811
|
};
|
|
812
812
|
|
|
813
813
|
// src/generated/speechmatics/languages.ts
|
|
@@ -3782,17 +3782,17 @@ var SummaryTypesEnum = {
|
|
|
3782
3782
|
concise: "concise"
|
|
3783
3783
|
};
|
|
3784
3784
|
|
|
3785
|
-
// src/generated/gladia/schema/transcriptMessageType.ts
|
|
3786
|
-
var TranscriptMessageType = {
|
|
3787
|
-
transcript: "transcript"
|
|
3788
|
-
};
|
|
3789
|
-
|
|
3790
3785
|
// src/generated/gladia/schema/transcriptionControllerListV2KindItem.ts
|
|
3791
3786
|
var TranscriptionControllerListV2KindItem = {
|
|
3792
3787
|
"pre-recorded": "pre-recorded",
|
|
3793
3788
|
live: "live"
|
|
3794
3789
|
};
|
|
3795
3790
|
|
|
3791
|
+
// src/generated/gladia/schema/transcriptMessageType.ts
|
|
3792
|
+
var TranscriptMessageType = {
|
|
3793
|
+
transcript: "transcript"
|
|
3794
|
+
};
|
|
3795
|
+
|
|
3796
3796
|
// src/generated/gladia/schema/translationMessageType.ts
|
|
3797
3797
|
var TranslationMessageType = {
|
|
3798
3798
|
translation: "translation"
|
|
@@ -4064,7 +4064,7 @@ var WebhookTranscriptionSuccessPayloadEvent = {
|
|
|
4064
4064
|
|
|
4065
4065
|
// src/generated/gladia/api/gladiaControlAPI.ts
|
|
4066
4066
|
var preRecordedControllerInitPreRecordedJobV2 = (initTranscriptionRequest, options) => {
|
|
4067
|
-
return axios.post(
|
|
4067
|
+
return axios.post("/v2/pre-recorded", initTranscriptionRequest, options);
|
|
4068
4068
|
};
|
|
4069
4069
|
var preRecordedControllerGetPreRecordedJobV2 = (id, options) => {
|
|
4070
4070
|
return axios.get(`/v2/pre-recorded/${id}`, options);
|
|
@@ -4079,13 +4079,13 @@ var preRecordedControllerGetAudioV2 = (id, options) => {
|
|
|
4079
4079
|
});
|
|
4080
4080
|
};
|
|
4081
4081
|
var transcriptionControllerListV2 = (params, options) => {
|
|
4082
|
-
return axios.get(
|
|
4082
|
+
return axios.get("/v2/transcription", {
|
|
4083
4083
|
...options,
|
|
4084
4084
|
params: { ...params, ...options?.params }
|
|
4085
4085
|
});
|
|
4086
4086
|
};
|
|
4087
4087
|
var streamingControllerInitStreamingSessionV2 = (streamingRequest, params, options) => {
|
|
4088
|
-
return axios.post(
|
|
4088
|
+
return axios.post("/v2/live", streamingRequest, {
|
|
4089
4089
|
...options,
|
|
4090
4090
|
params: { ...params, ...options?.params }
|
|
4091
4091
|
});
|
|
@@ -4351,7 +4351,6 @@ var GladiaAdapter = class extends BaseAdapter {
|
|
|
4351
4351
|
sentiment: result?.sentiment_analysis || void 0,
|
|
4352
4352
|
audioToLlm: result?.audio_to_llm || void 0,
|
|
4353
4353
|
chapters: result?.chapterization || void 0,
|
|
4354
|
-
speakerReidentification: result?.speaker_reidentification || void 0,
|
|
4355
4354
|
structuredData: result?.structured_data_extraction || void 0,
|
|
4356
4355
|
customMetadata: response.custom_metadata || void 0
|
|
4357
4356
|
},
|
|
@@ -5413,17 +5412,17 @@ var PiiPolicy = {
|
|
|
5413
5412
|
zodiac_sign: "zodiac_sign"
|
|
5414
5413
|
};
|
|
5415
5414
|
|
|
5415
|
+
// src/generated/assemblyai/schema/redactedAudioStatus.ts
|
|
5416
|
+
var RedactedAudioStatus = {
|
|
5417
|
+
redacted_audio_ready: "redacted_audio_ready"
|
|
5418
|
+
};
|
|
5419
|
+
|
|
5416
5420
|
// src/generated/assemblyai/schema/redactPiiAudioQuality.ts
|
|
5417
5421
|
var RedactPiiAudioQuality = {
|
|
5418
5422
|
mp3: "mp3",
|
|
5419
5423
|
wav: "wav"
|
|
5420
5424
|
};
|
|
5421
5425
|
|
|
5422
|
-
// src/generated/assemblyai/schema/redactedAudioStatus.ts
|
|
5423
|
-
var RedactedAudioStatus = {
|
|
5424
|
-
redacted_audio_ready: "redacted_audio_ready"
|
|
5425
|
-
};
|
|
5426
|
-
|
|
5427
5426
|
// src/generated/assemblyai/schema/sentiment.ts
|
|
5428
5427
|
var Sentiment = {
|
|
5429
5428
|
POSITIVE: "POSITIVE",
|
|
@@ -5487,10 +5486,10 @@ var TranscriptRemoveAudioTags = {
|
|
|
5487
5486
|
|
|
5488
5487
|
// src/generated/assemblyai/api/assemblyAIAPI.ts
|
|
5489
5488
|
var createTranscript = (transcriptParams, options) => {
|
|
5490
|
-
return axios2.post(
|
|
5489
|
+
return axios2.post("/v2/transcript", transcriptParams, options);
|
|
5491
5490
|
};
|
|
5492
5491
|
var listTranscripts = (params, options) => {
|
|
5493
|
-
return axios2.get(
|
|
5492
|
+
return axios2.get("/v2/transcript", {
|
|
5494
5493
|
...options,
|
|
5495
5494
|
params: { ...params, ...options?.params }
|
|
5496
5495
|
});
|
|
@@ -5900,22 +5899,22 @@ var AssemblyAIAdapter = class extends BaseAdapter {
|
|
|
5900
5899
|
normalizeResponse(response) {
|
|
5901
5900
|
let status;
|
|
5902
5901
|
switch (response.status) {
|
|
5903
|
-
case
|
|
5902
|
+
case TranscriptStatus.queued:
|
|
5904
5903
|
status = "queued";
|
|
5905
5904
|
break;
|
|
5906
|
-
case
|
|
5905
|
+
case TranscriptStatus.processing:
|
|
5907
5906
|
status = "processing";
|
|
5908
5907
|
break;
|
|
5909
|
-
case
|
|
5908
|
+
case TranscriptStatus.completed:
|
|
5910
5909
|
status = "completed";
|
|
5911
5910
|
break;
|
|
5912
|
-
case
|
|
5911
|
+
case TranscriptStatus.error:
|
|
5913
5912
|
status = "error";
|
|
5914
5913
|
break;
|
|
5915
5914
|
default:
|
|
5916
5915
|
status = "queued";
|
|
5917
5916
|
}
|
|
5918
|
-
if (response.status ===
|
|
5917
|
+
if (response.status === TranscriptStatus.error) {
|
|
5919
5918
|
return {
|
|
5920
5919
|
success: false,
|
|
5921
5920
|
provider: this.name,
|
|
@@ -7627,13 +7626,13 @@ var TextNormalizationKind = {
|
|
|
7627
7626
|
|
|
7628
7627
|
// src/generated/azure/api/speechServicesAPIVersion32.ts
|
|
7629
7628
|
var transcriptionsList = (params, options) => {
|
|
7630
|
-
return axios4.get(
|
|
7629
|
+
return axios4.get("/transcriptions", {
|
|
7631
7630
|
...options,
|
|
7632
7631
|
params: { ...params, ...options?.params }
|
|
7633
7632
|
});
|
|
7634
7633
|
};
|
|
7635
7634
|
var transcriptionsCreate = (transcription, options) => {
|
|
7636
|
-
return axios4.post(
|
|
7635
|
+
return axios4.post("/transcriptions", transcription, options);
|
|
7637
7636
|
};
|
|
7638
7637
|
var transcriptionsGet = (id, options) => {
|
|
7639
7638
|
return axios4.get(`/transcriptions/${id}`, options);
|
|
@@ -7648,13 +7647,13 @@ var transcriptionsListFiles = (id, params, options) => {
|
|
|
7648
7647
|
});
|
|
7649
7648
|
};
|
|
7650
7649
|
var webHooksList = (params, options) => {
|
|
7651
|
-
return axios4.get(
|
|
7650
|
+
return axios4.get("/webhooks", {
|
|
7652
7651
|
...options,
|
|
7653
7652
|
params: { ...params, ...options?.params }
|
|
7654
7653
|
});
|
|
7655
7654
|
};
|
|
7656
7655
|
var webHooksCreate = (webHook, options) => {
|
|
7657
|
-
return axios4.post(
|
|
7656
|
+
return axios4.post("/webhooks", webHook, options);
|
|
7658
7657
|
};
|
|
7659
7658
|
var webHooksDelete = (id, options) => {
|
|
7660
7659
|
return axios4.delete(`/webhooks/${id}`, options);
|
|
@@ -7782,7 +7781,7 @@ var AzureSTTAdapter = class extends BaseAdapter {
|
|
|
7782
7781
|
this.getAxiosConfig()
|
|
7783
7782
|
);
|
|
7784
7783
|
const files = filesResponse.data?.values || [];
|
|
7785
|
-
const resultFile = files.find((file) => file.kind ===
|
|
7784
|
+
const resultFile = files.find((file) => file.kind === FileKind.Transcription);
|
|
7786
7785
|
if (!resultFile?.links?.contentUrl) {
|
|
7787
7786
|
return {
|
|
7788
7787
|
success: false,
|
|
@@ -8006,15 +8005,20 @@ var AzureSTTAdapter = class extends BaseAdapter {
|
|
|
8006
8005
|
return properties;
|
|
8007
8006
|
}
|
|
8008
8007
|
/**
|
|
8009
|
-
* Normalize Azure status to unified status
|
|
8008
|
+
* Normalize Azure status to unified status using generated AzureStatus constants
|
|
8010
8009
|
*/
|
|
8011
8010
|
normalizeStatus(status) {
|
|
8012
|
-
|
|
8013
|
-
|
|
8014
|
-
|
|
8015
|
-
|
|
8016
|
-
|
|
8017
|
-
|
|
8011
|
+
switch (status) {
|
|
8012
|
+
case Status.Succeeded:
|
|
8013
|
+
return "completed";
|
|
8014
|
+
case Status.Running:
|
|
8015
|
+
return "processing";
|
|
8016
|
+
case Status.Failed:
|
|
8017
|
+
return "error";
|
|
8018
|
+
case Status.NotStarted:
|
|
8019
|
+
default:
|
|
8020
|
+
return "queued";
|
|
8021
|
+
}
|
|
8018
8022
|
}
|
|
8019
8023
|
/**
|
|
8020
8024
|
* Normalize Azure transcription response to unified format
|
|
@@ -8134,30 +8138,30 @@ function getAzureOpenAIRealtimeUrl(endpoint, deployment, apiVersion = "2024-10-0
|
|
|
8134
8138
|
import axios6 from "axios";
|
|
8135
8139
|
var createTranscription = (createTranscriptionRequest, options) => {
|
|
8136
8140
|
const formData = new FormData();
|
|
8137
|
-
formData.append(
|
|
8138
|
-
formData.append(
|
|
8141
|
+
formData.append("file", createTranscriptionRequest.file);
|
|
8142
|
+
formData.append("model", createTranscriptionRequest.model);
|
|
8139
8143
|
if (createTranscriptionRequest.language !== void 0) {
|
|
8140
|
-
formData.append(
|
|
8144
|
+
formData.append("language", createTranscriptionRequest.language);
|
|
8141
8145
|
}
|
|
8142
8146
|
if (createTranscriptionRequest.prompt !== void 0) {
|
|
8143
|
-
formData.append(
|
|
8147
|
+
formData.append("prompt", createTranscriptionRequest.prompt);
|
|
8144
8148
|
}
|
|
8145
8149
|
if (createTranscriptionRequest.response_format !== void 0) {
|
|
8146
|
-
formData.append(
|
|
8150
|
+
formData.append("response_format", createTranscriptionRequest.response_format);
|
|
8147
8151
|
}
|
|
8148
8152
|
if (createTranscriptionRequest.temperature !== void 0) {
|
|
8149
|
-
formData.append(
|
|
8153
|
+
formData.append("temperature", createTranscriptionRequest.temperature.toString());
|
|
8150
8154
|
}
|
|
8151
8155
|
if (createTranscriptionRequest.include !== void 0) {
|
|
8152
|
-
createTranscriptionRequest.include.forEach((value) => formData.append(
|
|
8156
|
+
createTranscriptionRequest.include.forEach((value) => formData.append("include", value));
|
|
8153
8157
|
}
|
|
8154
8158
|
if (createTranscriptionRequest.timestamp_granularities !== void 0) {
|
|
8155
8159
|
createTranscriptionRequest.timestamp_granularities.forEach(
|
|
8156
|
-
(value) => formData.append(
|
|
8160
|
+
(value) => formData.append("timestamp_granularities", value)
|
|
8157
8161
|
);
|
|
8158
8162
|
}
|
|
8159
8163
|
if (createTranscriptionRequest.stream !== void 0 && createTranscriptionRequest.stream !== null) {
|
|
8160
|
-
formData.append(
|
|
8164
|
+
formData.append("stream", createTranscriptionRequest.stream.toString());
|
|
8161
8165
|
}
|
|
8162
8166
|
if (createTranscriptionRequest.chunking_strategy !== void 0 && createTranscriptionRequest.chunking_strategy !== null) {
|
|
8163
8167
|
formData.append(
|
|
@@ -8167,15 +8171,15 @@ var createTranscription = (createTranscriptionRequest, options) => {
|
|
|
8167
8171
|
}
|
|
8168
8172
|
if (createTranscriptionRequest.known_speaker_names !== void 0) {
|
|
8169
8173
|
createTranscriptionRequest.known_speaker_names.forEach(
|
|
8170
|
-
(value) => formData.append(
|
|
8174
|
+
(value) => formData.append("known_speaker_names", value)
|
|
8171
8175
|
);
|
|
8172
8176
|
}
|
|
8173
8177
|
if (createTranscriptionRequest.known_speaker_references !== void 0) {
|
|
8174
8178
|
createTranscriptionRequest.known_speaker_references.forEach(
|
|
8175
|
-
(value) => formData.append(
|
|
8179
|
+
(value) => formData.append("known_speaker_references", value)
|
|
8176
8180
|
);
|
|
8177
8181
|
}
|
|
8178
|
-
return axios6.post(
|
|
8182
|
+
return axios6.post("/audio/transcriptions", formData, options);
|
|
8179
8183
|
};
|
|
8180
8184
|
|
|
8181
8185
|
// src/generated/openai/schema/createTranscriptionRequestTimestampGranularitiesItem.ts
|
|
@@ -8264,7 +8268,7 @@ var OpenAIWhisperAdapter = class extends BaseAdapter {
|
|
|
8264
8268
|
const request = {
|
|
8265
8269
|
...options?.openai,
|
|
8266
8270
|
file: audioData,
|
|
8267
|
-
//
|
|
8271
|
+
// Buffer/Blob both accepted at runtime; generated type expects Blob
|
|
8268
8272
|
model
|
|
8269
8273
|
};
|
|
8270
8274
|
if (options?.language) {
|
|
@@ -8284,7 +8288,11 @@ var OpenAIWhisperAdapter = class extends BaseAdapter {
|
|
|
8284
8288
|
request.response_format = OpenAIResponseFormat.json;
|
|
8285
8289
|
}
|
|
8286
8290
|
const response = await createTranscription(request, this.getAxiosConfig());
|
|
8287
|
-
return this.normalizeResponse(
|
|
8291
|
+
return this.normalizeResponse(
|
|
8292
|
+
response.data,
|
|
8293
|
+
model,
|
|
8294
|
+
isDiarization
|
|
8295
|
+
);
|
|
8288
8296
|
} catch (error) {
|
|
8289
8297
|
return this.createErrorResponse(error);
|
|
8290
8298
|
}
|
|
@@ -9004,8 +9012,16 @@ var SpeechmaticsAdapter = class extends BaseAdapter {
|
|
|
9004
9012
|
if (this.config?.wsBaseUrl) {
|
|
9005
9013
|
return this.config.wsBaseUrl;
|
|
9006
9014
|
}
|
|
9007
|
-
const
|
|
9008
|
-
|
|
9015
|
+
const rtRegionMap = {
|
|
9016
|
+
eu1: "eu",
|
|
9017
|
+
eu2: "eu",
|
|
9018
|
+
us1: "us",
|
|
9019
|
+
us2: "us",
|
|
9020
|
+
au1: "eu"
|
|
9021
|
+
// No AU RT endpoint — fall back to EU
|
|
9022
|
+
};
|
|
9023
|
+
const rtPrefix = rtRegionMap[region || ""] || "eu";
|
|
9024
|
+
return `wss://${rtPrefix}.rt.speechmatics.com/v2`;
|
|
9009
9025
|
}
|
|
9010
9026
|
/**
|
|
9011
9027
|
* Stream audio for real-time transcription via WebSocket
|
|
@@ -9614,8 +9630,23 @@ var SonioxAdapter = class extends BaseAdapter {
|
|
|
9614
9630
|
terms: options.customVocabulary
|
|
9615
9631
|
};
|
|
9616
9632
|
}
|
|
9633
|
+
if (options?.webhookUrl) {
|
|
9634
|
+
requestBody.webhook_url = options.webhookUrl;
|
|
9635
|
+
}
|
|
9617
9636
|
const response = await this.client.post("/transcriptions", requestBody);
|
|
9618
9637
|
const transcriptionId = response.data.id;
|
|
9638
|
+
if (options?.webhookUrl) {
|
|
9639
|
+
return {
|
|
9640
|
+
success: true,
|
|
9641
|
+
provider: this.name,
|
|
9642
|
+
data: {
|
|
9643
|
+
id: transcriptionId,
|
|
9644
|
+
text: "",
|
|
9645
|
+
status: "queued"
|
|
9646
|
+
},
|
|
9647
|
+
raw: response.data
|
|
9648
|
+
};
|
|
9649
|
+
}
|
|
9619
9650
|
return await this.pollForCompletion(transcriptionId);
|
|
9620
9651
|
} catch (error) {
|
|
9621
9652
|
return this.createErrorResponse(error);
|
|
@@ -9960,7 +9991,7 @@ var SonioxAdapter = class extends BaseAdapter {
|
|
|
9960
9991
|
start: token.start_ms ? token.start_ms / 1e3 : 0,
|
|
9961
9992
|
end: token.end_ms ? token.end_ms / 1e3 : 0,
|
|
9962
9993
|
confidence: token.confidence,
|
|
9963
|
-
speaker: token.speaker
|
|
9994
|
+
speaker: token.speaker ?? void 0
|
|
9964
9995
|
}));
|
|
9965
9996
|
return buildUtterancesFromWords(words);
|
|
9966
9997
|
}
|
|
@@ -9968,29 +9999,24 @@ var SonioxAdapter = class extends BaseAdapter {
|
|
|
9968
9999
|
* Normalize Soniox response to unified format
|
|
9969
10000
|
*/
|
|
9970
10001
|
normalizeResponse(response) {
|
|
9971
|
-
const
|
|
9972
|
-
const words =
|
|
9973
|
-
(t) => t.is_final !== false && t.start_ms !== void 0 && t.end_ms !== void 0
|
|
9974
|
-
).map((token) => ({
|
|
10002
|
+
const { text, tokens } = response;
|
|
10003
|
+
const words = tokens.map((token) => ({
|
|
9975
10004
|
word: token.text,
|
|
9976
10005
|
start: token.start_ms / 1e3,
|
|
9977
10006
|
end: token.end_ms / 1e3,
|
|
9978
10007
|
confidence: token.confidence,
|
|
9979
|
-
speaker: token.speaker
|
|
9980
|
-
}))
|
|
10008
|
+
speaker: token.speaker ?? void 0
|
|
10009
|
+
}));
|
|
9981
10010
|
const speakerSet = /* @__PURE__ */ new Set();
|
|
9982
|
-
|
|
9983
|
-
|
|
9984
|
-
if (t.speaker) speakerSet.add(t.speaker);
|
|
9985
|
-
});
|
|
10011
|
+
for (const token of tokens) {
|
|
10012
|
+
if (token.speaker) speakerSet.add(token.speaker);
|
|
9986
10013
|
}
|
|
9987
10014
|
const speakers = speakerSet.size > 0 ? Array.from(speakerSet).map((id) => ({
|
|
9988
10015
|
id,
|
|
9989
10016
|
label: `Speaker ${id}`
|
|
9990
10017
|
})) : void 0;
|
|
9991
|
-
const tokens = response.tokens ? response.tokens.filter((t) => t.is_final !== false) : [];
|
|
9992
10018
|
const utterances = tokens.length > 0 ? this.buildUtterancesFromTokens(tokens) : [];
|
|
9993
|
-
const language =
|
|
10019
|
+
const language = tokens.find((t) => t.language)?.language ?? void 0;
|
|
9994
10020
|
return {
|
|
9995
10021
|
success: true,
|
|
9996
10022
|
provider: this.name,
|
|
@@ -10164,11 +10190,29 @@ var ElevenLabsAdapter = class extends BaseAdapter {
|
|
|
10164
10190
|
}
|
|
10165
10191
|
}
|
|
10166
10192
|
}
|
|
10193
|
+
if (options?.webhookUrl) {
|
|
10194
|
+
if (!formData.has("webhook")) {
|
|
10195
|
+
formData.append("webhook", "true");
|
|
10196
|
+
}
|
|
10197
|
+
}
|
|
10167
10198
|
const response = await this.client.post("/v1/speech-to-text", formData, {
|
|
10168
10199
|
headers: {
|
|
10169
10200
|
"Content-Type": "multipart/form-data"
|
|
10170
10201
|
}
|
|
10171
10202
|
});
|
|
10203
|
+
if (options?.webhookUrl) {
|
|
10204
|
+
const transcriptionId = response.data.transcription_id || response.data.id || `elevenlabs_${Date.now()}`;
|
|
10205
|
+
return {
|
|
10206
|
+
success: true,
|
|
10207
|
+
provider: this.name,
|
|
10208
|
+
data: {
|
|
10209
|
+
id: transcriptionId,
|
|
10210
|
+
text: "",
|
|
10211
|
+
status: "queued"
|
|
10212
|
+
},
|
|
10213
|
+
raw: response.data
|
|
10214
|
+
};
|
|
10215
|
+
}
|
|
10172
10216
|
return this.normalizeResponse(response.data);
|
|
10173
10217
|
} catch (error) {
|
|
10174
10218
|
return this.createErrorResponse(error);
|
|
@@ -10432,7 +10476,7 @@ var ElevenLabsAdapter = class extends BaseAdapter {
|
|
|
10432
10476
|
* - Multi-channel: `MultichannelSpeechToTextResponseModel` with `transcripts[]`
|
|
10433
10477
|
*/
|
|
10434
10478
|
normalizeResponse(response) {
|
|
10435
|
-
const chunks =
|
|
10479
|
+
const chunks = "transcripts" in response ? response.transcripts : [response];
|
|
10436
10480
|
const text = chunks.map((c) => c.text).join(" ");
|
|
10437
10481
|
const words = [];
|
|
10438
10482
|
const speakerSet = /* @__PURE__ */ new Set();
|
|
@@ -10482,7 +10526,7 @@ var ElevenLabsAdapter = class extends BaseAdapter {
|
|
|
10482
10526
|
}
|
|
10483
10527
|
}
|
|
10484
10528
|
}
|
|
10485
|
-
const transcriptionId = response.transcription_id || chunks[0]?.transcription_id || `elevenlabs_${Date.now()}`;
|
|
10529
|
+
const transcriptionId = ("transcription_id" in response ? response.transcription_id : response.transcription_id) || chunks[0]?.transcription_id || `elevenlabs_${Date.now()}`;
|
|
10486
10530
|
return {
|
|
10487
10531
|
success: true,
|
|
10488
10532
|
provider: this.name,
|
|
@@ -10826,9 +10870,7 @@ var listenTranscribeQueryParams = zod.object({
|
|
|
10826
10870
|
),
|
|
10827
10871
|
dictation: zod.boolean().optional().describe("Dictation mode for controlling formatting with dictated speech"),
|
|
10828
10872
|
encoding: zod.enum(["linear16", "flac", "mulaw", "amr-nb", "amr-wb", "opus", "speex", "g729"]).optional().describe("Specify the expected encoding of your submitted audio"),
|
|
10829
|
-
filler_words: zod.boolean().optional().describe(
|
|
10830
|
-
'Filler Words can help transcribe interruptions in your audio, like "uh" and "um"'
|
|
10831
|
-
),
|
|
10873
|
+
filler_words: zod.boolean().optional().describe('Filler Words can help transcribe interruptions in your audio, like "uh" and "um"'),
|
|
10832
10874
|
keyterm: zod.array(zod.string()).optional().describe(
|
|
10833
10875
|
"Key term prompting can boost or suppress specialized terminology and brands. Only compatible with Nova-3"
|
|
10834
10876
|
),
|
|
@@ -11532,6 +11574,7 @@ __export(assemblyAIAPI_zod_exports, {
|
|
|
11532
11574
|
createTranscriptBodySpeechUnderstandingRequestTranslationFormalDefault: () => createTranscriptBodySpeechUnderstandingRequestTranslationFormalDefault,
|
|
11533
11575
|
createTranscriptBodySpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault: () => createTranscriptBodySpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault,
|
|
11534
11576
|
createTranscriptBodySummarizationDefault: () => createTranscriptBodySummarizationDefault,
|
|
11577
|
+
createTranscriptBodyTemperatureDefault: () => createTranscriptBodyTemperatureDefault,
|
|
11535
11578
|
createTranscriptResponse: () => createTranscriptResponse,
|
|
11536
11579
|
createTranscriptResponseLanguageDetectionOptionsCodeSwitchingConfidenceThresholdDefault: () => createTranscriptResponseLanguageDetectionOptionsCodeSwitchingConfidenceThresholdDefault,
|
|
11537
11580
|
createTranscriptResponseLanguageDetectionOptionsCodeSwitchingDefault: () => createTranscriptResponseLanguageDetectionOptionsCodeSwitchingDefault,
|
|
@@ -11601,6 +11644,7 @@ var createTranscriptBodySpeakerOptionsMinSpeakersExpectedDefault = 1;
|
|
|
11601
11644
|
var createTranscriptBodySpeechUnderstandingRequestTranslationFormalDefault = true;
|
|
11602
11645
|
var createTranscriptBodySpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault = false;
|
|
11603
11646
|
var createTranscriptBodySummarizationDefault = false;
|
|
11647
|
+
var createTranscriptBodyTemperatureDefault = 0;
|
|
11604
11648
|
var createTranscriptBodyCustomTopicsDefault = false;
|
|
11605
11649
|
var createTranscriptBody = zod3.object({
|
|
11606
11650
|
audio_end_at: zod3.number().optional().describe(
|
|
@@ -11610,10 +11654,10 @@ var createTranscriptBody = zod3.object({
|
|
|
11610
11654
|
"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."
|
|
11611
11655
|
),
|
|
11612
11656
|
auto_chapters: zod3.boolean().optional().describe(
|
|
11613
|
-
"Enable [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/
|
|
11657
|
+
"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"
|
|
11614
11658
|
),
|
|
11615
11659
|
auto_highlights: zod3.boolean().optional().describe(
|
|
11616
|
-
"Enable [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
11660
|
+
"Enable [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights), either true or false"
|
|
11617
11661
|
),
|
|
11618
11662
|
content_safety: zod3.boolean().optional().describe(
|
|
11619
11663
|
"Enable [Content Moderation](https://www.assemblyai.com/docs/content-moderation), can be true or false"
|
|
@@ -11629,16 +11673,16 @@ var createTranscriptBody = zod3.object({
|
|
|
11629
11673
|
"Object containing words or phrases to replace, and the word or phrase to replace with"
|
|
11630
11674
|
)
|
|
11631
11675
|
).optional().describe(
|
|
11632
|
-
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
11676
|
+
"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."
|
|
11633
11677
|
),
|
|
11634
11678
|
disfluencies: zod3.boolean().optional().describe(
|
|
11635
|
-
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/filler-words), like "umm", in your media file; can be true or false'
|
|
11679
|
+
'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'
|
|
11636
11680
|
),
|
|
11637
11681
|
domain: zod3.string().nullish().describe(
|
|
11638
11682
|
'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'
|
|
11639
11683
|
),
|
|
11640
11684
|
entity_detection: zod3.boolean().optional().describe(
|
|
11641
|
-
"Enable [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
11685
|
+
"Enable [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/detect-entities-in-transcript), can be true or false"
|
|
11642
11686
|
),
|
|
11643
11687
|
filter_profanity: zod3.boolean().optional().describe(
|
|
11644
11688
|
"Filter profanity from the transcribed text, can be true or false. See [Profanity Filtering](https://www.assemblyai.com/docs/profanity-filtering) for more details."
|
|
@@ -11647,7 +11691,7 @@ var createTranscriptBody = zod3.object({
|
|
|
11647
11691
|
"Enable [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio), can be true or false"
|
|
11648
11692
|
),
|
|
11649
11693
|
iab_categories: zod3.boolean().optional().describe(
|
|
11650
|
-
"Enable [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
11694
|
+
"Enable [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics), can be true or false"
|
|
11651
11695
|
),
|
|
11652
11696
|
keyterms_prompt: zod3.array(zod3.string()).optional().describe(
|
|
11653
11697
|
"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"
|
|
@@ -11895,7 +11939,7 @@ var createTranscriptBody = zod3.object({
|
|
|
11895
11939
|
"Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection)."
|
|
11896
11940
|
),
|
|
11897
11941
|
multichannel: zod3.boolean().optional().describe(
|
|
11898
|
-
"Enable [Multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
11942
|
+
"Enable [Multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) transcription, can be true or false."
|
|
11899
11943
|
),
|
|
11900
11944
|
prompt: zod3.string().optional().describe(
|
|
11901
11945
|
"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"
|
|
@@ -11978,23 +12022,23 @@ var createTranscriptBody = zod3.object({
|
|
|
11978
12022
|
"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."
|
|
11979
12023
|
),
|
|
11980
12024
|
sentiment_analysis: zod3.boolean().optional().describe(
|
|
11981
|
-
"Enable [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-
|
|
12025
|
+
"Enable [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/analyze-sentiment-of-speech), can be true or false"
|
|
11982
12026
|
),
|
|
11983
12027
|
speaker_labels: zod3.boolean().optional().describe(
|
|
11984
|
-
"Enable [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
12028
|
+
"Enable [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers), can be true or false"
|
|
11985
12029
|
),
|
|
11986
12030
|
speaker_options: zod3.object({
|
|
11987
12031
|
min_speakers_expected: zod3.number().default(createTranscriptBodySpeakerOptionsMinSpeakersExpectedDefault).describe(
|
|
11988
|
-
"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/
|
|
12032
|
+
"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."
|
|
11989
12033
|
),
|
|
11990
12034
|
max_speakers_expected: zod3.number().optional().describe(
|
|
11991
|
-
"<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/
|
|
12035
|
+
"<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"
|
|
11992
12036
|
)
|
|
11993
12037
|
}).optional().describe(
|
|
11994
|
-
"Specify options for [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
12038
|
+
"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."
|
|
11995
12039
|
),
|
|
11996
12040
|
speakers_expected: zod3.number().nullish().describe(
|
|
11997
|
-
"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/
|
|
12041
|
+
"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."
|
|
11998
12042
|
),
|
|
11999
12043
|
speech_models: zod3.array(
|
|
12000
12044
|
zod3.string().describe(
|
|
@@ -12070,7 +12114,7 @@ var createTranscriptBody = zod3.object({
|
|
|
12070
12114
|
"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"
|
|
12071
12115
|
),
|
|
12072
12116
|
summarization: zod3.boolean().optional().describe(
|
|
12073
|
-
"Enable [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
12117
|
+
"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"
|
|
12074
12118
|
),
|
|
12075
12119
|
summary_model: zod3.enum(["informative", "conversational", "catchy"]).optional().describe("The model to summarize the transcript"),
|
|
12076
12120
|
summary_type: zod3.enum(["bullets", "bullets_verbose", "gist", "headline", "paragraph"]).optional().describe("The type of summary"),
|
|
@@ -12079,6 +12123,9 @@ var createTranscriptBody = zod3.object({
|
|
|
12079
12123
|
).or(zod3.null()).optional().describe(
|
|
12080
12124
|
'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'
|
|
12081
12125
|
),
|
|
12126
|
+
temperature: zod3.number().optional().describe(
|
|
12127
|
+
"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"
|
|
12128
|
+
),
|
|
12082
12129
|
webhook_auth_header_name: zod3.string().nullish().describe(
|
|
12083
12130
|
"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"
|
|
12084
12131
|
),
|
|
@@ -12100,7 +12147,7 @@ var createTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault =
|
|
|
12100
12147
|
var createTranscriptResponseSpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault = false;
|
|
12101
12148
|
var createTranscriptResponse = zod3.object({
|
|
12102
12149
|
audio_channels: zod3.number().optional().describe(
|
|
12103
|
-
"The number of audio channels in the audio file. This is only present when [multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
12150
|
+
"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."
|
|
12104
12151
|
),
|
|
12105
12152
|
audio_duration: zod3.number().nullish().describe("The duration of this transcript object's media file, in seconds"),
|
|
12106
12153
|
audio_end_at: zod3.number().nullish().describe(
|
|
@@ -12111,10 +12158,10 @@ var createTranscriptResponse = zod3.object({
|
|
|
12111
12158
|
),
|
|
12112
12159
|
audio_url: zod3.string().describe("The URL of the media that was transcribed"),
|
|
12113
12160
|
auto_chapters: zod3.boolean().nullish().describe(
|
|
12114
|
-
"Whether [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/
|
|
12161
|
+
"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"
|
|
12115
12162
|
),
|
|
12116
12163
|
auto_highlights: zod3.boolean().describe(
|
|
12117
|
-
"Whether [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
12164
|
+
"Whether [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights) is enabled, either true or false"
|
|
12118
12165
|
),
|
|
12119
12166
|
auto_highlights_result: zod3.object({
|
|
12120
12167
|
status: zod3.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -12134,9 +12181,9 @@ var createTranscriptResponse = zod3.object({
|
|
|
12134
12181
|
})
|
|
12135
12182
|
).describe("A temporally-sequential array of Key Phrases")
|
|
12136
12183
|
}).describe(
|
|
12137
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
12184
|
+
"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"
|
|
12138
12185
|
).or(zod3.null()).optional().describe(
|
|
12139
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
12186
|
+
"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"
|
|
12140
12187
|
),
|
|
12141
12188
|
chapters: zod3.array(
|
|
12142
12189
|
zod3.object({
|
|
@@ -12149,7 +12196,7 @@ var createTranscriptResponse = zod3.object({
|
|
|
12149
12196
|
end: zod3.number().describe("The starting time, in milliseconds, for the chapter")
|
|
12150
12197
|
}).describe("Chapter of the audio file")
|
|
12151
12198
|
).nullish().describe(
|
|
12152
|
-
"An array of temporally sequential chapters for the audio file. See [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/
|
|
12199
|
+
"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."
|
|
12153
12200
|
),
|
|
12154
12201
|
confidence: zod3.number().nullish().describe(
|
|
12155
12202
|
"The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence)"
|
|
@@ -12205,10 +12252,10 @@ var createTranscriptResponse = zod3.object({
|
|
|
12205
12252
|
"Object containing words or phrases to replace, and the word or phrase to replace with"
|
|
12206
12253
|
)
|
|
12207
12254
|
).nullish().describe(
|
|
12208
|
-
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
12255
|
+
"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."
|
|
12209
12256
|
),
|
|
12210
12257
|
disfluencies: zod3.boolean().nullish().describe(
|
|
12211
|
-
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/filler-words), like "umm", in your media file; can be true or false'
|
|
12258
|
+
'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'
|
|
12212
12259
|
),
|
|
12213
12260
|
domain: zod3.string().nullish().describe(
|
|
12214
12261
|
'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'
|
|
@@ -12270,10 +12317,10 @@ var createTranscriptResponse = zod3.object({
|
|
|
12270
12317
|
)
|
|
12271
12318
|
}).describe("A detected entity")
|
|
12272
12319
|
).nullish().describe(
|
|
12273
|
-
"An array of results for the Entity Detection model, if it is enabled.\nSee [Entity detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
12320
|
+
"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"
|
|
12274
12321
|
),
|
|
12275
12322
|
entity_detection: zod3.boolean().nullish().describe(
|
|
12276
|
-
"Whether [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
12323
|
+
"Whether [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/detect-entities-in-transcript) is enabled, can be true or false"
|
|
12277
12324
|
),
|
|
12278
12325
|
error: zod3.string().optional().describe("Error message of why the transcript failed"),
|
|
12279
12326
|
filter_profanity: zod3.boolean().nullish().describe(
|
|
@@ -12283,7 +12330,7 @@ var createTranscriptResponse = zod3.object({
|
|
|
12283
12330
|
"Whether [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio) is enabled, either true or false"
|
|
12284
12331
|
),
|
|
12285
12332
|
iab_categories: zod3.boolean().nullish().describe(
|
|
12286
|
-
"Whether [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
12333
|
+
"Whether [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics) is enabled, can be true or false"
|
|
12287
12334
|
),
|
|
12288
12335
|
iab_categories_result: zod3.object({
|
|
12289
12336
|
status: zod3.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -12306,9 +12353,9 @@ var createTranscriptResponse = zod3.object({
|
|
|
12306
12353
|
).describe("An array of results for the Topic Detection model"),
|
|
12307
12354
|
summary: zod3.record(zod3.string(), zod3.number()).describe("The overall relevance of topic to the entire audio file")
|
|
12308
12355
|
}).describe(
|
|
12309
|
-
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
12356
|
+
"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"
|
|
12310
12357
|
).or(zod3.null()).optional().describe(
|
|
12311
|
-
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
12358
|
+
"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"
|
|
12312
12359
|
),
|
|
12313
12360
|
id: zod3.string().uuid().describe("The unique identifier of your transcript"),
|
|
12314
12361
|
keyterms_prompt: zod3.array(zod3.string()).optional().describe(
|
|
@@ -12558,7 +12605,7 @@ var createTranscriptResponse = zod3.object({
|
|
|
12558
12605
|
"Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection)."
|
|
12559
12606
|
),
|
|
12560
12607
|
multichannel: zod3.boolean().nullish().describe(
|
|
12561
|
-
"Whether [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
12608
|
+
"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"
|
|
12562
12609
|
),
|
|
12563
12610
|
prompt: zod3.string().optional().describe(
|
|
12564
12611
|
"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"
|
|
@@ -12641,7 +12688,7 @@ var createTranscriptResponse = zod3.object({
|
|
|
12641
12688
|
"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."
|
|
12642
12689
|
),
|
|
12643
12690
|
sentiment_analysis: zod3.boolean().nullish().describe(
|
|
12644
|
-
"Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-
|
|
12691
|
+
"Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/analyze-sentiment-of-speech) is enabled, can be true or false"
|
|
12645
12692
|
),
|
|
12646
12693
|
sentiment_analysis_results: zod3.array(
|
|
12647
12694
|
zod3.object({
|
|
@@ -12656,17 +12703,17 @@ var createTranscriptResponse = zod3.object({
|
|
|
12656
12703
|
"The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
12657
12704
|
),
|
|
12658
12705
|
speaker: zod3.string().nullable().describe(
|
|
12659
|
-
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
12706
|
+
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
12660
12707
|
)
|
|
12661
12708
|
}).describe("The result of the Sentiment Analysis model")
|
|
12662
12709
|
).nullish().describe(
|
|
12663
|
-
"An array of results for the Sentiment Analysis model, if it is enabled.\nSee [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-
|
|
12710
|
+
"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"
|
|
12664
12711
|
),
|
|
12665
12712
|
speaker_labels: zod3.boolean().nullish().describe(
|
|
12666
|
-
"Whether [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
12713
|
+
"Whether [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, can be true or false"
|
|
12667
12714
|
),
|
|
12668
12715
|
speakers_expected: zod3.number().nullish().describe(
|
|
12669
|
-
"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/
|
|
12716
|
+
"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."
|
|
12670
12717
|
),
|
|
12671
12718
|
speech_model_used: zod3.string().optional().describe(
|
|
12672
12719
|
"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."
|
|
@@ -12769,22 +12816,25 @@ var createTranscriptResponse = zod3.object({
|
|
|
12769
12816
|
"The status of your transcript. Possible values are queued, processing, completed, or error."
|
|
12770
12817
|
),
|
|
12771
12818
|
summarization: zod3.boolean().describe(
|
|
12772
|
-
"Whether [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
12819
|
+
"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"
|
|
12773
12820
|
),
|
|
12774
12821
|
summary: zod3.string().nullish().describe(
|
|
12775
|
-
"The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
12822
|
+
"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."
|
|
12776
12823
|
),
|
|
12777
12824
|
summary_model: zod3.string().nullish().describe(
|
|
12778
|
-
"The Summarization model used to generate the summary,\nif [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
12825
|
+
"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"
|
|
12779
12826
|
),
|
|
12780
12827
|
summary_type: zod3.string().nullish().describe(
|
|
12781
|
-
"The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
12828
|
+
"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."
|
|
12782
12829
|
),
|
|
12783
12830
|
remove_audio_tags: zod3.enum(["all"]).describe(
|
|
12784
12831
|
"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"
|
|
12785
12832
|
).or(zod3.null()).optional().describe(
|
|
12786
12833
|
"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"
|
|
12787
12834
|
),
|
|
12835
|
+
temperature: zod3.number().nullish().describe(
|
|
12836
|
+
"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"
|
|
12837
|
+
),
|
|
12788
12838
|
text: zod3.string().nullish().describe("The textual transcript of your media file"),
|
|
12789
12839
|
throttled: zod3.boolean().nullish().describe(
|
|
12790
12840
|
"True while a request is throttled and false when a request is no longer throttled"
|
|
@@ -12805,7 +12855,7 @@ var createTranscriptResponse = zod3.object({
|
|
|
12805
12855
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
12806
12856
|
),
|
|
12807
12857
|
speaker: zod3.string().nullable().describe(
|
|
12808
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
12858
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
12809
12859
|
)
|
|
12810
12860
|
})
|
|
12811
12861
|
).describe("The words in the utterance."),
|
|
@@ -12820,7 +12870,7 @@ var createTranscriptResponse = zod3.object({
|
|
|
12820
12870
|
)
|
|
12821
12871
|
})
|
|
12822
12872
|
).nullish().describe(
|
|
12823
|
-
"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/
|
|
12873
|
+
"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"
|
|
12824
12874
|
),
|
|
12825
12875
|
webhook_auth: zod3.boolean().describe(
|
|
12826
12876
|
"Whether [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) authentication details were provided"
|
|
@@ -12844,7 +12894,7 @@ var createTranscriptResponse = zod3.object({
|
|
|
12844
12894
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
12845
12895
|
),
|
|
12846
12896
|
speaker: zod3.string().nullable().describe(
|
|
12847
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
12897
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
12848
12898
|
)
|
|
12849
12899
|
})
|
|
12850
12900
|
).nullish().describe(
|
|
@@ -12917,7 +12967,7 @@ var getTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault = tr
|
|
|
12917
12967
|
var getTranscriptResponseSpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault = false;
|
|
12918
12968
|
var getTranscriptResponse = zod3.object({
|
|
12919
12969
|
audio_channels: zod3.number().optional().describe(
|
|
12920
|
-
"The number of audio channels in the audio file. This is only present when [multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
12970
|
+
"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."
|
|
12921
12971
|
),
|
|
12922
12972
|
audio_duration: zod3.number().nullish().describe("The duration of this transcript object's media file, in seconds"),
|
|
12923
12973
|
audio_end_at: zod3.number().nullish().describe(
|
|
@@ -12928,10 +12978,10 @@ var getTranscriptResponse = zod3.object({
|
|
|
12928
12978
|
),
|
|
12929
12979
|
audio_url: zod3.string().describe("The URL of the media that was transcribed"),
|
|
12930
12980
|
auto_chapters: zod3.boolean().nullish().describe(
|
|
12931
|
-
"Whether [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/
|
|
12981
|
+
"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"
|
|
12932
12982
|
),
|
|
12933
12983
|
auto_highlights: zod3.boolean().describe(
|
|
12934
|
-
"Whether [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
12984
|
+
"Whether [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights) is enabled, either true or false"
|
|
12935
12985
|
),
|
|
12936
12986
|
auto_highlights_result: zod3.object({
|
|
12937
12987
|
status: zod3.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -12951,9 +13001,9 @@ var getTranscriptResponse = zod3.object({
|
|
|
12951
13001
|
})
|
|
12952
13002
|
).describe("A temporally-sequential array of Key Phrases")
|
|
12953
13003
|
}).describe(
|
|
12954
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
13004
|
+
"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"
|
|
12955
13005
|
).or(zod3.null()).optional().describe(
|
|
12956
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
13006
|
+
"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"
|
|
12957
13007
|
),
|
|
12958
13008
|
chapters: zod3.array(
|
|
12959
13009
|
zod3.object({
|
|
@@ -12966,7 +13016,7 @@ var getTranscriptResponse = zod3.object({
|
|
|
12966
13016
|
end: zod3.number().describe("The starting time, in milliseconds, for the chapter")
|
|
12967
13017
|
}).describe("Chapter of the audio file")
|
|
12968
13018
|
).nullish().describe(
|
|
12969
|
-
"An array of temporally sequential chapters for the audio file. See [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/
|
|
13019
|
+
"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."
|
|
12970
13020
|
),
|
|
12971
13021
|
confidence: zod3.number().nullish().describe(
|
|
12972
13022
|
"The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence)"
|
|
@@ -13022,10 +13072,10 @@ var getTranscriptResponse = zod3.object({
|
|
|
13022
13072
|
"Object containing words or phrases to replace, and the word or phrase to replace with"
|
|
13023
13073
|
)
|
|
13024
13074
|
).nullish().describe(
|
|
13025
|
-
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
13075
|
+
"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."
|
|
13026
13076
|
),
|
|
13027
13077
|
disfluencies: zod3.boolean().nullish().describe(
|
|
13028
|
-
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/filler-words), like "umm", in your media file; can be true or false'
|
|
13078
|
+
'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'
|
|
13029
13079
|
),
|
|
13030
13080
|
domain: zod3.string().nullish().describe(
|
|
13031
13081
|
'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'
|
|
@@ -13087,10 +13137,10 @@ var getTranscriptResponse = zod3.object({
|
|
|
13087
13137
|
)
|
|
13088
13138
|
}).describe("A detected entity")
|
|
13089
13139
|
).nullish().describe(
|
|
13090
|
-
"An array of results for the Entity Detection model, if it is enabled.\nSee [Entity detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
13140
|
+
"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"
|
|
13091
13141
|
),
|
|
13092
13142
|
entity_detection: zod3.boolean().nullish().describe(
|
|
13093
|
-
"Whether [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
13143
|
+
"Whether [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/detect-entities-in-transcript) is enabled, can be true or false"
|
|
13094
13144
|
),
|
|
13095
13145
|
error: zod3.string().optional().describe("Error message of why the transcript failed"),
|
|
13096
13146
|
filter_profanity: zod3.boolean().nullish().describe(
|
|
@@ -13100,7 +13150,7 @@ var getTranscriptResponse = zod3.object({
|
|
|
13100
13150
|
"Whether [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio) is enabled, either true or false"
|
|
13101
13151
|
),
|
|
13102
13152
|
iab_categories: zod3.boolean().nullish().describe(
|
|
13103
|
-
"Whether [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
13153
|
+
"Whether [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics) is enabled, can be true or false"
|
|
13104
13154
|
),
|
|
13105
13155
|
iab_categories_result: zod3.object({
|
|
13106
13156
|
status: zod3.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -13123,9 +13173,9 @@ var getTranscriptResponse = zod3.object({
|
|
|
13123
13173
|
).describe("An array of results for the Topic Detection model"),
|
|
13124
13174
|
summary: zod3.record(zod3.string(), zod3.number()).describe("The overall relevance of topic to the entire audio file")
|
|
13125
13175
|
}).describe(
|
|
13126
|
-
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
13176
|
+
"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"
|
|
13127
13177
|
).or(zod3.null()).optional().describe(
|
|
13128
|
-
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
13178
|
+
"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"
|
|
13129
13179
|
),
|
|
13130
13180
|
id: zod3.string().uuid().describe("The unique identifier of your transcript"),
|
|
13131
13181
|
keyterms_prompt: zod3.array(zod3.string()).optional().describe(
|
|
@@ -13375,7 +13425,7 @@ var getTranscriptResponse = zod3.object({
|
|
|
13375
13425
|
"Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection)."
|
|
13376
13426
|
),
|
|
13377
13427
|
multichannel: zod3.boolean().nullish().describe(
|
|
13378
|
-
"Whether [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
13428
|
+
"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"
|
|
13379
13429
|
),
|
|
13380
13430
|
prompt: zod3.string().optional().describe(
|
|
13381
13431
|
"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"
|
|
@@ -13458,7 +13508,7 @@ var getTranscriptResponse = zod3.object({
|
|
|
13458
13508
|
"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."
|
|
13459
13509
|
),
|
|
13460
13510
|
sentiment_analysis: zod3.boolean().nullish().describe(
|
|
13461
|
-
"Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-
|
|
13511
|
+
"Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/analyze-sentiment-of-speech) is enabled, can be true or false"
|
|
13462
13512
|
),
|
|
13463
13513
|
sentiment_analysis_results: zod3.array(
|
|
13464
13514
|
zod3.object({
|
|
@@ -13473,17 +13523,17 @@ var getTranscriptResponse = zod3.object({
|
|
|
13473
13523
|
"The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
13474
13524
|
),
|
|
13475
13525
|
speaker: zod3.string().nullable().describe(
|
|
13476
|
-
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
13526
|
+
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
13477
13527
|
)
|
|
13478
13528
|
}).describe("The result of the Sentiment Analysis model")
|
|
13479
13529
|
).nullish().describe(
|
|
13480
|
-
"An array of results for the Sentiment Analysis model, if it is enabled.\nSee [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-
|
|
13530
|
+
"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"
|
|
13481
13531
|
),
|
|
13482
13532
|
speaker_labels: zod3.boolean().nullish().describe(
|
|
13483
|
-
"Whether [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
13533
|
+
"Whether [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, can be true or false"
|
|
13484
13534
|
),
|
|
13485
13535
|
speakers_expected: zod3.number().nullish().describe(
|
|
13486
|
-
"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/
|
|
13536
|
+
"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."
|
|
13487
13537
|
),
|
|
13488
13538
|
speech_model_used: zod3.string().optional().describe(
|
|
13489
13539
|
"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."
|
|
@@ -13586,22 +13636,25 @@ var getTranscriptResponse = zod3.object({
|
|
|
13586
13636
|
"The status of your transcript. Possible values are queued, processing, completed, or error."
|
|
13587
13637
|
),
|
|
13588
13638
|
summarization: zod3.boolean().describe(
|
|
13589
|
-
"Whether [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
13639
|
+
"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"
|
|
13590
13640
|
),
|
|
13591
13641
|
summary: zod3.string().nullish().describe(
|
|
13592
|
-
"The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
13642
|
+
"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."
|
|
13593
13643
|
),
|
|
13594
13644
|
summary_model: zod3.string().nullish().describe(
|
|
13595
|
-
"The Summarization model used to generate the summary,\nif [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
13645
|
+
"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"
|
|
13596
13646
|
),
|
|
13597
13647
|
summary_type: zod3.string().nullish().describe(
|
|
13598
|
-
"The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
13648
|
+
"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."
|
|
13599
13649
|
),
|
|
13600
13650
|
remove_audio_tags: zod3.enum(["all"]).describe(
|
|
13601
13651
|
"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"
|
|
13602
13652
|
).or(zod3.null()).optional().describe(
|
|
13603
13653
|
"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"
|
|
13604
13654
|
),
|
|
13655
|
+
temperature: zod3.number().nullish().describe(
|
|
13656
|
+
"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"
|
|
13657
|
+
),
|
|
13605
13658
|
text: zod3.string().nullish().describe("The textual transcript of your media file"),
|
|
13606
13659
|
throttled: zod3.boolean().nullish().describe(
|
|
13607
13660
|
"True while a request is throttled and false when a request is no longer throttled"
|
|
@@ -13622,7 +13675,7 @@ var getTranscriptResponse = zod3.object({
|
|
|
13622
13675
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
13623
13676
|
),
|
|
13624
13677
|
speaker: zod3.string().nullable().describe(
|
|
13625
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
13678
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
13626
13679
|
)
|
|
13627
13680
|
})
|
|
13628
13681
|
).describe("The words in the utterance."),
|
|
@@ -13637,7 +13690,7 @@ var getTranscriptResponse = zod3.object({
|
|
|
13637
13690
|
)
|
|
13638
13691
|
})
|
|
13639
13692
|
).nullish().describe(
|
|
13640
|
-
"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/
|
|
13693
|
+
"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"
|
|
13641
13694
|
),
|
|
13642
13695
|
webhook_auth: zod3.boolean().describe(
|
|
13643
13696
|
"Whether [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) authentication details were provided"
|
|
@@ -13661,7 +13714,7 @@ var getTranscriptResponse = zod3.object({
|
|
|
13661
13714
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
13662
13715
|
),
|
|
13663
13716
|
speaker: zod3.string().nullable().describe(
|
|
13664
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
13717
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
13665
13718
|
)
|
|
13666
13719
|
})
|
|
13667
13720
|
).nullish().describe(
|
|
@@ -13694,7 +13747,7 @@ var deleteTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault =
|
|
|
13694
13747
|
var deleteTranscriptResponseSpeechUnderstandingRequestTranslationMatchOriginalUtteranceDefault = false;
|
|
13695
13748
|
var deleteTranscriptResponse = zod3.object({
|
|
13696
13749
|
audio_channels: zod3.number().optional().describe(
|
|
13697
|
-
"The number of audio channels in the audio file. This is only present when [multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
13750
|
+
"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."
|
|
13698
13751
|
),
|
|
13699
13752
|
audio_duration: zod3.number().nullish().describe("The duration of this transcript object's media file, in seconds"),
|
|
13700
13753
|
audio_end_at: zod3.number().nullish().describe(
|
|
@@ -13705,10 +13758,10 @@ var deleteTranscriptResponse = zod3.object({
|
|
|
13705
13758
|
),
|
|
13706
13759
|
audio_url: zod3.string().describe("The URL of the media that was transcribed"),
|
|
13707
13760
|
auto_chapters: zod3.boolean().nullish().describe(
|
|
13708
|
-
"Whether [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/
|
|
13761
|
+
"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"
|
|
13709
13762
|
),
|
|
13710
13763
|
auto_highlights: zod3.boolean().describe(
|
|
13711
|
-
"Whether [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
13764
|
+
"Whether [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights) is enabled, either true or false"
|
|
13712
13765
|
),
|
|
13713
13766
|
auto_highlights_result: zod3.object({
|
|
13714
13767
|
status: zod3.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -13728,9 +13781,9 @@ var deleteTranscriptResponse = zod3.object({
|
|
|
13728
13781
|
})
|
|
13729
13782
|
).describe("A temporally-sequential array of Key Phrases")
|
|
13730
13783
|
}).describe(
|
|
13731
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
13784
|
+
"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"
|
|
13732
13785
|
).or(zod3.null()).optional().describe(
|
|
13733
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
13786
|
+
"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"
|
|
13734
13787
|
),
|
|
13735
13788
|
chapters: zod3.array(
|
|
13736
13789
|
zod3.object({
|
|
@@ -13743,7 +13796,7 @@ var deleteTranscriptResponse = zod3.object({
|
|
|
13743
13796
|
end: zod3.number().describe("The starting time, in milliseconds, for the chapter")
|
|
13744
13797
|
}).describe("Chapter of the audio file")
|
|
13745
13798
|
).nullish().describe(
|
|
13746
|
-
"An array of temporally sequential chapters for the audio file. See [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/
|
|
13799
|
+
"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."
|
|
13747
13800
|
),
|
|
13748
13801
|
confidence: zod3.number().nullish().describe(
|
|
13749
13802
|
"The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence)"
|
|
@@ -13799,10 +13852,10 @@ var deleteTranscriptResponse = zod3.object({
|
|
|
13799
13852
|
"Object containing words or phrases to replace, and the word or phrase to replace with"
|
|
13800
13853
|
)
|
|
13801
13854
|
).nullish().describe(
|
|
13802
|
-
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
13855
|
+
"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."
|
|
13803
13856
|
),
|
|
13804
13857
|
disfluencies: zod3.boolean().nullish().describe(
|
|
13805
|
-
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/filler-words), like "umm", in your media file; can be true or false'
|
|
13858
|
+
'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'
|
|
13806
13859
|
),
|
|
13807
13860
|
domain: zod3.string().nullish().describe(
|
|
13808
13861
|
'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'
|
|
@@ -13864,10 +13917,10 @@ var deleteTranscriptResponse = zod3.object({
|
|
|
13864
13917
|
)
|
|
13865
13918
|
}).describe("A detected entity")
|
|
13866
13919
|
).nullish().describe(
|
|
13867
|
-
"An array of results for the Entity Detection model, if it is enabled.\nSee [Entity detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
13920
|
+
"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"
|
|
13868
13921
|
),
|
|
13869
13922
|
entity_detection: zod3.boolean().nullish().describe(
|
|
13870
|
-
"Whether [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
13923
|
+
"Whether [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/detect-entities-in-transcript) is enabled, can be true or false"
|
|
13871
13924
|
),
|
|
13872
13925
|
error: zod3.string().optional().describe("Error message of why the transcript failed"),
|
|
13873
13926
|
filter_profanity: zod3.boolean().nullish().describe(
|
|
@@ -13877,7 +13930,7 @@ var deleteTranscriptResponse = zod3.object({
|
|
|
13877
13930
|
"Whether [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio) is enabled, either true or false"
|
|
13878
13931
|
),
|
|
13879
13932
|
iab_categories: zod3.boolean().nullish().describe(
|
|
13880
|
-
"Whether [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
13933
|
+
"Whether [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics) is enabled, can be true or false"
|
|
13881
13934
|
),
|
|
13882
13935
|
iab_categories_result: zod3.object({
|
|
13883
13936
|
status: zod3.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -13900,9 +13953,9 @@ var deleteTranscriptResponse = zod3.object({
|
|
|
13900
13953
|
).describe("An array of results for the Topic Detection model"),
|
|
13901
13954
|
summary: zod3.record(zod3.string(), zod3.number()).describe("The overall relevance of topic to the entire audio file")
|
|
13902
13955
|
}).describe(
|
|
13903
|
-
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
13956
|
+
"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"
|
|
13904
13957
|
).or(zod3.null()).optional().describe(
|
|
13905
|
-
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
13958
|
+
"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"
|
|
13906
13959
|
),
|
|
13907
13960
|
id: zod3.string().uuid().describe("The unique identifier of your transcript"),
|
|
13908
13961
|
keyterms_prompt: zod3.array(zod3.string()).optional().describe(
|
|
@@ -14152,7 +14205,7 @@ var deleteTranscriptResponse = zod3.object({
|
|
|
14152
14205
|
"Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection)."
|
|
14153
14206
|
),
|
|
14154
14207
|
multichannel: zod3.boolean().nullish().describe(
|
|
14155
|
-
"Whether [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
14208
|
+
"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"
|
|
14156
14209
|
),
|
|
14157
14210
|
prompt: zod3.string().optional().describe(
|
|
14158
14211
|
"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"
|
|
@@ -14235,7 +14288,7 @@ var deleteTranscriptResponse = zod3.object({
|
|
|
14235
14288
|
"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."
|
|
14236
14289
|
),
|
|
14237
14290
|
sentiment_analysis: zod3.boolean().nullish().describe(
|
|
14238
|
-
"Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-
|
|
14291
|
+
"Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/analyze-sentiment-of-speech) is enabled, can be true or false"
|
|
14239
14292
|
),
|
|
14240
14293
|
sentiment_analysis_results: zod3.array(
|
|
14241
14294
|
zod3.object({
|
|
@@ -14250,17 +14303,17 @@ var deleteTranscriptResponse = zod3.object({
|
|
|
14250
14303
|
"The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
14251
14304
|
),
|
|
14252
14305
|
speaker: zod3.string().nullable().describe(
|
|
14253
|
-
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
14306
|
+
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
14254
14307
|
)
|
|
14255
14308
|
}).describe("The result of the Sentiment Analysis model")
|
|
14256
14309
|
).nullish().describe(
|
|
14257
|
-
"An array of results for the Sentiment Analysis model, if it is enabled.\nSee [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-
|
|
14310
|
+
"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"
|
|
14258
14311
|
),
|
|
14259
14312
|
speaker_labels: zod3.boolean().nullish().describe(
|
|
14260
|
-
"Whether [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
14313
|
+
"Whether [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, can be true or false"
|
|
14261
14314
|
),
|
|
14262
14315
|
speakers_expected: zod3.number().nullish().describe(
|
|
14263
|
-
"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/
|
|
14316
|
+
"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."
|
|
14264
14317
|
),
|
|
14265
14318
|
speech_model_used: zod3.string().optional().describe(
|
|
14266
14319
|
"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."
|
|
@@ -14363,22 +14416,25 @@ var deleteTranscriptResponse = zod3.object({
|
|
|
14363
14416
|
"The status of your transcript. Possible values are queued, processing, completed, or error."
|
|
14364
14417
|
),
|
|
14365
14418
|
summarization: zod3.boolean().describe(
|
|
14366
|
-
"Whether [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
14419
|
+
"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"
|
|
14367
14420
|
),
|
|
14368
14421
|
summary: zod3.string().nullish().describe(
|
|
14369
|
-
"The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
14422
|
+
"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."
|
|
14370
14423
|
),
|
|
14371
14424
|
summary_model: zod3.string().nullish().describe(
|
|
14372
|
-
"The Summarization model used to generate the summary,\nif [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
14425
|
+
"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"
|
|
14373
14426
|
),
|
|
14374
14427
|
summary_type: zod3.string().nullish().describe(
|
|
14375
|
-
"The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
14428
|
+
"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."
|
|
14376
14429
|
),
|
|
14377
14430
|
remove_audio_tags: zod3.enum(["all"]).describe(
|
|
14378
14431
|
"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"
|
|
14379
14432
|
).or(zod3.null()).optional().describe(
|
|
14380
14433
|
"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"
|
|
14381
14434
|
),
|
|
14435
|
+
temperature: zod3.number().nullish().describe(
|
|
14436
|
+
"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"
|
|
14437
|
+
),
|
|
14382
14438
|
text: zod3.string().nullish().describe("The textual transcript of your media file"),
|
|
14383
14439
|
throttled: zod3.boolean().nullish().describe(
|
|
14384
14440
|
"True while a request is throttled and false when a request is no longer throttled"
|
|
@@ -14399,7 +14455,7 @@ var deleteTranscriptResponse = zod3.object({
|
|
|
14399
14455
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
14400
14456
|
),
|
|
14401
14457
|
speaker: zod3.string().nullable().describe(
|
|
14402
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
14458
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
14403
14459
|
)
|
|
14404
14460
|
})
|
|
14405
14461
|
).describe("The words in the utterance."),
|
|
@@ -14414,7 +14470,7 @@ var deleteTranscriptResponse = zod3.object({
|
|
|
14414
14470
|
)
|
|
14415
14471
|
})
|
|
14416
14472
|
).nullish().describe(
|
|
14417
|
-
"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/
|
|
14473
|
+
"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"
|
|
14418
14474
|
),
|
|
14419
14475
|
webhook_auth: zod3.boolean().describe(
|
|
14420
14476
|
"Whether [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) authentication details were provided"
|
|
@@ -14438,7 +14494,7 @@ var deleteTranscriptResponse = zod3.object({
|
|
|
14438
14494
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
14439
14495
|
),
|
|
14440
14496
|
speaker: zod3.string().nullable().describe(
|
|
14441
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
14497
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
14442
14498
|
)
|
|
14443
14499
|
})
|
|
14444
14500
|
).nullish().describe(
|
|
@@ -14483,7 +14539,7 @@ var getTranscriptSentencesResponse = zod3.object({
|
|
|
14483
14539
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
14484
14540
|
),
|
|
14485
14541
|
speaker: zod3.string().nullable().describe(
|
|
14486
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
14542
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
14487
14543
|
)
|
|
14488
14544
|
})
|
|
14489
14545
|
).describe("An array of words in the sentence"),
|
|
@@ -14491,7 +14547,7 @@ var getTranscriptSentencesResponse = zod3.object({
|
|
|
14491
14547
|
"The channel of the sentence. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
14492
14548
|
),
|
|
14493
14549
|
speaker: zod3.string().nullable().describe(
|
|
14494
|
-
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
14550
|
+
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
14495
14551
|
)
|
|
14496
14552
|
})
|
|
14497
14553
|
).describe("An array of sentences in the transcript")
|
|
@@ -14519,7 +14575,7 @@ var getTranscriptParagraphsResponse = zod3.object({
|
|
|
14519
14575
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
14520
14576
|
),
|
|
14521
14577
|
speaker: zod3.string().nullable().describe(
|
|
14522
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
14578
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
14523
14579
|
)
|
|
14524
14580
|
})
|
|
14525
14581
|
).describe("An array of words in the paragraph")
|
|
@@ -17131,23 +17187,6 @@ var preRecordedControllerGetPreRecordedJobsV2Response = zod5.object({
|
|
|
17131
17187
|
}).optional().describe(
|
|
17132
17188
|
"If `name_consistency` has been enabled, Gladia will improve consistency of the names accross the transcription"
|
|
17133
17189
|
),
|
|
17134
|
-
speaker_reidentification: zod5.object({
|
|
17135
|
-
success: zod5.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
17136
|
-
is_empty: zod5.boolean().describe("The audio intelligence model returned an empty value"),
|
|
17137
|
-
exec_time: zod5.number().describe("Time audio intelligence model took to complete the task"),
|
|
17138
|
-
error: zod5.object({
|
|
17139
|
-
status_code: zod5.number().describe("Status code of the addon error"),
|
|
17140
|
-
exception: zod5.string().describe("Reason of the addon error"),
|
|
17141
|
-
message: zod5.string().describe("Detailed message of the addon error")
|
|
17142
|
-
}).nullable().describe(
|
|
17143
|
-
"`null` if `success` is `true`. Contains the error details of the failed model"
|
|
17144
|
-
),
|
|
17145
|
-
results: zod5.string().describe(
|
|
17146
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
17147
|
-
)
|
|
17148
|
-
}).optional().describe(
|
|
17149
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
17150
|
-
),
|
|
17151
17190
|
structured_data_extraction: zod5.object({
|
|
17152
17191
|
success: zod5.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
17153
17192
|
is_empty: zod5.boolean().describe("The audio intelligence model returned an empty value"),
|
|
@@ -18628,23 +18667,6 @@ var preRecordedControllerGetPreRecordedJobV2Response = zod5.object({
|
|
|
18628
18667
|
}).optional().describe(
|
|
18629
18668
|
"If `name_consistency` has been enabled, Gladia will improve consistency of the names accross the transcription"
|
|
18630
18669
|
),
|
|
18631
|
-
speaker_reidentification: zod5.object({
|
|
18632
|
-
success: zod5.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
18633
|
-
is_empty: zod5.boolean().describe("The audio intelligence model returned an empty value"),
|
|
18634
|
-
exec_time: zod5.number().describe("Time audio intelligence model took to complete the task"),
|
|
18635
|
-
error: zod5.object({
|
|
18636
|
-
status_code: zod5.number().describe("Status code of the addon error"),
|
|
18637
|
-
exception: zod5.string().describe("Reason of the addon error"),
|
|
18638
|
-
message: zod5.string().describe("Detailed message of the addon error")
|
|
18639
|
-
}).nullable().describe(
|
|
18640
|
-
"`null` if `success` is `true`. Contains the error details of the failed model"
|
|
18641
|
-
),
|
|
18642
|
-
results: zod5.string().describe(
|
|
18643
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
18644
|
-
)
|
|
18645
|
-
}).optional().describe(
|
|
18646
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
18647
|
-
),
|
|
18648
18670
|
structured_data_extraction: zod5.object({
|
|
18649
18671
|
success: zod5.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
18650
18672
|
is_empty: zod5.boolean().describe("The audio intelligence model returned an empty value"),
|
|
@@ -20782,23 +20804,6 @@ var transcriptionControllerListV2Response = zod5.object({
|
|
|
20782
20804
|
}).optional().describe(
|
|
20783
20805
|
"If `name_consistency` has been enabled, Gladia will improve consistency of the names accross the transcription"
|
|
20784
20806
|
),
|
|
20785
|
-
speaker_reidentification: zod5.object({
|
|
20786
|
-
success: zod5.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
20787
|
-
is_empty: zod5.boolean().describe("The audio intelligence model returned an empty value"),
|
|
20788
|
-
exec_time: zod5.number().describe("Time audio intelligence model took to complete the task"),
|
|
20789
|
-
error: zod5.object({
|
|
20790
|
-
status_code: zod5.number().describe("Status code of the addon error"),
|
|
20791
|
-
exception: zod5.string().describe("Reason of the addon error"),
|
|
20792
|
-
message: zod5.string().describe("Detailed message of the addon error")
|
|
20793
|
-
}).nullable().describe(
|
|
20794
|
-
"`null` if `success` is `true`. Contains the error details of the failed model"
|
|
20795
|
-
),
|
|
20796
|
-
results: zod5.string().describe(
|
|
20797
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
20798
|
-
)
|
|
20799
|
-
}).optional().describe(
|
|
20800
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
20801
|
-
),
|
|
20802
20807
|
structured_data_extraction: zod5.object({
|
|
20803
20808
|
success: zod5.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
20804
20809
|
is_empty: zod5.boolean().describe("The audio intelligence model returned an empty value"),
|
|
@@ -21098,11 +21103,7 @@ var transcriptionControllerListV2Response = zod5.object({
|
|
|
21098
21103
|
channels: zod5.number().min(1).max(transcriptionControllerListV2ResponseItemsItemRequestParamsChannelsMax).default(
|
|
21099
21104
|
transcriptionControllerListV2ResponseItemsItemRequestParamsChannelsDefault
|
|
21100
21105
|
).describe("The number of channels of the audio stream"),
|
|
21101
|
-
model: zod5.enum(["solaria-1"]).describe(
|
|
21102
|
-
'The model used to process the audio. "solaria-1" is used by default.'
|
|
21103
|
-
).default(transcriptionControllerListV2ResponseItemsItemRequestParamsModelDefault).describe(
|
|
21104
|
-
'The model used to process the audio. "solaria-1" is used by default.'
|
|
21105
|
-
),
|
|
21106
|
+
model: zod5.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.'),
|
|
21106
21107
|
endpointing: zod5.number().min(transcriptionControllerListV2ResponseItemsItemRequestParamsEndpointingMin).max(transcriptionControllerListV2ResponseItemsItemRequestParamsEndpointingMax).default(
|
|
21107
21108
|
transcriptionControllerListV2ResponseItemsItemRequestParamsEndpointingDefault
|
|
21108
21109
|
).describe(
|
|
@@ -23526,23 +23527,6 @@ var transcriptionControllerGetTranscriptV2Response = zod5.discriminatedUnion("ki
|
|
|
23526
23527
|
}).optional().describe(
|
|
23527
23528
|
"If `name_consistency` has been enabled, Gladia will improve consistency of the names accross the transcription"
|
|
23528
23529
|
),
|
|
23529
|
-
speaker_reidentification: zod5.object({
|
|
23530
|
-
success: zod5.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
23531
|
-
is_empty: zod5.boolean().describe("The audio intelligence model returned an empty value"),
|
|
23532
|
-
exec_time: zod5.number().describe("Time audio intelligence model took to complete the task"),
|
|
23533
|
-
error: zod5.object({
|
|
23534
|
-
status_code: zod5.number().describe("Status code of the addon error"),
|
|
23535
|
-
exception: zod5.string().describe("Reason of the addon error"),
|
|
23536
|
-
message: zod5.string().describe("Detailed message of the addon error")
|
|
23537
|
-
}).nullable().describe(
|
|
23538
|
-
"`null` if `success` is `true`. Contains the error details of the failed model"
|
|
23539
|
-
),
|
|
23540
|
-
results: zod5.string().describe(
|
|
23541
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
23542
|
-
)
|
|
23543
|
-
}).optional().describe(
|
|
23544
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
23545
|
-
),
|
|
23546
23530
|
structured_data_extraction: zod5.object({
|
|
23547
23531
|
success: zod5.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
23548
23532
|
is_empty: zod5.boolean().describe("The audio intelligence model returned an empty value"),
|
|
@@ -26708,23 +26692,6 @@ var historyControllerGetListV1Response = zod5.object({
|
|
|
26708
26692
|
}).optional().describe(
|
|
26709
26693
|
"If `name_consistency` has been enabled, Gladia will improve consistency of the names accross the transcription"
|
|
26710
26694
|
),
|
|
26711
|
-
speaker_reidentification: zod5.object({
|
|
26712
|
-
success: zod5.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
26713
|
-
is_empty: zod5.boolean().describe("The audio intelligence model returned an empty value"),
|
|
26714
|
-
exec_time: zod5.number().describe("Time audio intelligence model took to complete the task"),
|
|
26715
|
-
error: zod5.object({
|
|
26716
|
-
status_code: zod5.number().describe("Status code of the addon error"),
|
|
26717
|
-
exception: zod5.string().describe("Reason of the addon error"),
|
|
26718
|
-
message: zod5.string().describe("Detailed message of the addon error")
|
|
26719
|
-
}).nullable().describe(
|
|
26720
|
-
"`null` if `success` is `true`. Contains the error details of the failed model"
|
|
26721
|
-
),
|
|
26722
|
-
results: zod5.string().describe(
|
|
26723
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
26724
|
-
)
|
|
26725
|
-
}).optional().describe(
|
|
26726
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
26727
|
-
),
|
|
26728
26695
|
structured_data_extraction: zod5.object({
|
|
26729
26696
|
success: zod5.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
26730
26697
|
is_empty: zod5.boolean().describe("The audio intelligence model returned an empty value"),
|
|
@@ -27018,11 +26985,7 @@ var historyControllerGetListV1Response = zod5.object({
|
|
|
27018
26985
|
historyControllerGetListV1ResponseItemsItemRequestParamsSampleRateDefault
|
|
27019
26986
|
).describe("The sample rate of the audio stream"),
|
|
27020
26987
|
channels: zod5.number().min(1).max(historyControllerGetListV1ResponseItemsItemRequestParamsChannelsMax).default(historyControllerGetListV1ResponseItemsItemRequestParamsChannelsDefault).describe("The number of channels of the audio stream"),
|
|
27021
|
-
model: zod5.enum(["solaria-1"]).describe(
|
|
27022
|
-
'The model used to process the audio. "solaria-1" is used by default.'
|
|
27023
|
-
).default(historyControllerGetListV1ResponseItemsItemRequestParamsModelDefault).describe(
|
|
27024
|
-
'The model used to process the audio. "solaria-1" is used by default.'
|
|
27025
|
-
),
|
|
26988
|
+
model: zod5.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.'),
|
|
27026
26989
|
endpointing: zod5.number().min(historyControllerGetListV1ResponseItemsItemRequestParamsEndpointingMin).max(historyControllerGetListV1ResponseItemsItemRequestParamsEndpointingMax).default(
|
|
27027
26990
|
historyControllerGetListV1ResponseItemsItemRequestParamsEndpointingDefault
|
|
27028
26991
|
).describe(
|
|
@@ -36183,6 +36146,7 @@ __export(sonioxPublicAPI_zod_exports, {
|
|
|
36183
36146
|
createTemporaryApiKeyBody: () => createTemporaryApiKeyBody,
|
|
36184
36147
|
createTemporaryApiKeyBodyClientReferenceIdMaxOne: () => createTemporaryApiKeyBodyClientReferenceIdMaxOne,
|
|
36185
36148
|
createTemporaryApiKeyBodyExpiresInSecondsMax: () => createTemporaryApiKeyBodyExpiresInSecondsMax,
|
|
36149
|
+
createTemporaryApiKeyBodyMaxSessionDurationSecondsMaxOne: () => createTemporaryApiKeyBodyMaxSessionDurationSecondsMaxOne,
|
|
36186
36150
|
createTranscriptionBody: () => createTranscriptionBody2,
|
|
36187
36151
|
createTranscriptionBodyAudioUrlMaxOne: () => createTranscriptionBodyAudioUrlMaxOne,
|
|
36188
36152
|
createTranscriptionBodyAudioUrlRegExpOne: () => createTranscriptionBodyAudioUrlRegExpOne,
|
|
@@ -36313,11 +36277,11 @@ var getTranscriptionsResponse = zod10.object({
|
|
|
36313
36277
|
});
|
|
36314
36278
|
var createTranscriptionBodyModelMaxThree = 32;
|
|
36315
36279
|
var createTranscriptionBodyAudioUrlMaxOne = 4096;
|
|
36316
|
-
var createTranscriptionBodyAudioUrlRegExpOne =
|
|
36280
|
+
var createTranscriptionBodyAudioUrlRegExpOne = /^https?:\/\/[^\s]+$/;
|
|
36317
36281
|
var createTranscriptionBodyLanguageHintsItemMax = 10;
|
|
36318
36282
|
var createTranscriptionBodyLanguageHintsMaxOne = 100;
|
|
36319
36283
|
var createTranscriptionBodyWebhookUrlMaxOne = 256;
|
|
36320
|
-
var createTranscriptionBodyWebhookUrlRegExpOne =
|
|
36284
|
+
var createTranscriptionBodyWebhookUrlRegExpOne = /^https?:\/\/[^\s]+$/;
|
|
36321
36285
|
var createTranscriptionBodyWebhookAuthHeaderNameMaxOne = 256;
|
|
36322
36286
|
var createTranscriptionBodyWebhookAuthHeaderValueMaxOne = 256;
|
|
36323
36287
|
var createTranscriptionBodyClientReferenceIdMaxOne = 256;
|
|
@@ -36465,10 +36429,15 @@ var getModelsResponse = zod10.object({
|
|
|
36465
36429
|
});
|
|
36466
36430
|
var createTemporaryApiKeyBodyExpiresInSecondsMax = 3600;
|
|
36467
36431
|
var createTemporaryApiKeyBodyClientReferenceIdMaxOne = 256;
|
|
36432
|
+
var createTemporaryApiKeyBodyMaxSessionDurationSecondsMaxOne = 18e3;
|
|
36468
36433
|
var createTemporaryApiKeyBody = zod10.object({
|
|
36469
36434
|
usage_type: zod10.enum(["transcribe_websocket"]),
|
|
36470
36435
|
expires_in_seconds: zod10.number().min(1).max(createTemporaryApiKeyBodyExpiresInSecondsMax).describe("Duration in seconds until the temporary API key expires."),
|
|
36471
|
-
client_reference_id: zod10.string().max(createTemporaryApiKeyBodyClientReferenceIdMaxOne).or(zod10.null()).optional().describe("Optional tracking identifier string. Does not need to be unique.")
|
|
36436
|
+
client_reference_id: zod10.string().max(createTemporaryApiKeyBodyClientReferenceIdMaxOne).or(zod10.null()).optional().describe("Optional tracking identifier string. Does not need to be unique."),
|
|
36437
|
+
single_use: zod10.boolean().or(zod10.null()).optional().describe("If true, the temporary API key can be used only once."),
|
|
36438
|
+
max_session_duration_seconds: zod10.number().min(1).max(createTemporaryApiKeyBodyMaxSessionDurationSecondsMaxOne).or(zod10.null()).optional().describe(
|
|
36439
|
+
"Maximum WebSocket connection duration in seconds. If exceeded, the connection will be dropped. If not set, no limit is applied."
|
|
36440
|
+
)
|
|
36472
36441
|
});
|
|
36473
36442
|
|
|
36474
36443
|
// src/generated/soniox/streaming-types.zod.ts
|
|
@@ -37719,6 +37688,16 @@ var ToolChoiceOptions = {
|
|
|
37719
37688
|
required: "required"
|
|
37720
37689
|
};
|
|
37721
37690
|
|
|
37691
|
+
// src/generated/openai/schema/transcriptionDiarizedSegmentType.ts
|
|
37692
|
+
var TranscriptionDiarizedSegmentType = {
|
|
37693
|
+
transcripttextsegment: "transcript.text.segment"
|
|
37694
|
+
};
|
|
37695
|
+
|
|
37696
|
+
// src/generated/openai/schema/transcriptionInclude.ts
|
|
37697
|
+
var TranscriptionInclude = {
|
|
37698
|
+
logprobs: "logprobs"
|
|
37699
|
+
};
|
|
37700
|
+
|
|
37722
37701
|
// src/generated/openai/schema/transcriptTextDeltaEventType.ts
|
|
37723
37702
|
var TranscriptTextDeltaEventType = {
|
|
37724
37703
|
transcripttextdelta: "transcript.text.delta"
|
|
@@ -37744,16 +37723,6 @@ var TranscriptTextUsageTokensType = {
|
|
|
37744
37723
|
tokens: "tokens"
|
|
37745
37724
|
};
|
|
37746
37725
|
|
|
37747
|
-
// src/generated/openai/schema/transcriptionDiarizedSegmentType.ts
|
|
37748
|
-
var TranscriptionDiarizedSegmentType = {
|
|
37749
|
-
transcripttextsegment: "transcript.text.segment"
|
|
37750
|
-
};
|
|
37751
|
-
|
|
37752
|
-
// src/generated/openai/schema/transcriptionInclude.ts
|
|
37753
|
-
var TranscriptionInclude = {
|
|
37754
|
-
logprobs: "logprobs"
|
|
37755
|
-
};
|
|
37756
|
-
|
|
37757
37726
|
// src/generated/openai/schema/vadConfigType.ts
|
|
37758
37727
|
var VadConfigType = {
|
|
37759
37728
|
server_vad: "server_vad"
|
|
@@ -38135,8 +38104,8 @@ var getJobsQueryParams = zod12.object({
|
|
|
38135
38104
|
var getJobsResponseJobsItemDurationMin = 0;
|
|
38136
38105
|
var getJobsResponseJobsItemConfigTranscriptionConfigPunctuationOverridesSensitivityMin = 0;
|
|
38137
38106
|
var getJobsResponseJobsItemConfigTranscriptionConfigPunctuationOverridesSensitivityMax = 1;
|
|
38138
|
-
var getJobsResponseJobsItemConfigTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp =
|
|
38139
|
-
var getJobsResponseJobsItemConfigTranscriptionConfigChannelDiarizationLabelsItemRegExp =
|
|
38107
|
+
var getJobsResponseJobsItemConfigTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp = /^(.|all)$/;
|
|
38108
|
+
var getJobsResponseJobsItemConfigTranscriptionConfigChannelDiarizationLabelsItemRegExp = /^[A-Za-z0-9._]+$/;
|
|
38140
38109
|
var getJobsResponseJobsItemConfigTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMin = 0;
|
|
38141
38110
|
var getJobsResponseJobsItemConfigTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMax = 1;
|
|
38142
38111
|
var getJobsResponseJobsItemConfigTranslationConfigTargetLanguagesMax = 5;
|
|
@@ -38334,8 +38303,8 @@ var getJobsJobidParams = zod12.object({
|
|
|
38334
38303
|
var getJobsJobidResponseJobDurationMin = 0;
|
|
38335
38304
|
var getJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesSensitivityMin = 0;
|
|
38336
38305
|
var getJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesSensitivityMax = 1;
|
|
38337
|
-
var getJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp =
|
|
38338
|
-
var getJobsJobidResponseJobConfigTranscriptionConfigChannelDiarizationLabelsItemRegExp =
|
|
38306
|
+
var getJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp = /^(.|all)$/;
|
|
38307
|
+
var getJobsJobidResponseJobConfigTranscriptionConfigChannelDiarizationLabelsItemRegExp = /^[A-Za-z0-9._]+$/;
|
|
38339
38308
|
var getJobsJobidResponseJobConfigTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMin = 0;
|
|
38340
38309
|
var getJobsJobidResponseJobConfigTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMax = 1;
|
|
38341
38310
|
var getJobsJobidResponseJobConfigTranslationConfigTargetLanguagesMax = 5;
|
|
@@ -38532,8 +38501,8 @@ var deleteJobsJobidQueryParams = zod12.object({
|
|
|
38532
38501
|
var deleteJobsJobidResponseJobDurationMin = 0;
|
|
38533
38502
|
var deleteJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesSensitivityMin = 0;
|
|
38534
38503
|
var deleteJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesSensitivityMax = 1;
|
|
38535
|
-
var deleteJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp =
|
|
38536
|
-
var deleteJobsJobidResponseJobConfigTranscriptionConfigChannelDiarizationLabelsItemRegExp =
|
|
38504
|
+
var deleteJobsJobidResponseJobConfigTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp = /^(.|all)$/;
|
|
38505
|
+
var deleteJobsJobidResponseJobConfigTranscriptionConfigChannelDiarizationLabelsItemRegExp = /^[A-Za-z0-9._]+$/;
|
|
38537
38506
|
var deleteJobsJobidResponseJobConfigTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMin = 0;
|
|
38538
38507
|
var deleteJobsJobidResponseJobConfigTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMax = 1;
|
|
38539
38508
|
var deleteJobsJobidResponseJobConfigTranslationConfigTargetLanguagesMax = 5;
|
|
@@ -38736,8 +38705,8 @@ var getJobsJobidTranscriptQueryParams = zod12.object({
|
|
|
38736
38705
|
var getJobsJobidTranscriptResponseJobDurationMin = 0;
|
|
38737
38706
|
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigPunctuationOverridesSensitivityMin = 0;
|
|
38738
38707
|
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigPunctuationOverridesSensitivityMax = 1;
|
|
38739
|
-
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp =
|
|
38740
|
-
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigChannelDiarizationLabelsItemRegExp =
|
|
38708
|
+
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigPunctuationOverridesPermittedMarksItemRegExp = /^(.|all)$/;
|
|
38709
|
+
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigChannelDiarizationLabelsItemRegExp = /^[A-Za-z0-9._]+$/;
|
|
38741
38710
|
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMin = 0;
|
|
38742
38711
|
var getJobsJobidTranscriptResponseMetadataTranscriptionConfigSpeakerDiarizationConfigSpeakerSensitivityMax = 1;
|
|
38743
38712
|
var getJobsJobidTranscriptResponseResultsItemVolumeMin = 0;
|