voice-router-dev 0.9.4 → 0.9.6
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 +66 -0
- package/dist/constants.d.mts +11 -92
- package/dist/constants.d.ts +11 -92
- package/dist/constants.js +11 -88
- package/dist/constants.mjs +11 -88
- package/dist/{field-configs-BXXH2T3E.d.mts → field-configs-Bt2iLgt_.d.mts} +8982 -7900
- package/dist/{field-configs-BXXH2T3E.d.ts → field-configs-Bt2iLgt_.d.ts} +8982 -7900
- package/dist/field-configs.d.mts +1 -1
- package/dist/field-configs.d.ts +1 -1
- package/dist/field-configs.js +583 -150
- package/dist/field-configs.mjs +583 -150
- package/dist/index.d.mts +1578 -560
- package/dist/index.d.ts +1578 -560
- package/dist/index.js +922 -279
- package/dist/index.mjs +925 -279
- package/dist/{provider-metadata-D1d-9cng.d.ts → provider-metadata-B5SFlFb0.d.ts} +6 -6
- package/dist/{provider-metadata-BJ29OPW1.d.mts → provider-metadata-J8URl-3i.d.mts} +6 -6
- package/dist/provider-metadata.d.mts +1 -1
- package/dist/provider-metadata.d.ts +1 -1
- package/dist/provider-metadata.js +3 -66
- package/dist/provider-metadata.mjs +3 -66
- package/dist/{speechToTextChunkResponseModel-BY2lGyZ3.d.ts → speechToTextChunkResponseModel-DhC5T0u1.d.ts} +364 -39
- package/dist/{speechToTextChunkResponseModel-KayxDiZ7.d.mts → speechToTextChunkResponseModel-SgJKP7kZ.d.mts} +364 -39
- package/dist/webhooks.d.mts +3 -2
- package/dist/webhooks.d.ts +3 -2
- package/package.json +8 -3
|
@@ -1,5 +1,6 @@
|
|
|
1
1
|
import { DeepgramModelCode, DeepgramTopicModeType, DeepgramRedactType, AssemblyAISampleRateType, AssemblyAIEncodingType, AssemblyAISpeechModelType, SonioxRealtimeModelCode, SonioxLanguageCode, ElevenLabsRealtimeModelCode, ElevenLabsAudioFormatType, SpeechmaticsRegionType, SonioxModelCode, ElevenLabsModelCode, DeepgramLanguageCode, ElevenLabsLanguageCode, SpeechmaticsLanguageCode, AzureLocaleCode } from './constants.mjs';
|
|
2
|
-
import {
|
|
2
|
+
import { TranscriptionContext, TranslationConfig as TranslationConfig$1, WaitOptions, CleanupTarget } from '@soniox/node';
|
|
3
|
+
import { e as StreamingProviderType, B as BatchOnlyProviderType, T as TranscriptionProvider } from './provider-metadata-J8URl-3i.mjs';
|
|
3
4
|
|
|
4
5
|
/**
|
|
5
6
|
* Unified audio encoding types for Voice Router SDK
|
|
@@ -1315,9 +1316,9 @@ interface PreRecordedRequestParamsResponse {
|
|
|
1315
1316
|
translation?: boolean;
|
|
1316
1317
|
/** **[Beta]** Translation configuration, if `translation` is enabled */
|
|
1317
1318
|
translation_config?: TranslationConfigDTO;
|
|
1318
|
-
/**
|
|
1319
|
+
/** Enable summarization for this audio */
|
|
1319
1320
|
summarization?: boolean;
|
|
1320
|
-
/**
|
|
1321
|
+
/** Summarization configuration, if `summarization` is enabled */
|
|
1321
1322
|
summarization_config?: SummarizationConfigDTO;
|
|
1322
1323
|
/** **[Alpha]** Enable named entity recognition for this audio */
|
|
1323
1324
|
named_entity_recognition?: boolean;
|
|
@@ -1327,9 +1328,9 @@ interface PreRecordedRequestParamsResponse {
|
|
|
1327
1328
|
custom_spelling_config?: CustomSpellingConfigDTO;
|
|
1328
1329
|
/** Enable sentiment analysis for this audio */
|
|
1329
1330
|
sentiment_analysis?: boolean;
|
|
1330
|
-
/**
|
|
1331
|
+
/** Enable audio to LLM processing for this audio */
|
|
1331
1332
|
audio_to_llm?: boolean;
|
|
1332
|
-
/**
|
|
1333
|
+
/** Audio to LLM configuration, if `audio_to_llm` is enabled */
|
|
1333
1334
|
audio_to_llm_config?: AudioToLlmListConfigDTO;
|
|
1334
1335
|
/** Enable PII redaction for this audio */
|
|
1335
1336
|
pii_redaction?: boolean;
|
|
@@ -2524,7 +2525,7 @@ type SpeechModel = string;
|
|
|
2524
2525
|
* OpenAPI spec version: 1.0.0
|
|
2525
2526
|
*/
|
|
2526
2527
|
/**
|
|
2527
|
-
* 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.
|
|
2528
|
+
* The replacement logic for detected PII, can be `entity_name` or `hash`. See [PII redaction](https://www.assemblyai.com/docs/streaming/pii-redaction) for more details.
|
|
2528
2529
|
*/
|
|
2529
2530
|
type SubstitutionPolicy = (typeof SubstitutionPolicy)[keyof typeof SubstitutionPolicy];
|
|
2530
2531
|
declare const SubstitutionPolicy: {
|
|
@@ -2898,7 +2899,7 @@ type TranscriptCustomTopics = boolean | null;
|
|
|
2898
2899
|
* OpenAPI spec version: 1.0.0
|
|
2899
2900
|
*/
|
|
2900
2901
|
/**
|
|
2901
|
-
* 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
|
|
2902
|
+
* 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. Supported on Universal-3 Pro and Universal-2.
|
|
2902
2903
|
*/
|
|
2903
2904
|
type TranscriptDisfluencies = boolean | null;
|
|
2904
2905
|
|
|
@@ -2942,12 +2943,20 @@ declare const EntityType: {
|
|
|
2942
2943
|
readonly email_address: "email_address";
|
|
2943
2944
|
readonly event: "event";
|
|
2944
2945
|
readonly filename: "filename";
|
|
2946
|
+
readonly gender: "gender";
|
|
2945
2947
|
readonly gender_sexuality: "gender_sexuality";
|
|
2946
2948
|
readonly healthcare_number: "healthcare_number";
|
|
2947
2949
|
readonly injury: "injury";
|
|
2948
2950
|
readonly ip_address: "ip_address";
|
|
2949
2951
|
readonly language: "language";
|
|
2950
2952
|
readonly location: "location";
|
|
2953
|
+
readonly location_address: "location_address";
|
|
2954
|
+
readonly location_address_street: "location_address_street";
|
|
2955
|
+
readonly location_city: "location_city";
|
|
2956
|
+
readonly location_coordinate: "location_coordinate";
|
|
2957
|
+
readonly location_country: "location_country";
|
|
2958
|
+
readonly location_state: "location_state";
|
|
2959
|
+
readonly location_zip: "location_zip";
|
|
2951
2960
|
readonly marital_status: "marital_status";
|
|
2952
2961
|
readonly medical_condition: "medical_condition";
|
|
2953
2962
|
readonly medical_process: "medical_process";
|
|
@@ -2956,6 +2965,7 @@ declare const EntityType: {
|
|
|
2956
2965
|
readonly number_sequence: "number_sequence";
|
|
2957
2966
|
readonly occupation: "occupation";
|
|
2958
2967
|
readonly organization: "organization";
|
|
2968
|
+
readonly organization_medical_facility: "organization_medical_facility";
|
|
2959
2969
|
readonly passport_number: "passport_number";
|
|
2960
2970
|
readonly password: "password";
|
|
2961
2971
|
readonly person_age: "person_age";
|
|
@@ -2964,6 +2974,7 @@ declare const EntityType: {
|
|
|
2964
2974
|
readonly physical_attribute: "physical_attribute";
|
|
2965
2975
|
readonly political_affiliation: "political_affiliation";
|
|
2966
2976
|
readonly religion: "religion";
|
|
2977
|
+
readonly sexuality: "sexuality";
|
|
2967
2978
|
readonly statistics: "statistics";
|
|
2968
2979
|
readonly time: "time";
|
|
2969
2980
|
readonly url: "url";
|
|
@@ -3338,6 +3349,70 @@ interface TranscriptLanguageDetectionOptions {
|
|
|
3338
3349
|
code_switching_confidence_threshold?: number;
|
|
3339
3350
|
}
|
|
3340
3351
|
|
|
3352
|
+
/**
|
|
3353
|
+
* Generated by orval v7.9.0 🍺
|
|
3354
|
+
* Do not edit manually.
|
|
3355
|
+
* AssemblyAI API
|
|
3356
|
+
* AssemblyAI Speech-to-Text API - Batch transcription endpoints. Filtered from the official AssemblyAI docs spec.
|
|
3357
|
+
* OpenAPI spec version: 1.0.0
|
|
3358
|
+
*/
|
|
3359
|
+
/**
|
|
3360
|
+
* The domain-specific model that was applied to the transcription (for example, `"medical-v1"` when [Medical Mode](https://www.assemblyai.com/docs/pre-recorded-audio/medical-mode) was applied), or `null` if no domain-specific model was used. Always present when `metadata` is present.
|
|
3361
|
+
|
|
3362
|
+
*/
|
|
3363
|
+
type TranscriptMetadataDomainUsed = string | null;
|
|
3364
|
+
|
|
3365
|
+
/**
|
|
3366
|
+
* Generated by orval v7.9.0 🍺
|
|
3367
|
+
* Do not edit manually.
|
|
3368
|
+
* AssemblyAI API
|
|
3369
|
+
* AssemblyAI Speech-to-Text API - Batch transcription endpoints. Filtered from the official AssemblyAI docs spec.
|
|
3370
|
+
* OpenAPI spec version: 1.0.0
|
|
3371
|
+
*/
|
|
3372
|
+
/**
|
|
3373
|
+
* A warning message emitted while processing a transcription request. Warnings are surfaced on the transcript response under `metadata.warnings`.
|
|
3374
|
+
|
|
3375
|
+
*/
|
|
3376
|
+
interface TranscriptWarning {
|
|
3377
|
+
/** A human-readable description of the warning. */
|
|
3378
|
+
message: string;
|
|
3379
|
+
}
|
|
3380
|
+
|
|
3381
|
+
/**
|
|
3382
|
+
* Generated by orval v7.9.0 🍺
|
|
3383
|
+
* Do not edit manually.
|
|
3384
|
+
* AssemblyAI API
|
|
3385
|
+
* AssemblyAI Speech-to-Text API - Batch transcription endpoints. Filtered from the official AssemblyAI docs spec.
|
|
3386
|
+
* OpenAPI spec version: 1.0.0
|
|
3387
|
+
*/
|
|
3388
|
+
|
|
3389
|
+
/**
|
|
3390
|
+
* Additional metadata about the transcription returned on the `Transcript` object under `metadata`. Only present when there is information to report — when all of its fields would be empty, the `metadata` object is omitted from the response entirely.
|
|
3391
|
+
|
|
3392
|
+
*/
|
|
3393
|
+
interface TranscriptMetadata$1 {
|
|
3394
|
+
/** The domain-specific model that was applied to the transcription (for example, `"medical-v1"` when [Medical Mode](https://www.assemblyai.com/docs/pre-recorded-audio/medical-mode) was applied), or `null` if no domain-specific model was used. Always present when `metadata` is present.
|
|
3395
|
+
*/
|
|
3396
|
+
domain_used?: TranscriptMetadataDomainUsed;
|
|
3397
|
+
/** Warning messages emitted while processing the request. Each warning is an object with a human-readable `message`. When there are no warnings to report, this field is omitted from the `metadata` object entirely.
|
|
3398
|
+
*/
|
|
3399
|
+
warnings?: TranscriptWarning[];
|
|
3400
|
+
}
|
|
3401
|
+
|
|
3402
|
+
/**
|
|
3403
|
+
* Generated by orval v7.9.0 🍺
|
|
3404
|
+
* Do not edit manually.
|
|
3405
|
+
* AssemblyAI API
|
|
3406
|
+
* AssemblyAI Speech-to-Text API - Batch transcription endpoints. Filtered from the official AssemblyAI docs spec.
|
|
3407
|
+
* OpenAPI spec version: 1.0.0
|
|
3408
|
+
*/
|
|
3409
|
+
|
|
3410
|
+
/**
|
|
3411
|
+
* Additional metadata about the transcription, including any warnings emitted while processing the request. Only present when there is information to report; if no fields would be populated, `metadata` is omitted from the response entirely.
|
|
3412
|
+
|
|
3413
|
+
*/
|
|
3414
|
+
type TranscriptMetadataProperty = TranscriptMetadata$1 | null;
|
|
3415
|
+
|
|
3341
3416
|
/**
|
|
3342
3417
|
* Generated by orval v7.9.0 🍺
|
|
3343
3418
|
* Do not edit manually.
|
|
@@ -3450,7 +3525,7 @@ type TranscriptRedactPiiAudioQuality = RedactPiiAudioQuality | null;
|
|
|
3450
3525
|
* OpenAPI spec version: 1.0.0
|
|
3451
3526
|
*/
|
|
3452
3527
|
/**
|
|
3453
|
-
* The type of PII to redact
|
|
3528
|
+
* The type of PII to redact. See [PII redaction](https://www.assemblyai.com/docs/streaming/pii-redaction) for the full list of policies and their descriptions.
|
|
3454
3529
|
*/
|
|
3455
3530
|
type PiiPolicy = (typeof PiiPolicy)[keyof typeof PiiPolicy];
|
|
3456
3531
|
declare const PiiPolicy: {
|
|
@@ -3469,12 +3544,20 @@ declare const PiiPolicy: {
|
|
|
3469
3544
|
readonly email_address: "email_address";
|
|
3470
3545
|
readonly event: "event";
|
|
3471
3546
|
readonly filename: "filename";
|
|
3547
|
+
readonly gender: "gender";
|
|
3472
3548
|
readonly gender_sexuality: "gender_sexuality";
|
|
3473
3549
|
readonly healthcare_number: "healthcare_number";
|
|
3474
3550
|
readonly injury: "injury";
|
|
3475
3551
|
readonly ip_address: "ip_address";
|
|
3476
3552
|
readonly language: "language";
|
|
3477
3553
|
readonly location: "location";
|
|
3554
|
+
readonly location_address: "location_address";
|
|
3555
|
+
readonly location_address_street: "location_address_street";
|
|
3556
|
+
readonly location_city: "location_city";
|
|
3557
|
+
readonly location_coordinate: "location_coordinate";
|
|
3558
|
+
readonly location_country: "location_country";
|
|
3559
|
+
readonly location_state: "location_state";
|
|
3560
|
+
readonly location_zip: "location_zip";
|
|
3478
3561
|
readonly marital_status: "marital_status";
|
|
3479
3562
|
readonly medical_condition: "medical_condition";
|
|
3480
3563
|
readonly medical_process: "medical_process";
|
|
@@ -3483,6 +3566,7 @@ declare const PiiPolicy: {
|
|
|
3483
3566
|
readonly number_sequence: "number_sequence";
|
|
3484
3567
|
readonly occupation: "occupation";
|
|
3485
3568
|
readonly organization: "organization";
|
|
3569
|
+
readonly organization_medical_facility: "organization_medical_facility";
|
|
3486
3570
|
readonly passport_number: "passport_number";
|
|
3487
3571
|
readonly password: "password";
|
|
3488
3572
|
readonly person_age: "person_age";
|
|
@@ -3491,6 +3575,7 @@ declare const PiiPolicy: {
|
|
|
3491
3575
|
readonly physical_attribute: "physical_attribute";
|
|
3492
3576
|
readonly political_affiliation: "political_affiliation";
|
|
3493
3577
|
readonly religion: "religion";
|
|
3578
|
+
readonly sexuality: "sexuality";
|
|
3494
3579
|
readonly statistics: "statistics";
|
|
3495
3580
|
readonly time: "time";
|
|
3496
3581
|
readonly url: "url";
|
|
@@ -3523,7 +3608,20 @@ type TranscriptRedactPiiPolicies = PiiPolicy[] | null;
|
|
|
3523
3608
|
* OpenAPI spec version: 1.0.0
|
|
3524
3609
|
*/
|
|
3525
3610
|
/**
|
|
3526
|
-
* Whether [
|
|
3611
|
+
* Whether the original unredacted transcript was also returned alongside the redacted one. When `true`, the response includes `unredacted_text`, `unredacted_words`, and `unredacted_utterances`. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more information.
|
|
3612
|
+
|
|
3613
|
+
*/
|
|
3614
|
+
type TranscriptRedactPiiReturnUnredacted = boolean | null;
|
|
3615
|
+
|
|
3616
|
+
/**
|
|
3617
|
+
* Generated by orval v7.9.0 🍺
|
|
3618
|
+
* Do not edit manually.
|
|
3619
|
+
* AssemblyAI API
|
|
3620
|
+
* AssemblyAI Speech-to-Text API - Batch transcription endpoints. Filtered from the official AssemblyAI docs spec.
|
|
3621
|
+
* OpenAPI spec version: 1.0.0
|
|
3622
|
+
*/
|
|
3623
|
+
/**
|
|
3624
|
+
* Universal-3 Pro generates rich transcripts that can include inline annotations such as audio event markers and speaker cues. Set to `"all"` to remove all inline annotations, or `"speaker"` to remove only speaker cues while keeping other annotations.
|
|
3527
3625
|
|
|
3528
3626
|
Note: This parameter is only supported for the Universal-3 Pro model.
|
|
3529
3627
|
|
|
@@ -3531,6 +3629,7 @@ Note: This parameter is only supported for the Universal-3 Pro model.
|
|
|
3531
3629
|
type TranscriptRemoveAudioTags = (typeof TranscriptRemoveAudioTags)[keyof typeof TranscriptRemoveAudioTags];
|
|
3532
3630
|
declare const TranscriptRemoveAudioTags: {
|
|
3533
3631
|
readonly all: "all";
|
|
3632
|
+
readonly speaker: "speaker";
|
|
3534
3633
|
};
|
|
3535
3634
|
|
|
3536
3635
|
/**
|
|
@@ -3542,7 +3641,7 @@ declare const TranscriptRemoveAudioTags: {
|
|
|
3542
3641
|
*/
|
|
3543
3642
|
|
|
3544
3643
|
/**
|
|
3545
|
-
*
|
|
3644
|
+
* Universal-3 Pro generates rich transcripts that can include inline annotations such as audio event markers and speaker cues. Set to `"all"` to remove all inline annotations, or `"speaker"` to remove only speaker cues while keeping other annotations.
|
|
3546
3645
|
|
|
3547
3646
|
Note: This parameter is only supported for the Universal-3 Pro model.
|
|
3548
3647
|
|
|
@@ -4021,7 +4120,7 @@ type TranscriptSummary = string | null;
|
|
|
4021
4120
|
*/
|
|
4022
4121
|
/**
|
|
4023
4122
|
* The Summarization model used to generate the summary,
|
|
4024
|
-
if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts
|
|
4123
|
+
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.
|
|
4025
4124
|
|
|
4026
4125
|
*/
|
|
4027
4126
|
type TranscriptSummaryModel = string | null;
|
|
@@ -4034,7 +4133,7 @@ type TranscriptSummaryModel = string | null;
|
|
|
4034
4133
|
* OpenAPI spec version: 1.0.0
|
|
4035
4134
|
*/
|
|
4036
4135
|
/**
|
|
4037
|
-
* The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts
|
|
4136
|
+
* The type of summary generated, 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.
|
|
4038
4137
|
*/
|
|
4039
4138
|
type TranscriptSummaryType = string | null;
|
|
4040
4139
|
|
|
@@ -4092,6 +4191,19 @@ interface TranscriptTranslatedTexts {
|
|
|
4092
4191
|
language_code?: string;
|
|
4093
4192
|
}
|
|
4094
4193
|
|
|
4194
|
+
/**
|
|
4195
|
+
* Generated by orval v7.9.0 🍺
|
|
4196
|
+
* Do not edit manually.
|
|
4197
|
+
* AssemblyAI API
|
|
4198
|
+
* AssemblyAI Speech-to-Text API - Batch transcription endpoints. Filtered from the official AssemblyAI docs spec.
|
|
4199
|
+
* OpenAPI spec version: 1.0.0
|
|
4200
|
+
*/
|
|
4201
|
+
/**
|
|
4202
|
+
* The original textual transcript of your media file before PII redaction was applied. Only returned when `redact_pii_return_unredacted` was set to `true` on the transcription request, otherwise this field is omitted and the `text` field remains fully redacted. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more information.
|
|
4203
|
+
|
|
4204
|
+
*/
|
|
4205
|
+
type TranscriptUnredactedText = string | null;
|
|
4206
|
+
|
|
4095
4207
|
/**
|
|
4096
4208
|
* Generated by orval v7.9.0 🍺
|
|
4097
4209
|
* Do not edit manually.
|
|
@@ -4192,6 +4304,34 @@ interface TranscriptUtterance {
|
|
|
4192
4304
|
translated_texts?: TranscriptUtteranceTranslatedTexts;
|
|
4193
4305
|
}
|
|
4194
4306
|
|
|
4307
|
+
/**
|
|
4308
|
+
* Generated by orval v7.9.0 🍺
|
|
4309
|
+
* Do not edit manually.
|
|
4310
|
+
* AssemblyAI API
|
|
4311
|
+
* AssemblyAI Speech-to-Text API - Batch transcription endpoints. Filtered from the official AssemblyAI docs spec.
|
|
4312
|
+
* OpenAPI spec version: 1.0.0
|
|
4313
|
+
*/
|
|
4314
|
+
|
|
4315
|
+
/**
|
|
4316
|
+
* The original turn-by-turn utterance objects before PII redaction was applied. Same shape as `utterances`. Only returned when `redact_pii_return_unredacted` was set to `true` on the transcription request, otherwise this field is omitted and the `utterances` field remains fully redacted. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more information.
|
|
4317
|
+
|
|
4318
|
+
*/
|
|
4319
|
+
type TranscriptUnredactedUtterances = TranscriptUtterance[] | null;
|
|
4320
|
+
|
|
4321
|
+
/**
|
|
4322
|
+
* Generated by orval v7.9.0 🍺
|
|
4323
|
+
* Do not edit manually.
|
|
4324
|
+
* AssemblyAI API
|
|
4325
|
+
* AssemblyAI Speech-to-Text API - Batch transcription endpoints. Filtered from the official AssemblyAI docs spec.
|
|
4326
|
+
* OpenAPI spec version: 1.0.0
|
|
4327
|
+
*/
|
|
4328
|
+
|
|
4329
|
+
/**
|
|
4330
|
+
* The original temporally-sequential word objects before PII redaction was applied. Same shape as `words`. Only returned when `redact_pii_return_unredacted` was set to `true` on the transcription request, otherwise this field is omitted and the `words` field remains fully redacted. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more information.
|
|
4331
|
+
|
|
4332
|
+
*/
|
|
4333
|
+
type TranscriptUnredactedWords = TranscriptWord[] | null;
|
|
4334
|
+
|
|
4195
4335
|
/**
|
|
4196
4336
|
* Generated by orval v7.9.0 🍺
|
|
4197
4337
|
* Do not edit manually.
|
|
@@ -4303,7 +4443,7 @@ interface Transcript {
|
|
|
4303
4443
|
content_safety_labels?: TranscriptContentSafetyLabels;
|
|
4304
4444
|
/** 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. */
|
|
4305
4445
|
custom_spelling?: TranscriptCustomSpellingProperty;
|
|
4306
|
-
/** 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 */
|
|
4446
|
+
/** 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. Supported on Universal-3 Pro and Universal-2. */
|
|
4307
4447
|
disfluencies?: TranscriptDisfluencies;
|
|
4308
4448
|
/** 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.
|
|
4309
4449
|
*/
|
|
@@ -4351,6 +4491,9 @@ interface Transcript {
|
|
|
4351
4491
|
language_detection?: TranscriptLanguageDetection;
|
|
4352
4492
|
/** Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection). */
|
|
4353
4493
|
language_detection_options?: TranscriptLanguageDetectionOptions;
|
|
4494
|
+
/** Additional metadata about the transcription, including any warnings emitted while processing the request. Only present when there is information to report; if no fields would be populated, `metadata` is omitted from the response entirely.
|
|
4495
|
+
*/
|
|
4496
|
+
metadata?: TranscriptMetadataProperty;
|
|
4354
4497
|
/** 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 */
|
|
4355
4498
|
multichannel?: TranscriptMultichannel;
|
|
4356
4499
|
/** 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.
|
|
@@ -4380,6 +4523,9 @@ interface Transcript {
|
|
|
4380
4523
|
redact_pii_policies?: TranscriptRedactPiiPolicies;
|
|
4381
4524
|
/** 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. */
|
|
4382
4525
|
redact_pii_sub?: SubstitutionPolicy;
|
|
4526
|
+
/** Whether the original unredacted transcript was also returned alongside the redacted one. When `true`, the response includes `unredacted_text`, `unredacted_words`, and `unredacted_utterances`. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more information.
|
|
4527
|
+
*/
|
|
4528
|
+
redact_pii_return_unredacted?: TranscriptRedactPiiReturnUnredacted;
|
|
4383
4529
|
/** Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/analyze-sentiment-of-speech) is enabled, can be true or false */
|
|
4384
4530
|
sentiment_analysis?: TranscriptSentimentAnalysis;
|
|
4385
4531
|
/** An array of results for the Sentiment Analysis model, if it is enabled.
|
|
@@ -4412,12 +4558,12 @@ interface Transcript {
|
|
|
4412
4558
|
/** 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. */
|
|
4413
4559
|
summary?: TranscriptSummary;
|
|
4414
4560
|
/** The Summarization model used to generate the summary,
|
|
4415
|
-
if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts
|
|
4561
|
+
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.
|
|
4416
4562
|
*/
|
|
4417
4563
|
summary_model?: TranscriptSummaryModel;
|
|
4418
|
-
/** The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts
|
|
4564
|
+
/** The type of summary generated, 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. */
|
|
4419
4565
|
summary_type?: TranscriptSummaryType;
|
|
4420
|
-
/**
|
|
4566
|
+
/** Universal-3 Pro generates rich transcripts that can include inline annotations such as audio event markers and speaker cues. Set to `"all"` to remove all inline annotations, or `"speaker"` to remove only speaker cues while keeping other annotations.
|
|
4421
4567
|
|
|
4422
4568
|
Note: This parameter is only supported for the Universal-3 Pro model.
|
|
4423
4569
|
*/
|
|
@@ -4429,12 +4575,18 @@ interface Transcript {
|
|
|
4429
4575
|
temperature?: TranscriptTemperature;
|
|
4430
4576
|
/** The textual transcript of your media file */
|
|
4431
4577
|
text?: TranscriptText;
|
|
4578
|
+
/** The original textual transcript of your media file before PII redaction was applied. Only returned when `redact_pii_return_unredacted` was set to `true` on the transcription request, otherwise this field is omitted and the `text` field remains fully redacted. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more information.
|
|
4579
|
+
*/
|
|
4580
|
+
unredacted_text?: TranscriptUnredactedText;
|
|
4432
4581
|
/** True while a request is throttled and false when a request is no longer throttled */
|
|
4433
4582
|
throttled?: TranscriptThrottled;
|
|
4434
4583
|
/** When multichannel or speaker_labels is enabled, a list of turn-by-turn utterance objects.
|
|
4435
4584
|
See [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.
|
|
4436
4585
|
*/
|
|
4437
4586
|
utterances?: TranscriptUtterances;
|
|
4587
|
+
/** The original turn-by-turn utterance objects before PII redaction was applied. Same shape as `utterances`. Only returned when `redact_pii_return_unredacted` was set to `true` on the transcription request, otherwise this field is omitted and the `utterances` field remains fully redacted. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more information.
|
|
4588
|
+
*/
|
|
4589
|
+
unredacted_utterances?: TranscriptUnredactedUtterances;
|
|
4438
4590
|
/** Whether [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) authentication details were provided */
|
|
4439
4591
|
webhook_auth: boolean;
|
|
4440
4592
|
/** 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 */
|
|
@@ -4447,6 +4599,9 @@ interface Transcript {
|
|
|
4447
4599
|
/** An array of temporally-sequential word objects, one for each word in the transcript.
|
|
4448
4600
|
*/
|
|
4449
4601
|
words?: TranscriptWords;
|
|
4602
|
+
/** The original temporally-sequential word objects before PII redaction was applied. Same shape as `words`. Only returned when `redact_pii_return_unredacted` was set to `true` on the transcription request, otherwise this field is omitted and the `words` field remains fully redacted. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more information.
|
|
4603
|
+
*/
|
|
4604
|
+
unredacted_words?: TranscriptUnredactedWords;
|
|
4450
4605
|
/** This parameter does not currently have any functionality attached to it. */
|
|
4451
4606
|
acoustic_model: string;
|
|
4452
4607
|
/** This parameter does not currently have any functionality attached to it. */
|
|
@@ -4839,6 +4994,20 @@ declare const V1ListenPostParametersCustomTopicMode: {
|
|
|
4839
4994
|
*/
|
|
4840
4995
|
type V1ListenPostParametersDetectLanguage = boolean | string[];
|
|
4841
4996
|
|
|
4997
|
+
/**
|
|
4998
|
+
* Generated by orval v7.9.0 🍺
|
|
4999
|
+
* Do not edit manually.
|
|
5000
|
+
* Deepgram API
|
|
5001
|
+
* Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
|
|
5002
|
+
* OpenAPI spec version: 1.0.0
|
|
5003
|
+
*/
|
|
5004
|
+
type V1ListenPostParametersDiarizeModel = (typeof V1ListenPostParametersDiarizeModel)[keyof typeof V1ListenPostParametersDiarizeModel];
|
|
5005
|
+
declare const V1ListenPostParametersDiarizeModel: {
|
|
5006
|
+
readonly latest: "latest";
|
|
5007
|
+
readonly v1: "v1";
|
|
5008
|
+
readonly v2: "v2";
|
|
5009
|
+
};
|
|
5010
|
+
|
|
4842
5011
|
/**
|
|
4843
5012
|
* Generated by orval v7.9.0 🍺
|
|
4844
5013
|
* Do not edit manually.
|
|
@@ -5106,6 +5275,10 @@ type ListenTranscribeParams = {
|
|
|
5106
5275
|
* Recognize speaker changes. Each word in the transcript will be assigned a speaker number starting at 0
|
|
5107
5276
|
*/
|
|
5108
5277
|
diarize?: boolean;
|
|
5278
|
+
/**
|
|
5279
|
+
* Select and enable a specific batch diarization model version. If specifying this parameter, you should not set the deprecated `diarize=true` parameter. Not accepted on streaming requests.
|
|
5280
|
+
*/
|
|
5281
|
+
diarize_model?: V1ListenPostParametersDiarizeModel;
|
|
5109
5282
|
/**
|
|
5110
5283
|
* Dictation mode for controlling formatting with dictated speech
|
|
5111
5284
|
*/
|
|
@@ -5396,7 +5569,7 @@ type TranscriptParamsRedactPiiSub = SubstitutionPolicy | null;
|
|
|
5396
5569
|
* OpenAPI spec version: 1.0.0
|
|
5397
5570
|
*/
|
|
5398
5571
|
/**
|
|
5399
|
-
*
|
|
5572
|
+
* Universal-3 Pro generates rich transcripts that can include inline annotations such as audio event markers and speaker cues. Set to `"all"` to remove all inline annotations, or `"speaker"` to remove only speaker cues while keeping other annotations.
|
|
5400
5573
|
|
|
5401
5574
|
Note: This parameter is only supported for the Universal-3 Pro model.
|
|
5402
5575
|
|
|
@@ -5404,6 +5577,7 @@ Note: This parameter is only supported for the Universal-3 Pro model.
|
|
|
5404
5577
|
type TranscriptOptionalParamsRemoveAudioTags = (typeof TranscriptOptionalParamsRemoveAudioTags)[keyof typeof TranscriptOptionalParamsRemoveAudioTags];
|
|
5405
5578
|
declare const TranscriptOptionalParamsRemoveAudioTags: {
|
|
5406
5579
|
readonly all: "all";
|
|
5580
|
+
readonly speaker: "speaker";
|
|
5407
5581
|
};
|
|
5408
5582
|
|
|
5409
5583
|
/**
|
|
@@ -5415,7 +5589,7 @@ declare const TranscriptOptionalParamsRemoveAudioTags: {
|
|
|
5415
5589
|
*/
|
|
5416
5590
|
|
|
5417
5591
|
/**
|
|
5418
|
-
*
|
|
5592
|
+
* Universal-3 Pro generates rich transcripts that can include inline annotations such as audio event markers and speaker cues. Set to `"all"` to remove all inline annotations, or `"speaker"` to remove only speaker cues while keeping other annotations.
|
|
5419
5593
|
|
|
5420
5594
|
Note: This parameter is only supported for the Universal-3 Pro model.
|
|
5421
5595
|
|
|
@@ -5501,7 +5675,7 @@ interface TranscriptParams {
|
|
|
5501
5675
|
content_safety_confidence?: number;
|
|
5502
5676
|
/** 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. */
|
|
5503
5677
|
custom_spelling?: TranscriptCustomSpelling[];
|
|
5504
|
-
/** 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 */
|
|
5678
|
+
/** 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. Supported on Universal-3 Pro and Universal-2. */
|
|
5505
5679
|
disfluencies?: boolean;
|
|
5506
5680
|
/** 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.
|
|
5507
5681
|
|
|
@@ -5557,6 +5731,11 @@ interface TranscriptParams {
|
|
|
5557
5731
|
redact_pii_policies?: PiiPolicy[];
|
|
5558
5732
|
/** 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. */
|
|
5559
5733
|
redact_pii_sub?: TranscriptParamsRedactPiiSub;
|
|
5734
|
+
/** When set to `true`, returns the original unredacted transcript alongside the redacted one in the same response. Requires `redact_pii` to be `true`, otherwise a 400 error is returned.
|
|
5735
|
+
|
|
5736
|
+
When enabled, the response includes the additional fields `unredacted_text`, `unredacted_words`, and `unredacted_utterances`. The existing `text`, `words`, and `utterances` fields remain fully redacted. When disabled (default), the response is unchanged and contains only the redacted transcript. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more details.
|
|
5737
|
+
*/
|
|
5738
|
+
redact_pii_return_unredacted?: boolean;
|
|
5560
5739
|
/** Enable [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/analyze-sentiment-of-speech), can be true or false */
|
|
5561
5740
|
sentiment_analysis?: boolean;
|
|
5562
5741
|
/** Enable [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers), can be true or false */
|
|
@@ -5584,7 +5763,7 @@ interface TranscriptParams {
|
|
|
5584
5763
|
summary_model?: SummaryModel;
|
|
5585
5764
|
/** The type of summary. 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. */
|
|
5586
5765
|
summary_type?: SummaryType;
|
|
5587
|
-
/**
|
|
5766
|
+
/** Universal-3 Pro generates rich transcripts that can include inline annotations such as audio event markers and speaker cues. Set to `"all"` to remove all inline annotations, or `"speaker"` to remove only speaker cues while keeping other annotations.
|
|
5588
5767
|
|
|
5589
5768
|
Note: This parameter is only supported for the Universal-3 Pro model.
|
|
5590
5769
|
*/
|
|
@@ -5655,9 +5834,9 @@ interface InitTranscriptionRequest {
|
|
|
5655
5834
|
translation?: boolean;
|
|
5656
5835
|
/** **[Beta]** Translation configuration, if `translation` is enabled */
|
|
5657
5836
|
translation_config?: TranslationConfigDTO;
|
|
5658
|
-
/**
|
|
5837
|
+
/** Enable summarization for this audio */
|
|
5659
5838
|
summarization?: boolean;
|
|
5660
|
-
/**
|
|
5839
|
+
/** Summarization configuration, if `summarization` is enabled */
|
|
5661
5840
|
summarization_config?: SummarizationConfigDTO;
|
|
5662
5841
|
/** **[Alpha]** Enable named entity recognition for this audio */
|
|
5663
5842
|
named_entity_recognition?: boolean;
|
|
@@ -5667,9 +5846,9 @@ interface InitTranscriptionRequest {
|
|
|
5667
5846
|
custom_spelling_config?: CustomSpellingConfigDTO;
|
|
5668
5847
|
/** Enable sentiment analysis for this audio */
|
|
5669
5848
|
sentiment_analysis?: boolean;
|
|
5670
|
-
/**
|
|
5849
|
+
/** Enable audio to LLM processing for this audio */
|
|
5671
5850
|
audio_to_llm?: boolean;
|
|
5672
|
-
/**
|
|
5851
|
+
/** Audio to LLM configuration, if `audio_to_llm` is enabled */
|
|
5673
5852
|
audio_to_llm_config?: AudioToLlmListConfigDTO;
|
|
5674
5853
|
/** Enable PII redaction for this audio */
|
|
5675
5854
|
pii_redaction?: boolean;
|
|
@@ -6259,7 +6438,7 @@ type AdditionalFormats = ExportOptions[];
|
|
|
6259
6438
|
* OpenAPI spec version: 1.0
|
|
6260
6439
|
*/
|
|
6261
6440
|
/**
|
|
6262
|
-
* The HTTPS URL of the file to transcribe. Exactly one of the file or cloud_storage_url parameters must be provided. The file must be accessible via HTTPS and the file size must be less than 2GB. Any valid HTTPS URL is accepted, including URLs from cloud storage providers (AWS S3, Google Cloud Storage, Cloudflare R2, etc.), CDNs, or any other HTTPS source. URLs can be pre-signed or include authentication tokens in query parameters.
|
|
6441
|
+
* [Deprecated] This parameter is deprecated and will be removed in the future. Use 'source_url' instead.The HTTPS URL of the file to transcribe. Exactly one of the file or cloud_storage_url parameters must be provided. The file must be accessible via HTTPS and the file size must be less than 2GB. Any valid HTTPS URL is accepted, including URLs from cloud storage providers (AWS S3, Google Cloud Storage, Cloudflare R2, etc.), CDNs, or any other HTTPS source. URLs can be pre-signed or include authentication tokens in query parameters.
|
|
6263
6442
|
* @deprecated
|
|
6264
6443
|
*/
|
|
6265
6444
|
type BodySpeechToTextV1SpeechToTextPostCloudStorageUrl = string | null;
|
|
@@ -6308,7 +6487,7 @@ type BodySpeechToTextV1SpeechToTextPostEntityRedaction = string | string[] | nul
|
|
|
6308
6487
|
* OpenAPI spec version: 1.0
|
|
6309
6488
|
*/
|
|
6310
6489
|
/**
|
|
6311
|
-
* The file to transcribe (100ms minimum audio length). All major audio and video formats are supported. Exactly one of the file or cloud_storage_url parameters must be provided. The file size must be less than
|
|
6490
|
+
* The file to transcribe (100ms minimum audio length). All major audio and video formats are supported. Exactly one of the file or cloud_storage_url parameters must be provided. The file size must be less than 5.0GB.
|
|
6312
6491
|
*/
|
|
6313
6492
|
type BodySpeechToTextV1SpeechToTextPostFile = Blob | null;
|
|
6314
6493
|
|
|
@@ -6468,7 +6647,7 @@ type BodySpeechToTextV1SpeechToTextPostWebhookMetadata = string | BodySpeechToTe
|
|
|
6468
6647
|
interface BodySpeechToTextV1SpeechToTextPost {
|
|
6469
6648
|
/** The ID of the model to use for transcription. */
|
|
6470
6649
|
model_id: BodySpeechToTextV1SpeechToTextPostModelId;
|
|
6471
|
-
/** The file to transcribe (100ms minimum audio length). All major audio and video formats are supported. Exactly one of the file or cloud_storage_url parameters must be provided. The file size must be less than
|
|
6650
|
+
/** The file to transcribe (100ms minimum audio length). All major audio and video formats are supported. Exactly one of the file or cloud_storage_url parameters must be provided. The file size must be less than 5.0GB. */
|
|
6472
6651
|
file?: BodySpeechToTextV1SpeechToTextPostFile;
|
|
6473
6652
|
/** An ISO-639-1 or ISO-639-3 language_code corresponding to the language of the audio file. Can sometimes improve transcription performance if known beforehand. Defaults to null, in this case the language is predicted automatically. */
|
|
6474
6653
|
language_code?: BodySpeechToTextV1SpeechToTextPostLanguageCode;
|
|
@@ -6487,7 +6666,7 @@ interface BodySpeechToTextV1SpeechToTextPost {
|
|
|
6487
6666
|
/** The format of input audio. Options are 'pcm_s16le_16' or 'other' For `pcm_s16le_16`, the input audio must be 16-bit PCM at a 16kHz sample rate, single channel (mono), and little-endian byte order. Latency will be lower than with passing an encoded waveform. */
|
|
6488
6667
|
file_format?: BodySpeechToTextV1SpeechToTextPostFileFormat;
|
|
6489
6668
|
/**
|
|
6490
|
-
* The HTTPS URL of the file to transcribe. Exactly one of the file or cloud_storage_url parameters must be provided. The file must be accessible via HTTPS and the file size must be less than 2GB. Any valid HTTPS URL is accepted, including URLs from cloud storage providers (AWS S3, Google Cloud Storage, Cloudflare R2, etc.), CDNs, or any other HTTPS source. URLs can be pre-signed or include authentication tokens in query parameters.
|
|
6669
|
+
* [Deprecated] This parameter is deprecated and will be removed in the future. Use 'source_url' instead.The HTTPS URL of the file to transcribe. Exactly one of the file or cloud_storage_url parameters must be provided. The file must be accessible via HTTPS and the file size must be less than 2GB. Any valid HTTPS URL is accepted, including URLs from cloud storage providers (AWS S3, Google Cloud Storage, Cloudflare R2, etc.), CDNs, or any other HTTPS source. URLs can be pre-signed or include authentication tokens in query parameters.
|
|
6491
6670
|
* @deprecated
|
|
6492
6671
|
*/
|
|
6493
6672
|
cloud_storage_url?: BodySpeechToTextV1SpeechToTextPostCloudStorageUrl;
|
|
@@ -6515,7 +6694,7 @@ interface BodySpeechToTextV1SpeechToTextPost {
|
|
|
6515
6694
|
entity_redaction?: BodySpeechToTextV1SpeechToTextPostEntityRedaction;
|
|
6516
6695
|
/** How to format redacted entities. 'redacted' replaces with {REDACTED}, 'entity_type' replaces with {ENTITY_TYPE}, 'enumerated_entity_type' replaces with {ENTITY_TYPE_N} where N enumerates each occurrence. Only used when entity_redaction is set. */
|
|
6517
6696
|
entity_redaction_mode?: string;
|
|
6518
|
-
/** A list of keyterms to bias the transcription towards. The keyterms are words or phrases you want the model to recognise more accurately. The number of keyterms cannot exceed 1000. The length of each keyterm must be less than 50 characters. Keyterms can contain at most 5 words (after normalisation). For example ["hello", "world", "technical term"]. Usage of this parameter will incur an additional 20% surcharge on the base transcription cost. When more than 100 keyterms are provided, a minimum billable duration of 20 seconds applies per request. */
|
|
6697
|
+
/** A list of keyterms to bias the transcription towards. The keyterms are words or phrases you want the model to recognise more accurately. The number of keyterms cannot exceed 1000. The length of each keyterm must be less than 50 characters. Keyterms can contain at most 5 words (after normalisation). For example ["hello", "world", "technical term"]. The following characters are not supported: `<`, `>`, `{`, `}`, `[`, `]`, `\`. Usage of this parameter will incur an additional 20% surcharge on the base transcription cost. When more than 100 keyterms are provided, a minimum billable duration of 20 seconds applies per request. */
|
|
6519
6698
|
keyterms?: string[];
|
|
6520
6699
|
}
|
|
6521
6700
|
|
|
@@ -7096,7 +7275,7 @@ declare const StreamingSupportedRegions: {
|
|
|
7096
7275
|
* The Realtime model used for this session.
|
|
7097
7276
|
|
|
7098
7277
|
*/
|
|
7099
|
-
type RealtimeSessionCreateRequestGAModel = string | "gpt-realtime" | "gpt-realtime-1.5" | "gpt-realtime-2025-08-28" | "gpt-4o-realtime-preview" | "gpt-4o-realtime-preview-2024-10-01" | "gpt-4o-realtime-preview-2024-12-17" | "gpt-4o-realtime-preview-2025-06-03" | "gpt-4o-mini-realtime-preview" | "gpt-4o-mini-realtime-preview-2024-12-17" | "gpt-realtime-mini" | "gpt-realtime-mini-2025-10-06" | "gpt-realtime-mini-2025-12-15" | "gpt-audio-1.5" | "gpt-audio-mini" | "gpt-audio-mini-2025-10-06" | "gpt-audio-mini-2025-12-15";
|
|
7278
|
+
type RealtimeSessionCreateRequestGAModel = string | "gpt-realtime" | "gpt-realtime-1.5" | "gpt-realtime-2" | "gpt-realtime-2025-08-28" | "gpt-4o-realtime-preview" | "gpt-4o-realtime-preview-2024-10-01" | "gpt-4o-realtime-preview-2024-12-17" | "gpt-4o-realtime-preview-2025-06-03" | "gpt-4o-mini-realtime-preview" | "gpt-4o-mini-realtime-preview-2024-12-17" | "gpt-realtime-mini" | "gpt-realtime-mini-2025-10-06" | "gpt-realtime-mini-2025-12-15" | "gpt-audio-1.5" | "gpt-audio-mini" | "gpt-audio-mini-2025-10-06" | "gpt-audio-mini-2025-12-15";
|
|
7100
7279
|
|
|
7101
7280
|
/**
|
|
7102
7281
|
* Generated by orval v7.9.0 🍺
|
|
@@ -7608,6 +7787,11 @@ interface SonioxStreamingOptions {
|
|
|
7608
7787
|
* ```
|
|
7609
7788
|
*/
|
|
7610
7789
|
languageHints?: SonioxLanguageCode[];
|
|
7790
|
+
/**
|
|
7791
|
+
* When true, recognition is strongly biased toward language hints.
|
|
7792
|
+
* Best-effort only, not a hard guarantee.
|
|
7793
|
+
*/
|
|
7794
|
+
languageHintsStrict?: boolean;
|
|
7611
7795
|
/**
|
|
7612
7796
|
* Enable language identification
|
|
7613
7797
|
* Each token will include a language field
|
|
@@ -7623,6 +7807,11 @@ interface SonioxStreamingOptions {
|
|
|
7623
7807
|
* Detects when a speaker has finished talking
|
|
7624
7808
|
*/
|
|
7625
7809
|
enableEndpointDetection?: boolean;
|
|
7810
|
+
/**
|
|
7811
|
+
* Maximum delay between the end of speech and returned endpoint.
|
|
7812
|
+
* Supported range is 500-3000 ms.
|
|
7813
|
+
*/
|
|
7814
|
+
maxEndpointDelayMs?: number;
|
|
7626
7815
|
/**
|
|
7627
7816
|
* Additional context to improve transcription accuracy
|
|
7628
7817
|
* Can be a structured object or plain string
|
|
@@ -7658,6 +7847,21 @@ interface SonioxStreamingOptions {
|
|
|
7658
7847
|
* Useful for correlating requests in logs
|
|
7659
7848
|
*/
|
|
7660
7849
|
clientReferenceId?: string;
|
|
7850
|
+
/**
|
|
7851
|
+
* Interval for keepalive messages while paused, in milliseconds.
|
|
7852
|
+
* SDK session option, not sent to Soniox.
|
|
7853
|
+
*/
|
|
7854
|
+
keepaliveIntervalMs?: number;
|
|
7855
|
+
/**
|
|
7856
|
+
* Max time to wait for the WebSocket connection to open, in milliseconds.
|
|
7857
|
+
* SDK session option, not sent to Soniox.
|
|
7858
|
+
*/
|
|
7859
|
+
connectTimeoutMs?: number;
|
|
7860
|
+
/**
|
|
7861
|
+
* AbortSignal for cancelling the real-time session.
|
|
7862
|
+
* SDK session option, not sent to Soniox.
|
|
7863
|
+
*/
|
|
7864
|
+
signal?: AbortSignal;
|
|
7661
7865
|
}
|
|
7662
7866
|
/**
|
|
7663
7867
|
* ElevenLabs realtime streaming options
|
|
@@ -8024,6 +8228,25 @@ type ListProjectRequestsParams = {
|
|
|
8024
8228
|
* These types provide a provider-agnostic interface for transcription services
|
|
8025
8229
|
*/
|
|
8026
8230
|
|
|
8231
|
+
interface SonioxBatchOptions {
|
|
8232
|
+
language_hints?: string[];
|
|
8233
|
+
language_hints_strict?: boolean;
|
|
8234
|
+
enable_language_identification?: boolean;
|
|
8235
|
+
enable_speaker_diarization?: boolean;
|
|
8236
|
+
context?: TranscriptionContext | CreateTranscriptionPayload["context"];
|
|
8237
|
+
translation?: TranslationConfig$1 | CreateTranscriptionPayload["translation"];
|
|
8238
|
+
webhook_url?: string;
|
|
8239
|
+
webhook_auth_header_name?: string;
|
|
8240
|
+
webhook_auth_header_value?: string;
|
|
8241
|
+
client_reference_id?: string;
|
|
8242
|
+
wait?: boolean;
|
|
8243
|
+
wait_options?: WaitOptions;
|
|
8244
|
+
fetch_transcript?: boolean;
|
|
8245
|
+
webhook_query?: string | URLSearchParams | Record<string, string>;
|
|
8246
|
+
signal?: AbortSignal;
|
|
8247
|
+
timeout_ms?: number;
|
|
8248
|
+
cleanup?: CleanupTarget[];
|
|
8249
|
+
}
|
|
8027
8250
|
/**
|
|
8028
8251
|
* Speechmatics operating point (model) type
|
|
8029
8252
|
* Manually defined as Speechmatics OpenAPI spec doesn't export this cleanly
|
|
@@ -8322,7 +8545,7 @@ interface TranscribeOptions {
|
|
|
8322
8545
|
* Soniox-specific options (passed directly to API)
|
|
8323
8546
|
* @see https://soniox.com/docs/stt/
|
|
8324
8547
|
*/
|
|
8325
|
-
soniox?:
|
|
8548
|
+
soniox?: SonioxBatchOptions;
|
|
8326
8549
|
}
|
|
8327
8550
|
/**
|
|
8328
8551
|
* Speaker information from diarization
|
|
@@ -9162,6 +9385,33 @@ interface StreamingSession {
|
|
|
9162
9385
|
getStatus: () => "connecting" | "open" | "closing" | "closed";
|
|
9163
9386
|
/** Session creation timestamp */
|
|
9164
9387
|
createdAt: Date;
|
|
9388
|
+
/**
|
|
9389
|
+
* Pause audio transmission when supported by the provider.
|
|
9390
|
+
* Currently implemented by Soniox real-time sessions.
|
|
9391
|
+
*/
|
|
9392
|
+
pause?: () => void;
|
|
9393
|
+
/**
|
|
9394
|
+
* Resume audio transmission when supported by the provider.
|
|
9395
|
+
* Currently implemented by Soniox real-time sessions.
|
|
9396
|
+
*/
|
|
9397
|
+
resume?: () => void;
|
|
9398
|
+
/**
|
|
9399
|
+
* Ask the provider to finalize the current utterance when supported.
|
|
9400
|
+
* Currently implemented by Soniox real-time sessions.
|
|
9401
|
+
*/
|
|
9402
|
+
finalize?: (options?: {
|
|
9403
|
+
trailingSilenceMs?: number;
|
|
9404
|
+
}) => void;
|
|
9405
|
+
/**
|
|
9406
|
+
* Send a keepalive ping when supported by the provider.
|
|
9407
|
+
* Currently implemented by Soniox real-time sessions.
|
|
9408
|
+
*/
|
|
9409
|
+
keepAlive?: () => void;
|
|
9410
|
+
/**
|
|
9411
|
+
* Access the provider-native streaming session object when available.
|
|
9412
|
+
* Currently implemented by Soniox as a `RealtimeSttSession`.
|
|
9413
|
+
*/
|
|
9414
|
+
getRawSession?: () => unknown;
|
|
9165
9415
|
}
|
|
9166
9416
|
|
|
9167
9417
|
/**
|
|
@@ -9343,9 +9593,13 @@ interface AudioEventSummary {
|
|
|
9343
9593
|
* OpenAPI spec version: 2.0.0
|
|
9344
9594
|
*/
|
|
9345
9595
|
interface Chapter {
|
|
9596
|
+
/** The auto-generated title for the chapter */
|
|
9346
9597
|
title?: string;
|
|
9598
|
+
/** An auto-generated paragraph-style, short summary of the chapter */
|
|
9347
9599
|
summary?: string;
|
|
9600
|
+
/** The start time of the chapter in the audio file */
|
|
9348
9601
|
start_time?: number;
|
|
9602
|
+
/** The end time of the chapter in the audio file */
|
|
9349
9603
|
end_time?: number;
|
|
9350
9604
|
}
|
|
9351
9605
|
|
|
@@ -9487,6 +9741,25 @@ type TranscriptionConfigAdditionalVocabItem = {
|
|
|
9487
9741
|
sounds_like?: string[];
|
|
9488
9742
|
};
|
|
9489
9743
|
|
|
9744
|
+
/**
|
|
9745
|
+
* Generated by orval v7.9.0 🍺
|
|
9746
|
+
* Do not edit manually.
|
|
9747
|
+
* Speechmatics ASR REST API
|
|
9748
|
+
* The Speechmatics Automatic Speech Recognition REST API is used to submit ASR jobs and receive the results. The supported job type is transcription of audio files.
|
|
9749
|
+
* OpenAPI spec version: 2.0.0
|
|
9750
|
+
*/
|
|
9751
|
+
/**
|
|
9752
|
+
* Configuration for limiting the transcription of quiet audio.
|
|
9753
|
+
*/
|
|
9754
|
+
type TranscriptionConfigAudioFilteringConfig = {
|
|
9755
|
+
/**
|
|
9756
|
+
* Controls the lower limit of audio volume at which speech and audio events will be transcribed. If the volume limit is very low, then most sound will be passed to the speech recognition engine. Higher numbers will cut out increasing amounts of sound.
|
|
9757
|
+
* @minimum 0
|
|
9758
|
+
* @maximum 100
|
|
9759
|
+
*/
|
|
9760
|
+
volume_threshold?: number;
|
|
9761
|
+
};
|
|
9762
|
+
|
|
9490
9763
|
/**
|
|
9491
9764
|
* Generated by orval v7.9.0 🍺
|
|
9492
9765
|
* Do not edit manually.
|
|
@@ -9554,6 +9827,24 @@ type TranscriptionConfigPunctuationOverrides = {
|
|
|
9554
9827
|
* The Speechmatics Automatic Speech Recognition REST API is used to submit ASR jobs and receive the results. The supported job type is transcription of audio files.
|
|
9555
9828
|
* OpenAPI spec version: 2.0.0
|
|
9556
9829
|
*/
|
|
9830
|
+
interface SpeakersInputItem {
|
|
9831
|
+
/**
|
|
9832
|
+
* Speaker label, which must not match the format used internally (e.g. S1, S2, etc)
|
|
9833
|
+
* @minLength 1
|
|
9834
|
+
*/
|
|
9835
|
+
label: string;
|
|
9836
|
+
/** @minItems 1 */
|
|
9837
|
+
speaker_identifiers: string[];
|
|
9838
|
+
}
|
|
9839
|
+
|
|
9840
|
+
/**
|
|
9841
|
+
* Generated by orval v7.9.0 🍺
|
|
9842
|
+
* Do not edit manually.
|
|
9843
|
+
* Speechmatics ASR REST API
|
|
9844
|
+
* The Speechmatics Automatic Speech Recognition REST API is used to submit ASR jobs and receive the results. The supported job type is transcription of audio files.
|
|
9845
|
+
* OpenAPI spec version: 2.0.0
|
|
9846
|
+
*/
|
|
9847
|
+
|
|
9557
9848
|
/**
|
|
9558
9849
|
* Configuration for speaker diarization
|
|
9559
9850
|
*/
|
|
@@ -9566,6 +9857,10 @@ type TranscriptionConfigSpeakerDiarizationConfig = {
|
|
|
9566
9857
|
* @maximum 1
|
|
9567
9858
|
*/
|
|
9568
9859
|
speaker_sensitivity?: number;
|
|
9860
|
+
/** If true, speaker identifiers will be returned at the end of transcript. */
|
|
9861
|
+
get_speakers?: boolean;
|
|
9862
|
+
/** Use this option to provide speaker labels linked to their speaker identifiers. When passed, the transcription system will tag spoken words in the transcript with the provided speaker labels whenever any of the specified speakers is detected in the audio. A maximum of 50 speakers identifiers across all speakers can be provided. */
|
|
9863
|
+
speakers?: SpeakersInputItem[];
|
|
9569
9864
|
};
|
|
9570
9865
|
|
|
9571
9866
|
/**
|
|
@@ -9576,7 +9871,9 @@ type TranscriptionConfigSpeakerDiarizationConfig = {
|
|
|
9576
9871
|
* OpenAPI spec version: 2.0.0
|
|
9577
9872
|
*/
|
|
9578
9873
|
type TranscriptionConfigTranscriptFilteringConfigReplacementsItem = {
|
|
9874
|
+
/** The text or pattern identified to be replaced. */
|
|
9579
9875
|
from: string;
|
|
9876
|
+
/** The corrected or formatted string to appear in the transcript. */
|
|
9580
9877
|
to: string;
|
|
9581
9878
|
};
|
|
9582
9879
|
|
|
@@ -9589,12 +9886,12 @@ type TranscriptionConfigTranscriptFilteringConfigReplacementsItem = {
|
|
|
9589
9886
|
*/
|
|
9590
9887
|
|
|
9591
9888
|
/**
|
|
9592
|
-
* Configuration for applying filtering to the transcription
|
|
9889
|
+
* Configuration for applying filtering to the transcription.
|
|
9593
9890
|
*/
|
|
9594
9891
|
type TranscriptionConfigTranscriptFilteringConfig = {
|
|
9595
|
-
/** If true, words
|
|
9892
|
+
/** If true, words identified as disfluencies (e.g., 'um', 'uh') will be removed from the transcript. If false (default), they are tagged in the transcript as 'disfluency'. */
|
|
9596
9893
|
remove_disfluencies?: boolean;
|
|
9597
|
-
/**
|
|
9894
|
+
/** An array of objects defining custom replacements. Each replacement contains a pair of strings: the text to find ("from:") and the text to replace it with ("to:"). */
|
|
9598
9895
|
replacements?: TranscriptionConfigTranscriptFilteringConfigReplacementsItem[];
|
|
9599
9896
|
};
|
|
9600
9897
|
|
|
@@ -9632,7 +9929,9 @@ interface TranscriptionConfig {
|
|
|
9632
9929
|
enable_entities?: boolean;
|
|
9633
9930
|
/** Whether or not to enable flexible endpointing and allow the entity to continue to be spoken. */
|
|
9634
9931
|
max_delay_mode?: TranscriptionConfigMaxDelayMode;
|
|
9635
|
-
/** Configuration for
|
|
9932
|
+
/** Configuration for limiting the transcription of quiet audio. */
|
|
9933
|
+
audio_filtering_config?: TranscriptionConfigAudioFilteringConfig;
|
|
9934
|
+
/** Configuration for applying filtering to the transcription. */
|
|
9636
9935
|
transcript_filtering_config?: TranscriptionConfigTranscriptFilteringConfig;
|
|
9637
9936
|
/** Configuration for speaker diarization */
|
|
9638
9937
|
speaker_diarization_config?: TranscriptionConfigSpeakerDiarizationConfig;
|
|
@@ -9932,6 +10231,8 @@ interface RecognitionMetadata {
|
|
|
9932
10231
|
created_at: string;
|
|
9933
10232
|
type: JobType;
|
|
9934
10233
|
transcription_config?: TranscriptionConfig;
|
|
10234
|
+
/** The engine version used to generate transcription output. */
|
|
10235
|
+
orchestrator_version?: string;
|
|
9935
10236
|
/** List of errors that occurred in the translation stage. */
|
|
9936
10237
|
translation_errors?: TranslationError[];
|
|
9937
10238
|
/** List of errors that occurred in the summarization stage. */
|
|
@@ -9946,8 +10247,6 @@ interface RecognitionMetadata {
|
|
|
9946
10247
|
output_config?: OutputConfig;
|
|
9947
10248
|
language_pack_info?: LanguagePackInfo;
|
|
9948
10249
|
language_identification?: LanguageIdentificationResult;
|
|
9949
|
-
/** Orchestrator version in PEP 440 Format or set to 'version_not_found' as default. */
|
|
9950
|
-
orchestrator_version?: string;
|
|
9951
10250
|
}
|
|
9952
10251
|
|
|
9953
10252
|
/**
|
|
@@ -10159,12 +10458,19 @@ type RetrieveTranscriptResponseTranslations = {
|
|
|
10159
10458
|
* Represents a segment of text and its associated sentiment.
|
|
10160
10459
|
*/
|
|
10161
10460
|
interface SentimentSegment {
|
|
10461
|
+
/** Represents the transcript of the analysed segment */
|
|
10162
10462
|
text?: string;
|
|
10463
|
+
/** The assigned sentiment to the segment, which can be positive, neutral or negative */
|
|
10464
|
+
sentiment?: string;
|
|
10465
|
+
/** The timestamp corresponding to the beginning of the transcription segment */
|
|
10163
10466
|
start_time?: number;
|
|
10467
|
+
/** The timestamp corresponding to the end of the transcription segment */
|
|
10164
10468
|
end_time?: number;
|
|
10165
|
-
|
|
10469
|
+
/** The speaker label for the segment, if speaker diarization is enabled */
|
|
10166
10470
|
speaker?: string;
|
|
10471
|
+
/** The channel label for the segment, if channel diarization is enabled */
|
|
10167
10472
|
channel?: string;
|
|
10473
|
+
/** A confidence score in the range of 0-1 */
|
|
10168
10474
|
confidence?: number;
|
|
10169
10475
|
}
|
|
10170
10476
|
|
|
@@ -10270,6 +10576,23 @@ interface SentimentAnalysisResult {
|
|
|
10270
10576
|
sentiment_analysis?: SentimentAnalysisResultSentimentAnalysis;
|
|
10271
10577
|
}
|
|
10272
10578
|
|
|
10579
|
+
/**
|
|
10580
|
+
* Generated by orval v7.9.0 🍺
|
|
10581
|
+
* Do not edit manually.
|
|
10582
|
+
* Speechmatics ASR REST API
|
|
10583
|
+
* The Speechmatics Automatic Speech Recognition REST API is used to submit ASR jobs and receive the results. The supported job type is transcription of audio files.
|
|
10584
|
+
* OpenAPI spec version: 2.0.0
|
|
10585
|
+
*/
|
|
10586
|
+
interface SpeakersResultItem {
|
|
10587
|
+
/**
|
|
10588
|
+
* Speaker label.
|
|
10589
|
+
* @minLength 1
|
|
10590
|
+
*/
|
|
10591
|
+
label: string;
|
|
10592
|
+
/** @minItems 1 */
|
|
10593
|
+
speaker_identifiers: string[];
|
|
10594
|
+
}
|
|
10595
|
+
|
|
10273
10596
|
/**
|
|
10274
10597
|
* Generated by orval v7.9.0 🍺
|
|
10275
10598
|
* Do not edit manually.
|
|
@@ -10376,6 +10699,8 @@ interface RetrieveTranscriptResponse {
|
|
|
10376
10699
|
job: JobInfo;
|
|
10377
10700
|
metadata: RecognitionMetadata;
|
|
10378
10701
|
results: RecognitionResult[];
|
|
10702
|
+
/** List of unique speaker identifiers detected in the transcript. */
|
|
10703
|
+
speakers?: SpeakersResultItem[];
|
|
10379
10704
|
/** Translations of the transcript into other languages. It is a map of ISO language codes to arrays of translated sentences. Configured using `translation_config`. */
|
|
10380
10705
|
translations?: RetrieveTranscriptResponseTranslations;
|
|
10381
10706
|
summary?: SummarizationResult;
|
|
@@ -10849,4 +11174,4 @@ interface SpeechToTextChunkResponseModel {
|
|
|
10849
11174
|
audio_duration_secs?: SpeechToTextChunkResponseModelAudioDurationSecs;
|
|
10850
11175
|
}
|
|
10851
11176
|
|
|
10852
|
-
export { type CustomSpellingConfigDTO as $, type AssemblyAIStreamingOptions as A, type AudioToLlmListDTO as B, type CallbackConfig as C, type DeepgramStreamingOptions as D, type AudioToLlmListDTOError as E, type FileResponse as F, type GladiaStreamingOptions as G, type AudioToLlmResultDTO as H, type CallbackConfigDto as I, CallbackMethodEnum as J, type CallbackTranscriptionErrorPayload as K, type ListTranscriptsOptions as L, type MessagesConfig as M, type NamedEntityRecognitionDTO as N, type CallbackTranscriptionErrorPayloadCustomMetadata as O, type PreProcessingConfig as P, CallbackTranscriptionErrorPayloadEvent as Q, type RealtimeProcessingConfig as R, type StreamingOptions as S, type TranscribeOptions as T, type UnifiedTranscriptResponse as U, type CallbackTranscriptionSuccessPayload as V, type WordDTO as W, type CallbackTranscriptionSuccessPayloadCustomMetadata as X, CallbackTranscriptionSuccessPayloadEvent as Y, type ChapterizationDTOError as Z, type ChapterizationDTOResults as _, type StreamingCallbacks as a, type CustomFormattingRequestBodyCustomFormatting as a$, type CustomSpellingConfigDTOSpellingDictionary as a0, type CustomVocabularyConfigDTO as a1, type CustomVocabularyConfigDTOVocabularyItem as a2, type CustomVocabularyEntryDTO as a3, type DiarizationConfigDTO as a4, type DiarizationDTO as a5, type DiarizationDTOError as a6, type DisplayModeDTO as a7, type DisplayModeDTOError as a8, type ErrorDTO as a9, type SubtitlesConfigDTO as aA, SubtitlesFormatEnum as aB, SubtitlesStyleEnum as aC, type SummarizationConfigDTO as aD, type SummarizationDTOError as aE, SummaryTypesEnum as aF, TranscriptionControllerListV2KindItem as aG, type TranscriptionControllerListV2Params as aH, TranscriptionControllerListV2StatusItem as aI, type TranscriptionResultDTO as aJ, type TranslationConfigDTO as aK, type TranslationDTOError as aL, TranslationModelEnum as aM, type TranslationResultDTO as aN, type TranslationResultDTOError as aO, TranscriptStatus as aP, type TranscriptWord as aQ, AudioIntelligenceModelStatus as aR, type AutoHighlightResult as aS, type AutoHighlightsResult as aT, type Chapter$1 as aU, type ContentSafetyLabel as aV, type ContentSafetyLabelResult as aW, type ContentSafetyLabelsResult as aX, type ContentSafetyLabelsResultSeverityScoreSummary as aY, type ContentSafetyLabelsResultSummary as aZ, type CustomFormattingRequestBody as a_, type InitTranscriptionRequest as aa, type InitTranscriptionRequestCustomMetadata as ab, type ModerationDTO as ac, type ModerationDTOError as ad, type NamedEntityRecognitionDTOError as ae, type NamesConsistencyDTO as af, type NamesConsistencyDTOError as ag, type PiiRedactionConfigDTO as ah, PiiRedactionConfigDTOProcessedTextType as ai, PiiRedactionEntityTypeEnum as aj, type PreRecordedRequestParamsResponse as ak, type PreRecordedResponseCustomMetadata as al, type PreRecordedResponseFile as am, PreRecordedResponseKind as an, type PreRecordedResponsePostSessionMetadata as ao, type PreRecordedResponseRequestParams as ap, type PreRecordedResponseResult as aq, PreRecordedResponseStatus as ar, type SentencesDTO as as, type SentencesDTOError as at, type SentimentAnalysisDTOError as au, type StreamingRequest as av, type StreamingRequestCustomMetadata as aw, type StructuredDataExtractionDTO as ax, type StructuredDataExtractionDTOError as ay, type SubtitleDTO as az, type StreamingSession as b, type TranscriptOptionalParamsSpeechUnderstandingRequest as b$, type CustomFormattingResponse as b0, type CustomFormattingResponseCustomFormatting as b1, type CustomFormattingResponseCustomFormattingMapping as b2, type Entity as b3, EntityType as b4, type ListTranscriptsParams as b5, PiiPolicy as b6, RedactPiiAudioQuality as b7, Sentiment as b8, type SentimentAnalysisResult$1 as b9, type TranscriptConfidence as bA, type TranscriptContentSafety as bB, type TranscriptContentSafetyLabels as bC, type TranscriptCustomSpelling as bD, type TranscriptCustomSpellingProperty as bE, type TranscriptCustomTopics as bF, type TranscriptDisfluencies as bG, type TranscriptDomain as bH, type TranscriptEntities as bI, type TranscriptEntityDetection as bJ, type TranscriptFilterProfanity as bK, type TranscriptFormatText as bL, type TranscriptIabCategories as bM, type TranscriptIabCategoriesResult as bN, TranscriptLanguageCode as bO, type TranscriptLanguageCodes as bP, type TranscriptLanguageConfidence as bQ, type TranscriptLanguageConfidenceThreshold as bR, type TranscriptLanguageDetection as bS, type TranscriptLanguageDetectionOptions as bT, type TranscriptMultichannel as bU, type TranscriptOptionalParamsLanguageDetectionOptions as bV, type TranscriptOptionalParamsRedactPiiAudioOptions as bW, TranscriptOptionalParamsRedactPiiAudioOptionsOverrideAudioRedactionMethod as bX, TranscriptOptionalParamsRemoveAudioTags as bY, type TranscriptOptionalParamsSpeakerOptions as bZ, type TranscriptOptionalParamsSpeechUnderstanding as b_, type SentimentAnalysisResultChannel as ba, type SentimentAnalysisResultSpeaker as bb, type SeverityScoreSummary as bc, type SpeakerIdentificationRequestBody as bd, type SpeakerIdentificationRequestBodySpeakerIdentification as be, SpeakerIdentificationRequestBodySpeakerIdentificationSpeakerType as bf, type SpeakerIdentificationRequestBodySpeakerIdentificationSpeakersItems as bg, type SpeakerIdentificationResponse as bh, type SpeakerIdentificationResponseSpeakerIdentification as bi, type SpeakerIdentificationResponseSpeakerIdentificationMapping as bj, type SpeechModel as bk, SubstitutionPolicy as bl, SummaryModel as bm, SummaryType as bn, type Timestamp as bo, type TopicDetectionModelResult as bp, type TopicDetectionModelResultSummary as bq, type TopicDetectionResult$1 as br, type TopicDetectionResultLabelsItems as bs, type Transcript as bt, type TranscriptAudioDuration as bu, type TranscriptAudioEndAt as bv, type TranscriptAudioStartFrom as bw, type TranscriptAutoChapters as bx, type TranscriptAutoHighlightsResult as by, type TranscriptChapters as bz, type StreamEvent as c, type TranscriptionLinks as c$, type TranscriptParams as c0, type TranscriptParamsDomain as c1, type TranscriptParamsLanguageCode as c2, type TranscriptParamsLanguageCodes as c3, type TranscriptParamsRedactPiiSub as c4, type TranscriptParamsRemoveAudioTags as c5, type TranscriptParamsSpeakersExpected as c6, type TranscriptParamsSpeechThreshold as c7, type TranscriptParamsWebhookAuthHeaderName as c8, type TranscriptParamsWebhookAuthHeaderValue as c9, type TranscriptUtterance as cA, type TranscriptUtteranceChannel as cB, type TranscriptUtteranceTranslatedTexts as cC, type TranscriptUtterances as cD, type TranscriptWebhookAuthHeaderName as cE, type TranscriptWebhookStatusCode as cF, type TranscriptWebhookUrl as cG, type TranscriptWordChannel as cH, type TranscriptWordSpeaker as cI, type TranscriptWords as cJ, type TranslationRequestBody as cK, type TranslationRequestBodyTranslation as cL, type TranslationResponse as cM, type TranslationResponseTranslation as cN, type StreamingUpdateConfiguration as cO, type Transcription$1 as cP, type EntityError as cQ, Status as cR, type EntityReference as cS, type DiarizationProperties as cT, type DiarizationSpeakersProperties as cU, LanguageIdentificationMode as cV, type LanguageIdentificationProperties as cW, type LanguageIdentificationPropertiesSpeechModelMapping as cX, ProfanityFilterMode as cY, PunctuationMode as cZ, type TranscriptionCustomProperties as c_, type TranscriptPunctuate as ca, type TranscriptRedactPiiAudio as cb, type TranscriptRedactPiiAudioOptions as cc, TranscriptRedactPiiAudioOptionsOverrideAudioRedactionMethod as cd, type TranscriptRedactPiiAudioQuality as ce, type TranscriptRedactPiiPolicies as cf, TranscriptRemoveAudioTags as cg, type TranscriptRemoveAudioTagsProperty as ch, type TranscriptSentimentAnalysis as ci, type TranscriptSentimentAnalysisResults as cj, type TranscriptSpeakerLabels as ck, type TranscriptSpeakersExpected as cl, type TranscriptSpeechModel as cm, type TranscriptSpeechModels as cn, type TranscriptSpeechThreshold as co, type TranscriptSpeechUnderstanding as cp, type TranscriptSpeechUnderstandingRequest as cq, type TranscriptSpeechUnderstandingResponse as cr, type TranscriptSpeedBoost as cs, type TranscriptSummary as ct, type TranscriptSummaryModel as cu, type TranscriptSummaryType as cv, type TranscriptTemperature as cw, type TranscriptText as cx, type TranscriptThrottled as cy, type TranscriptTranslatedTexts as cz, StreamingSupportedEncodingEnum as d, type SharedIntentsResultsIntentsSegmentsItems as d$, type TranscriptionProperties as d0, type TranscriptTextUsageTokens as d1, type TranscriptionSegment as d2, type RealtimeSessionCreateRequestGAModel as d3, RealtimeTranscriptionSessionCreateRequestTurnDetectionType as d4, RealtimeTranscriptionSessionCreateRequestInputAudioFormat as d5, AudioResponseFormat as d6, type CreateTranscription200One as d7, type CreateTranscriptionRequest as d8, type CreateTranscriptionRequestChunkingStrategy as d9, type ListProjectRequestsParams as dA, type ListenTranscribeParams as dB, type ListenV1ResponseMetadata as dC, type ListenV1ResponseMetadataIntentsInfo as dD, type ListenV1ResponseMetadataModelInfo as dE, type ListenV1ResponseMetadataSentimentInfo as dF, type ListenV1ResponseMetadataSummaryInfo as dG, type ListenV1ResponseMetadataTopicsInfo as dH, type ListenV1ResponseResults as dI, type ListenV1ResponseResultsChannels as dJ, type ListenV1ResponseResultsChannelsItems as dK, type ListenV1ResponseResultsChannelsItemsAlternativesItems as dL, type ListenV1ResponseResultsChannelsItemsAlternativesItemsEntitiesItems as dM, type ListenV1ResponseResultsChannelsItemsAlternativesItemsParagraphs as dN, type ListenV1ResponseResultsChannelsItemsAlternativesItemsParagraphsParagraphsItems as dO, type ListenV1ResponseResultsChannelsItemsAlternativesItemsParagraphsParagraphsItemsSentencesItems as dP, type ListenV1ResponseResultsChannelsItemsAlternativesItemsSummariesItems as dQ, type ListenV1ResponseResultsChannelsItemsAlternativesItemsTopicsItems as dR, type ListenV1ResponseResultsChannelsItemsAlternativesItemsWordsItems as dS, type ListenV1ResponseResultsChannelsItemsSearchItems as dT, type ListenV1ResponseResultsChannelsItemsSearchItemsHitsItems as dU, type ListenV1ResponseResultsSummary as dV, type ListenV1ResponseResultsUtterances as dW, type ListenV1ResponseResultsUtterancesItems as dX, type ListenV1ResponseResultsUtterancesItemsWordsItems as dY, type SharedIntentsResults as dZ, type SharedIntentsResultsIntents as d_, type CreateTranscriptionRequestChunkingStrategyAnyOf as da, type CreateTranscriptionRequestModel as db, type CreateTranscriptionRequestStream as dc, CreateTranscriptionRequestTimestampGranularitiesItem as dd, type CreateTranscriptionResponseDiarizedJson as de, CreateTranscriptionResponseDiarizedJsonTask as df, type CreateTranscriptionResponseDiarizedJsonUsage as dg, type CreateTranscriptionResponseJson as dh, type CreateTranscriptionResponseJsonLogprobsItem as di, type CreateTranscriptionResponseJsonUsage as dj, type CreateTranscriptionResponseVerboseJson as dk, type TranscriptTextUsageDuration as dl, TranscriptTextUsageDurationType as dm, type TranscriptTextUsageTokensInputTokenDetails as dn, TranscriptTextUsageTokensType as dp, type TranscriptionDiarizedSegment as dq, TranscriptionDiarizedSegmentType as dr, TranscriptionInclude as ds, type TranscriptionWord as dt, type VadConfig as du, VadConfigType as dv, type ListenV1Response as dw, type SharedTopics as dx, type SharedIntents as dy, type SharedSentiments as dz, StreamingSupportedBitDepthEnum as e, type RetrieveTranscriptResponseTranslations as e$, type SharedIntentsResultsIntentsSegmentsItemsIntentsItems as e0, type SharedSentimentsAverage as e1, type SharedSentimentsSegmentsItems as e2, type SharedTopicsResults as e3, type SharedTopicsResultsTopics as e4, type SharedTopicsResultsTopicsSegmentsItems as e5, type SharedTopicsResultsTopicsSegmentsItemsTopicsItems as e6, V1ListenPostParametersCallbackMethod as e7, type V1ListenPostParametersCustomIntent as e8, V1ListenPostParametersCustomIntentMode as e9, type OutputConfig as eA, OperatingPoint as eB, type AudioEventItem as eC, type AudioEventSummary as eD, type AudioEventSummaryItem as eE, type AutoChaptersResult as eF, type AutoChaptersResultError as eG, AutoChaptersResultErrorType as eH, type Chapter as eI, type JobInfo as eJ, type LanguageIdentificationResult as eK, type LanguageIdentificationResultAlternative as eL, LanguageIdentificationResultError as eM, type LanguageIdentificationResultItem as eN, type LanguagePackInfo as eO, LanguagePackInfoWritingDirection as eP, type OutputConfigSrtOverrides as eQ, type RecognitionAlternative as eR, type RecognitionDisplay as eS, RecognitionDisplayDirection as eT, type RecognitionMetadata as eU, type RecognitionResult as eV, RecognitionResultAttachesTo as eW, RecognitionResultType as eX, type RetrieveTranscriptResponse as eY, type RetrieveTranscriptResponseAudioEventSummary as eZ, type RetrieveTranscriptResponseAudioEventSummaryChannels as e_, type V1ListenPostParametersCustomTopic as ea, V1ListenPostParametersCustomTopicMode as eb, type V1ListenPostParametersDetectLanguage as ec, V1ListenPostParametersEncoding as ed, type V1ListenPostParametersExtra as ee, type V1ListenPostParametersKeywords as ef, type V1ListenPostParametersModel as eg, V1ListenPostParametersModel0 as eh, type V1ListenPostParametersRedact as ei, type V1ListenPostParametersRedact1 as ej, V1ListenPostParametersRedactSchemaOneOf1Items as ek, type V1ListenPostParametersReplace as el, type V1ListenPostParametersSearch as em, type V1ListenPostParametersSummarize as en, V1ListenPostParametersSummarize0 as eo, type V1ListenPostParametersTag as ep, type V1ListenPostParametersVersion as eq, V1ListenPostParametersVersion0 as er, V1ProjectsProjectIdRequestsGetParametersDeployment as es, V1ProjectsProjectIdRequestsGetParametersEndpoint as et, V1ProjectsProjectIdRequestsGetParametersMethod as eu, V1ProjectsProjectIdRequestsGetParametersStatus as ev, JobType as ew, type AlignmentConfig as ex, type TranscriptionConfig as ey, type TrackingData as ez, StreamingSupportedSampleRateEnum as f, type TranscriptionWebhookAuthHeaderName as f$, type SentimentAnalysisError as f0, SentimentAnalysisErrorType as f1, type SentimentAnalysisResult as f2, type SentimentAnalysisResultSentimentAnalysis as f3, type SentimentChannelSummary as f4, type SentimentSegment as f5, type SentimentSpeakerSummary as f6, type SentimentSummary as f7, type SentimentSummaryDetail as f8, type SpokenFormRecognitionResult as f9, type CreateTranscriptionPayloadAudioUrl as fA, type CreateTranscriptionPayloadClientReferenceId as fB, type CreateTranscriptionPayloadContext as fC, type CreateTranscriptionPayloadEnableLanguageIdentification as fD, type CreateTranscriptionPayloadEnableSpeakerDiarization as fE, type CreateTranscriptionPayloadFileId as fF, type CreateTranscriptionPayloadLanguageHints as fG, type CreateTranscriptionPayloadLanguageHintsStrict as fH, type CreateTranscriptionPayloadTranslation as fI, type CreateTranscriptionPayloadWebhookAuthHeaderName as fJ, type CreateTranscriptionPayloadWebhookAuthHeaderValue as fK, type CreateTranscriptionPayloadWebhookUrl as fL, type StructuredContext as fM, type StructuredContextGeneral as fN, type StructuredContextGeneralItem as fO, type StructuredContextTerms as fP, type StructuredContextText as fQ, type StructuredContextTranslationTerm as fR, type StructuredContextTranslationTerms as fS, type TranscriptionAudioDurationMs as fT, type TranscriptionAudioUrl as fU, type TranscriptionClientReferenceId as fV, type TranscriptionErrorMessage as fW, type TranscriptionErrorType as fX, type TranscriptionFileId as fY, type TranscriptionLanguageHints as fZ, TranscriptionStatus as f_, SpokenFormRecognitionResultType as fa, type SummarizationError as fb, SummarizationErrorType as fc, type SummarizationResult as fd, type TopicDetectionError as fe, TopicDetectionErrorType as ff, type TopicDetectionResult as fg, type TopicDetectionSegment as fh, type TopicDetectionSegmentTopic as fi, type TopicDetectionSummary as fj, type TopicDetectionSummaryOverall as fk, type TrackingDataDetails as fl, type TranscriptionConfigAdditionalVocabItem as fm, TranscriptionConfigDiarization as fn, TranscriptionConfigMaxDelayMode as fo, type TranscriptionConfigPunctuationOverrides as fp, type TranscriptionConfigSpeakerDiarizationConfig as fq, type TranscriptionConfigTranscriptFilteringConfig as fr, type TranscriptionConfigTranscriptFilteringConfigReplacementsItem as fs, type TranslationError as ft, TranslationErrorType as fu, type TranslationSentence as fv, type WrittenFormRecognitionResult as fw, WrittenFormRecognitionResultType as fx, type Transcription as fy, type CreateTranscriptionPayload as fz, StreamingSupportedModels as g, type SpeechToTextWordResponseModelStart as g$, type TranscriptionWebhookAuthHeaderValue as g0, type TranscriptionWebhookStatusCode as g1, type TranscriptionWebhookUrl as g2, type TranslationConfig as g3, type TranslationConfigLanguageA as g4, type TranslationConfigLanguageB as g5, type TranslationConfigTargetLanguage as g6, TranslationConfigType as g7, type SpeechToTextChunkResponseModel as g8, type AdditionalFormatResponseModel as g9, HtmlExportOptionsFormat as gA, type HtmlExportOptionsMaxSegmentChars as gB, type HtmlExportOptionsMaxSegmentDurationS as gC, type HtmlExportOptionsSegmentOnSilenceLongerThanS as gD, type PdfExportOptions as gE, PdfExportOptionsFormat as gF, type PdfExportOptionsMaxSegmentChars as gG, type PdfExportOptionsMaxSegmentDurationS as gH, type PdfExportOptionsSegmentOnSilenceLongerThanS as gI, type SegmentedJsonExportOptions as gJ, SegmentedJsonExportOptionsFormat as gK, type SegmentedJsonExportOptionsMaxSegmentChars as gL, type SegmentedJsonExportOptionsMaxSegmentDurationS as gM, type SegmentedJsonExportOptionsSegmentOnSilenceLongerThanS as gN, type SpeechToTextCharacterResponseModel as gO, type SpeechToTextCharacterResponseModelEnd as gP, type SpeechToTextCharacterResponseModelStart as gQ, type SpeechToTextChunkResponseModelAdditionalFormats as gR, type SpeechToTextChunkResponseModelAdditionalFormatsAnyOfItem as gS, type SpeechToTextChunkResponseModelAudioDurationSecs as gT, type SpeechToTextChunkResponseModelChannelIndex as gU, type SpeechToTextChunkResponseModelEntities as gV, type SpeechToTextChunkResponseModelTranscriptionId as gW, type SpeechToTextWordResponseModel as gX, type SpeechToTextWordResponseModelCharacters as gY, type SpeechToTextWordResponseModelEnd as gZ, type SpeechToTextWordResponseModelSpeakerId as g_, type AdditionalFormats as ga, type BodySpeechToTextV1SpeechToTextPost as gb, type BodySpeechToTextV1SpeechToTextPostCloudStorageUrl as gc, type BodySpeechToTextV1SpeechToTextPostDiarizationThreshold as gd, type BodySpeechToTextV1SpeechToTextPostEntityDetection as ge, type BodySpeechToTextV1SpeechToTextPostEntityRedaction as gf, type BodySpeechToTextV1SpeechToTextPostFile as gg, BodySpeechToTextV1SpeechToTextPostFileFormat as gh, type BodySpeechToTextV1SpeechToTextPostLanguageCode as gi, BodySpeechToTextV1SpeechToTextPostModelId as gj, type BodySpeechToTextV1SpeechToTextPostNumSpeakers as gk, type BodySpeechToTextV1SpeechToTextPostSeed as gl, type BodySpeechToTextV1SpeechToTextPostSourceUrl as gm, type BodySpeechToTextV1SpeechToTextPostTemperature as gn, BodySpeechToTextV1SpeechToTextPostTimestampsGranularity as go, type BodySpeechToTextV1SpeechToTextPostWebhookId as gp, type BodySpeechToTextV1SpeechToTextPostWebhookMetadata as gq, type BodySpeechToTextV1SpeechToTextPostWebhookMetadataAnyOf as gr, type DetectedEntity as gs, type DocxExportOptions as gt, DocxExportOptionsFormat as gu, type DocxExportOptionsMaxSegmentChars as gv, type DocxExportOptionsMaxSegmentDurationS as gw, type DocxExportOptionsSegmentOnSilenceLongerThanS as gx, type ExportOptions as gy, type HtmlExportOptions as gz, type LanguageConfig as h, SpeechToTextWordResponseModelType as h0, type SrtExportOptions as h1, SrtExportOptionsFormat as h2, type SrtExportOptionsMaxCharactersPerLine as h3, type SrtExportOptionsMaxSegmentChars as h4, type SrtExportOptionsMaxSegmentDurationS as h5, type SrtExportOptionsSegmentOnSilenceLongerThanS as h6, type TxtExportOptions as h7, TxtExportOptionsFormat as h8, type TxtExportOptionsMaxCharactersPerLine as h9, type EntityEvent as hA, type SummarizationEvent as hB, type ChapterizationEvent as hC, type AudioAckEvent as hD, type LifecycleEvent as hE, type AudioChunk as hF, type RawWebSocketMessage as hG, type AssemblyAIUpdateConfiguration as hH, type OpenAIStreamingOptions as hI, type SonioxStreamingOptions as hJ, type ElevenLabsStreamingOptions as hK, type SpeechmaticsStreamingOptions as hL, type ProviderStreamingOptions as hM, type StreamingOptionsForProvider as hN, type TranscribeStreamParams as hO, type BeginEvent as hP, type TurnEvent as hQ, type TerminationEvent as hR, type ErrorEvent as hS, type StreamingEventMessage as hT, type StreamingWord as hU, type StreamingForceEndpoint as hV, type TxtExportOptionsMaxSegmentChars as ha, type TxtExportOptionsMaxSegmentDurationS as hb, type TxtExportOptionsSegmentOnSilenceLongerThanS as hc, type SpeechmaticsOperatingPoint as hd, type TranscriptionModel as he, type TranscriptionLanguage as hf, type AssemblyAIExtendedData as hg, type GladiaExtendedData as hh, type DeepgramExtendedData as hi, type ElevenLabsExtendedData as hj, type ProviderExtendedDataMap as hk, type StreamingProvider as hl, type BatchOnlyProvider as hm, type SessionStatus as hn, type Speaker as ho, type Word as hp, type Utterance as hq, type TranscriptionStatus$1 as hr, type TranscriptMetadata as hs, type TranscriptData as ht, type ListTranscriptsResponse as hu, type ProviderRawResponseMap as hv, type StreamEventType as hw, type SpeechEvent as hx, type TranslationEvent as hy, type SentimentEvent as hz, type PostProcessingConfig as i, type TranscriptionMetadataDTO as j, type TranscriptionDTO as k, type TranslationDTO as l, type SummarizationDTO as m, type SentimentAnalysisDTO as n, type ChapterizationDTO as o, type PreRecordedResponse as p, type UtteranceDTO as q, TranscriptionLanguageCodeEnum as r, TranslationLanguageCodeEnum as s, type NamedEntityRecognitionResult as t, StreamingSupportedRegions as u, type AddonErrorDTO as v, type AudioToLlmDTO as w, type AudioToLlmDTOError as x, type AudioToLlmDTOResults as y, type AudioToLlmListConfigDTO as z };
|
|
11177
|
+
export { type ChapterizationDTOResults as $, type AssemblyAIStreamingOptions as A, type AudioToLlmListConfigDTO as B, type CallbackConfig as C, type DeepgramStreamingOptions as D, type AudioToLlmListDTO as E, type FileResponse as F, type GladiaStreamingOptions as G, type AudioToLlmListDTOError as H, type AudioToLlmResultDTO as I, type CallbackConfigDto as J, CallbackMethodEnum as K, type ListTranscriptsOptions as L, type MessagesConfig as M, type NamedEntityRecognitionDTO as N, type CallbackTranscriptionErrorPayload as O, type PreProcessingConfig as P, type CallbackTranscriptionErrorPayloadCustomMetadata as Q, type RealtimeProcessingConfig as R, type StreamingOptions as S, type TranscribeOptions as T, type UnifiedTranscriptResponse as U, CallbackTranscriptionErrorPayloadEvent as V, type WordDTO as W, type CallbackTranscriptionSuccessPayload as X, type CallbackTranscriptionSuccessPayloadCustomMetadata as Y, CallbackTranscriptionSuccessPayloadEvent as Z, type ChapterizationDTOError as _, type StreamingCallbacks as a, type CustomFormattingRequestBody as a$, type CustomSpellingConfigDTO as a0, type CustomSpellingConfigDTOSpellingDictionary as a1, type CustomVocabularyConfigDTO as a2, type CustomVocabularyConfigDTOVocabularyItem as a3, type CustomVocabularyEntryDTO as a4, type DiarizationConfigDTO as a5, type DiarizationDTO as a6, type DiarizationDTOError as a7, type DisplayModeDTO as a8, type DisplayModeDTOError as a9, type SubtitleDTO as aA, type SubtitlesConfigDTO as aB, SubtitlesFormatEnum as aC, SubtitlesStyleEnum as aD, type SummarizationConfigDTO as aE, type SummarizationDTOError as aF, SummaryTypesEnum as aG, TranscriptionControllerListV2KindItem as aH, type TranscriptionControllerListV2Params as aI, TranscriptionControllerListV2StatusItem as aJ, type TranscriptionResultDTO as aK, type TranslationConfigDTO as aL, type TranslationDTOError as aM, TranslationModelEnum as aN, type TranslationResultDTO as aO, type TranslationResultDTOError as aP, TranscriptStatus as aQ, type TranscriptWord as aR, AudioIntelligenceModelStatus as aS, type AutoHighlightResult as aT, type AutoHighlightsResult as aU, type Chapter$1 as aV, type ContentSafetyLabel as aW, type ContentSafetyLabelResult as aX, type ContentSafetyLabelsResult as aY, type ContentSafetyLabelsResultSeverityScoreSummary as aZ, type ContentSafetyLabelsResultSummary as a_, type ErrorDTO as aa, type InitTranscriptionRequest as ab, type InitTranscriptionRequestCustomMetadata as ac, type ModerationDTO as ad, type ModerationDTOError as ae, type NamedEntityRecognitionDTOError as af, type NamesConsistencyDTO as ag, type NamesConsistencyDTOError as ah, type PiiRedactionConfigDTO as ai, PiiRedactionConfigDTOProcessedTextType as aj, PiiRedactionEntityTypeEnum as ak, type PreRecordedRequestParamsResponse as al, type PreRecordedResponseCustomMetadata as am, type PreRecordedResponseFile as an, PreRecordedResponseKind as ao, type PreRecordedResponsePostSessionMetadata as ap, type PreRecordedResponseRequestParams as aq, type PreRecordedResponseResult as ar, PreRecordedResponseStatus as as, type SentencesDTO as at, type SentencesDTOError as au, type SentimentAnalysisDTOError as av, type StreamingRequest as aw, type StreamingRequestCustomMetadata as ax, type StructuredDataExtractionDTO as ay, type StructuredDataExtractionDTOError as az, type StreamingSession as b, TranscriptOptionalParamsRedactPiiAudioOptionsOverrideAudioRedactionMethod as b$, type CustomFormattingRequestBodyCustomFormatting as b0, type CustomFormattingResponse as b1, type CustomFormattingResponseCustomFormatting as b2, type CustomFormattingResponseCustomFormattingMapping as b3, type Entity as b4, EntityType as b5, type ListTranscriptsParams as b6, PiiPolicy as b7, RedactPiiAudioQuality as b8, Sentiment as b9, type TranscriptChapters as bA, type TranscriptConfidence as bB, type TranscriptContentSafety as bC, type TranscriptContentSafetyLabels as bD, type TranscriptCustomSpelling as bE, type TranscriptCustomSpellingProperty as bF, type TranscriptCustomTopics as bG, type TranscriptDisfluencies as bH, type TranscriptDomain as bI, type TranscriptEntities as bJ, type TranscriptEntityDetection as bK, type TranscriptFilterProfanity as bL, type TranscriptFormatText as bM, type TranscriptIabCategories as bN, type TranscriptIabCategoriesResult as bO, TranscriptLanguageCode as bP, type TranscriptLanguageCodes as bQ, type TranscriptLanguageConfidence as bR, type TranscriptLanguageConfidenceThreshold as bS, type TranscriptLanguageDetection as bT, type TranscriptLanguageDetectionOptions as bU, type TranscriptMetadata$1 as bV, type TranscriptMetadataDomainUsed as bW, type TranscriptMetadataProperty as bX, type TranscriptMultichannel as bY, type TranscriptOptionalParamsLanguageDetectionOptions as bZ, type TranscriptOptionalParamsRedactPiiAudioOptions as b_, type SentimentAnalysisResult$1 as ba, type SentimentAnalysisResultChannel as bb, type SentimentAnalysisResultSpeaker as bc, type SeverityScoreSummary as bd, type SpeakerIdentificationRequestBody as be, type SpeakerIdentificationRequestBodySpeakerIdentification as bf, SpeakerIdentificationRequestBodySpeakerIdentificationSpeakerType as bg, type SpeakerIdentificationRequestBodySpeakerIdentificationSpeakersItems as bh, type SpeakerIdentificationResponse as bi, type SpeakerIdentificationResponseSpeakerIdentification as bj, type SpeakerIdentificationResponseSpeakerIdentificationMapping as bk, type SpeechModel as bl, SubstitutionPolicy as bm, SummaryModel as bn, SummaryType as bo, type Timestamp as bp, type TopicDetectionModelResult as bq, type TopicDetectionModelResultSummary as br, type TopicDetectionResult$1 as bs, type TopicDetectionResultLabelsItems as bt, type Transcript as bu, type TranscriptAudioDuration as bv, type TranscriptAudioEndAt as bw, type TranscriptAudioStartFrom as bx, type TranscriptAutoChapters as by, type TranscriptAutoHighlightsResult as bz, type StreamEvent as c, type EntityReference as c$, TranscriptOptionalParamsRemoveAudioTags as c0, type TranscriptOptionalParamsSpeakerOptions as c1, type TranscriptOptionalParamsSpeechUnderstanding as c2, type TranscriptOptionalParamsSpeechUnderstandingRequest as c3, type TranscriptParams as c4, type TranscriptParamsDomain as c5, type TranscriptParamsLanguageCode as c6, type TranscriptParamsLanguageCodes as c7, type TranscriptParamsRedactPiiSub as c8, type TranscriptParamsRemoveAudioTags as c9, type TranscriptSummaryType as cA, type TranscriptTemperature as cB, type TranscriptText as cC, type TranscriptThrottled as cD, type TranscriptTranslatedTexts as cE, type TranscriptUnredactedText as cF, type TranscriptUnredactedUtterances as cG, type TranscriptUnredactedWords as cH, type TranscriptUtterance as cI, type TranscriptUtteranceChannel as cJ, type TranscriptUtteranceTranslatedTexts as cK, type TranscriptUtterances as cL, type TranscriptWarning as cM, type TranscriptWebhookAuthHeaderName as cN, type TranscriptWebhookStatusCode as cO, type TranscriptWebhookUrl as cP, type TranscriptWordChannel as cQ, type TranscriptWordSpeaker as cR, type TranscriptWords as cS, type TranslationRequestBody as cT, type TranslationRequestBodyTranslation as cU, type TranslationResponse as cV, type TranslationResponseTranslation as cW, type StreamingUpdateConfiguration as cX, type Transcription$1 as cY, type EntityError as cZ, Status as c_, type TranscriptParamsSpeakersExpected as ca, type TranscriptParamsSpeechThreshold as cb, type TranscriptParamsWebhookAuthHeaderName as cc, type TranscriptParamsWebhookAuthHeaderValue as cd, type TranscriptPunctuate as ce, type TranscriptRedactPiiAudio as cf, type TranscriptRedactPiiAudioOptions as cg, TranscriptRedactPiiAudioOptionsOverrideAudioRedactionMethod as ch, type TranscriptRedactPiiAudioQuality as ci, type TranscriptRedactPiiPolicies as cj, type TranscriptRedactPiiReturnUnredacted as ck, TranscriptRemoveAudioTags as cl, type TranscriptRemoveAudioTagsProperty as cm, type TranscriptSentimentAnalysis as cn, type TranscriptSentimentAnalysisResults as co, type TranscriptSpeakerLabels as cp, type TranscriptSpeakersExpected as cq, type TranscriptSpeechModel as cr, type TranscriptSpeechModels as cs, type TranscriptSpeechThreshold as ct, type TranscriptSpeechUnderstanding as cu, type TranscriptSpeechUnderstandingRequest as cv, type TranscriptSpeechUnderstandingResponse as cw, type TranscriptSpeedBoost as cx, type TranscriptSummary as cy, type TranscriptSummaryModel as cz, type SonioxStreamingOptions as d, type ListenV1ResponseResultsChannelsItemsAlternativesItemsWordsItems as d$, type DiarizationProperties as d0, type DiarizationSpeakersProperties as d1, LanguageIdentificationMode as d2, type LanguageIdentificationProperties as d3, type LanguageIdentificationPropertiesSpeechModelMapping as d4, ProfanityFilterMode as d5, PunctuationMode as d6, type TranscriptionCustomProperties as d7, type TranscriptionLinks as d8, type TranscriptionProperties as d9, TranscriptionDiarizedSegmentType as dA, TranscriptionInclude as dB, type TranscriptionWord as dC, type VadConfig as dD, VadConfigType as dE, type ListenV1Response as dF, type SharedTopics as dG, type SharedIntents as dH, type SharedSentiments as dI, type ListProjectRequestsParams as dJ, type ListenTranscribeParams as dK, type ListenV1ResponseMetadata as dL, type ListenV1ResponseMetadataIntentsInfo as dM, type ListenV1ResponseMetadataModelInfo as dN, type ListenV1ResponseMetadataSentimentInfo as dO, type ListenV1ResponseMetadataSummaryInfo as dP, type ListenV1ResponseMetadataTopicsInfo as dQ, type ListenV1ResponseResults as dR, type ListenV1ResponseResultsChannels as dS, type ListenV1ResponseResultsChannelsItems as dT, type ListenV1ResponseResultsChannelsItemsAlternativesItems as dU, type ListenV1ResponseResultsChannelsItemsAlternativesItemsEntitiesItems as dV, type ListenV1ResponseResultsChannelsItemsAlternativesItemsParagraphs as dW, type ListenV1ResponseResultsChannelsItemsAlternativesItemsParagraphsParagraphsItems as dX, type ListenV1ResponseResultsChannelsItemsAlternativesItemsParagraphsParagraphsItemsSentencesItems as dY, type ListenV1ResponseResultsChannelsItemsAlternativesItemsSummariesItems as dZ, type ListenV1ResponseResultsChannelsItemsAlternativesItemsTopicsItems as d_, type TranscriptTextUsageTokens as da, type TranscriptionSegment as db, type RealtimeSessionCreateRequestGAModel as dc, RealtimeTranscriptionSessionCreateRequestTurnDetectionType as dd, RealtimeTranscriptionSessionCreateRequestInputAudioFormat as de, AudioResponseFormat as df, type CreateTranscription200One as dg, type CreateTranscriptionRequest as dh, type CreateTranscriptionRequestChunkingStrategy as di, type CreateTranscriptionRequestChunkingStrategyAnyOf as dj, type CreateTranscriptionRequestModel as dk, type CreateTranscriptionRequestStream as dl, CreateTranscriptionRequestTimestampGranularitiesItem as dm, type CreateTranscriptionResponseDiarizedJson as dn, CreateTranscriptionResponseDiarizedJsonTask as dp, type CreateTranscriptionResponseDiarizedJsonUsage as dq, type CreateTranscriptionResponseJson as dr, type CreateTranscriptionResponseJsonLogprobsItem as ds, type CreateTranscriptionResponseJsonUsage as dt, type CreateTranscriptionResponseVerboseJson as du, type TranscriptTextUsageDuration as dv, TranscriptTextUsageDurationType as dw, type TranscriptTextUsageTokensInputTokenDetails as dx, TranscriptTextUsageTokensType as dy, type TranscriptionDiarizedSegment as dz, StreamingSupportedEncodingEnum as e, type RecognitionAlternative as e$, type ListenV1ResponseResultsChannelsItemsSearchItems as e0, type ListenV1ResponseResultsChannelsItemsSearchItemsHitsItems as e1, type ListenV1ResponseResultsSummary as e2, type ListenV1ResponseResultsUtterances as e3, type ListenV1ResponseResultsUtterancesItems as e4, type ListenV1ResponseResultsUtterancesItemsWordsItems as e5, type SharedIntentsResults as e6, type SharedIntentsResultsIntents as e7, type SharedIntentsResultsIntentsSegmentsItems as e8, type SharedIntentsResultsIntentsSegmentsItemsIntentsItems as e9, type V1ListenPostParametersVersion as eA, V1ListenPostParametersVersion0 as eB, V1ProjectsProjectIdRequestsGetParametersDeployment as eC, V1ProjectsProjectIdRequestsGetParametersEndpoint as eD, V1ProjectsProjectIdRequestsGetParametersMethod as eE, V1ProjectsProjectIdRequestsGetParametersStatus as eF, JobType as eG, type AlignmentConfig as eH, type TranscriptionConfig as eI, type TrackingData as eJ, type OutputConfig as eK, OperatingPoint as eL, type AudioEventItem as eM, type AudioEventSummary as eN, type AudioEventSummaryItem as eO, type AutoChaptersResult as eP, type AutoChaptersResultError as eQ, AutoChaptersResultErrorType as eR, type Chapter as eS, type JobInfo as eT, type LanguageIdentificationResult as eU, type LanguageIdentificationResultAlternative as eV, LanguageIdentificationResultError as eW, type LanguageIdentificationResultItem as eX, type LanguagePackInfo as eY, LanguagePackInfoWritingDirection as eZ, type OutputConfigSrtOverrides as e_, type SharedSentimentsAverage as ea, type SharedSentimentsSegmentsItems as eb, type SharedTopicsResults as ec, type SharedTopicsResultsTopics as ed, type SharedTopicsResultsTopicsSegmentsItems as ee, type SharedTopicsResultsTopicsSegmentsItemsTopicsItems as ef, V1ListenPostParametersCallbackMethod as eg, type V1ListenPostParametersCustomIntent as eh, V1ListenPostParametersCustomIntentMode as ei, type V1ListenPostParametersCustomTopic as ej, V1ListenPostParametersCustomTopicMode as ek, type V1ListenPostParametersDetectLanguage as el, V1ListenPostParametersDiarizeModel as em, V1ListenPostParametersEncoding as en, type V1ListenPostParametersExtra as eo, type V1ListenPostParametersKeywords as ep, type V1ListenPostParametersModel as eq, V1ListenPostParametersModel0 as er, type V1ListenPostParametersRedact as es, type V1ListenPostParametersRedact1 as et, V1ListenPostParametersRedactSchemaOneOf1Items as eu, type V1ListenPostParametersReplace as ev, type V1ListenPostParametersSearch as ew, type V1ListenPostParametersSummarize as ex, V1ListenPostParametersSummarize0 as ey, type V1ListenPostParametersTag as ez, StreamingSupportedBitDepthEnum as f, type StructuredContextGeneralItem as f$, type RecognitionDisplay as f0, RecognitionDisplayDirection as f1, type RecognitionMetadata as f2, type RecognitionResult as f3, RecognitionResultAttachesTo as f4, RecognitionResultType as f5, type RetrieveTranscriptResponse as f6, type RetrieveTranscriptResponseAudioEventSummary as f7, type RetrieveTranscriptResponseAudioEventSummaryChannels as f8, type RetrieveTranscriptResponseTranslations as f9, TranscriptionConfigDiarization as fA, TranscriptionConfigMaxDelayMode as fB, type TranscriptionConfigPunctuationOverrides as fC, type TranscriptionConfigSpeakerDiarizationConfig as fD, type TranscriptionConfigTranscriptFilteringConfig as fE, type TranscriptionConfigTranscriptFilteringConfigReplacementsItem as fF, type TranslationError as fG, TranslationErrorType as fH, type TranslationSentence as fI, type WrittenFormRecognitionResult as fJ, WrittenFormRecognitionResultType as fK, type Transcription as fL, type CreateTranscriptionPayload as fM, type CreateTranscriptionPayloadAudioUrl as fN, type CreateTranscriptionPayloadClientReferenceId as fO, type CreateTranscriptionPayloadContext as fP, type CreateTranscriptionPayloadEnableLanguageIdentification as fQ, type CreateTranscriptionPayloadEnableSpeakerDiarization as fR, type CreateTranscriptionPayloadFileId as fS, type CreateTranscriptionPayloadLanguageHints as fT, type CreateTranscriptionPayloadLanguageHintsStrict as fU, type CreateTranscriptionPayloadTranslation as fV, type CreateTranscriptionPayloadWebhookAuthHeaderName as fW, type CreateTranscriptionPayloadWebhookAuthHeaderValue as fX, type CreateTranscriptionPayloadWebhookUrl as fY, type StructuredContext as fZ, type StructuredContextGeneral as f_, type SentimentAnalysisError as fa, SentimentAnalysisErrorType as fb, type SentimentAnalysisResult as fc, type SentimentAnalysisResultSentimentAnalysis as fd, type SentimentChannelSummary as fe, type SentimentSegment as ff, type SentimentSpeakerSummary as fg, type SentimentSummary as fh, type SentimentSummaryDetail as fi, type SpeakersInputItem as fj, type SpeakersResultItem as fk, type SpokenFormRecognitionResult as fl, SpokenFormRecognitionResultType as fm, type SummarizationError as fn, SummarizationErrorType as fo, type SummarizationResult as fp, type TopicDetectionError as fq, TopicDetectionErrorType as fr, type TopicDetectionResult as fs, type TopicDetectionSegment as ft, type TopicDetectionSegmentTopic as fu, type TopicDetectionSummary as fv, type TopicDetectionSummaryOverall as fw, type TrackingDataDetails as fx, type TranscriptionConfigAdditionalVocabItem as fy, type TranscriptionConfigAudioFilteringConfig as fz, StreamingSupportedSampleRateEnum as g, type SpeechToTextCharacterResponseModel as g$, type StructuredContextTerms as g0, type StructuredContextText as g1, type StructuredContextTranslationTerm as g2, type StructuredContextTranslationTerms as g3, type TranscriptionAudioDurationMs as g4, type TranscriptionAudioUrl as g5, type TranscriptionClientReferenceId as g6, type TranscriptionErrorMessage as g7, type TranscriptionErrorType as g8, type TranscriptionFileId as g9, type BodySpeechToTextV1SpeechToTextPostTemperature as gA, BodySpeechToTextV1SpeechToTextPostTimestampsGranularity as gB, type BodySpeechToTextV1SpeechToTextPostWebhookId as gC, type BodySpeechToTextV1SpeechToTextPostWebhookMetadata as gD, type BodySpeechToTextV1SpeechToTextPostWebhookMetadataAnyOf as gE, type DetectedEntity as gF, type DocxExportOptions as gG, DocxExportOptionsFormat as gH, type DocxExportOptionsMaxSegmentChars as gI, type DocxExportOptionsMaxSegmentDurationS as gJ, type DocxExportOptionsSegmentOnSilenceLongerThanS as gK, type ExportOptions as gL, type HtmlExportOptions as gM, HtmlExportOptionsFormat as gN, type HtmlExportOptionsMaxSegmentChars as gO, type HtmlExportOptionsMaxSegmentDurationS as gP, type HtmlExportOptionsSegmentOnSilenceLongerThanS as gQ, type PdfExportOptions as gR, PdfExportOptionsFormat as gS, type PdfExportOptionsMaxSegmentChars as gT, type PdfExportOptionsMaxSegmentDurationS as gU, type PdfExportOptionsSegmentOnSilenceLongerThanS as gV, type SegmentedJsonExportOptions as gW, SegmentedJsonExportOptionsFormat as gX, type SegmentedJsonExportOptionsMaxSegmentChars as gY, type SegmentedJsonExportOptionsMaxSegmentDurationS as gZ, type SegmentedJsonExportOptionsSegmentOnSilenceLongerThanS as g_, type TranscriptionLanguageHints as ga, TranscriptionStatus as gb, type TranscriptionWebhookAuthHeaderName as gc, type TranscriptionWebhookAuthHeaderValue as gd, type TranscriptionWebhookStatusCode as ge, type TranscriptionWebhookUrl as gf, type TranslationConfig as gg, type TranslationConfigLanguageA as gh, type TranslationConfigLanguageB as gi, type TranslationConfigTargetLanguage as gj, TranslationConfigType as gk, type SpeechToTextChunkResponseModel as gl, type AdditionalFormatResponseModel as gm, type AdditionalFormats as gn, type BodySpeechToTextV1SpeechToTextPost as go, type BodySpeechToTextV1SpeechToTextPostCloudStorageUrl as gp, type BodySpeechToTextV1SpeechToTextPostDiarizationThreshold as gq, type BodySpeechToTextV1SpeechToTextPostEntityDetection as gr, type BodySpeechToTextV1SpeechToTextPostEntityRedaction as gs, type BodySpeechToTextV1SpeechToTextPostFile as gt, BodySpeechToTextV1SpeechToTextPostFileFormat as gu, type BodySpeechToTextV1SpeechToTextPostLanguageCode as gv, BodySpeechToTextV1SpeechToTextPostModelId as gw, type BodySpeechToTextV1SpeechToTextPostNumSpeakers as gx, type BodySpeechToTextV1SpeechToTextPostSeed as gy, type BodySpeechToTextV1SpeechToTextPostSourceUrl as gz, StreamingSupportedModels as h, type SonioxStructuredContext as h$, type SpeechToTextCharacterResponseModelEnd as h0, type SpeechToTextCharacterResponseModelStart as h1, type SpeechToTextChunkResponseModelAdditionalFormats as h2, type SpeechToTextChunkResponseModelAdditionalFormatsAnyOfItem as h3, type SpeechToTextChunkResponseModelAudioDurationSecs as h4, type SpeechToTextChunkResponseModelChannelIndex as h5, type SpeechToTextChunkResponseModelEntities as h6, type SpeechToTextChunkResponseModelTranscriptionId as h7, type SpeechToTextWordResponseModel as h8, type SpeechToTextWordResponseModelCharacters as h9, type BatchOnlyProvider as hA, type SessionStatus as hB, type Speaker as hC, type Word as hD, type Utterance as hE, type TranscriptionStatus$1 as hF, type TranscriptMetadata as hG, type TranscriptData as hH, type ListTranscriptsResponse as hI, type ProviderRawResponseMap as hJ, type StreamEventType as hK, type SpeechEvent as hL, type TranslationEvent as hM, type SentimentEvent as hN, type EntityEvent as hO, type SummarizationEvent as hP, type ChapterizationEvent as hQ, type AudioAckEvent as hR, type LifecycleEvent as hS, type AudioChunk as hT, type RawWebSocketMessage as hU, type AssemblyAIUpdateConfiguration as hV, type OpenAIStreamingOptions as hW, type SonioxAudioFormat as hX, type SonioxOneWayTranslation as hY, type SonioxTwoWayTranslation as hZ, type SonioxTranslationConfig as h_, type SpeechToTextWordResponseModelEnd as ha, type SpeechToTextWordResponseModelSpeakerId as hb, type SpeechToTextWordResponseModelStart as hc, SpeechToTextWordResponseModelType as hd, type SrtExportOptions as he, SrtExportOptionsFormat as hf, type SrtExportOptionsMaxCharactersPerLine as hg, type SrtExportOptionsMaxSegmentChars as hh, type SrtExportOptionsMaxSegmentDurationS as hi, type SrtExportOptionsSegmentOnSilenceLongerThanS as hj, type TxtExportOptions as hk, TxtExportOptionsFormat as hl, type TxtExportOptionsMaxCharactersPerLine as hm, type TxtExportOptionsMaxSegmentChars as hn, type TxtExportOptionsMaxSegmentDurationS as ho, type TxtExportOptionsSegmentOnSilenceLongerThanS as hp, type SonioxBatchOptions as hq, type SpeechmaticsOperatingPoint as hr, type TranscriptionModel as hs, type TranscriptionLanguage as ht, type AssemblyAIExtendedData as hu, type GladiaExtendedData as hv, type DeepgramExtendedData as hw, type ElevenLabsExtendedData as hx, type ProviderExtendedDataMap as hy, type StreamingProvider as hz, type LanguageConfig as i, type SonioxContext as i0, type ElevenLabsStreamingOptions as i1, type SpeechmaticsStreamingOptions as i2, type ProviderStreamingOptions as i3, type StreamingOptionsForProvider as i4, type TranscribeStreamParams as i5, type BeginEvent as i6, type TurnEvent as i7, type TerminationEvent as i8, type ErrorEvent as i9, type StreamingEventMessage as ia, type StreamingWord as ib, type StreamingForceEndpoint as ic, type PostProcessingConfig as j, type TranscriptionMetadataDTO as k, type TranscriptionDTO as l, type TranslationDTO as m, type SummarizationDTO as n, type SentimentAnalysisDTO as o, type ChapterizationDTO as p, type PreRecordedResponse as q, type UtteranceDTO as r, TranscriptionLanguageCodeEnum as s, TranslationLanguageCodeEnum as t, type NamedEntityRecognitionResult as u, StreamingSupportedRegions as v, type AddonErrorDTO as w, type AudioToLlmDTO as x, type AudioToLlmDTOError as y, type AudioToLlmDTOResults as z };
|