voice-router-dev 0.8.5 → 0.8.7

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.
@@ -37,82 +37,75 @@ type AudioChannels = 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8;
37
37
  /**
38
38
  * Generated by orval v7.9.0 🍺
39
39
  * Do not edit manually.
40
- * Deepgram API Specification
41
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
42
-
40
+ * Deepgram API
41
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
43
42
  * OpenAPI spec version: 1.0.0
44
43
  */
45
- type ListenV1ResponseMetadataModelInfo = {
44
+ interface ListenV1ResponseMetadataModelInfo {
46
45
  [key: string]: unknown;
47
- };
46
+ }
48
47
 
49
48
  /**
50
49
  * Generated by orval v7.9.0 🍺
51
50
  * Do not edit manually.
52
- * Deepgram API Specification
53
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
54
-
51
+ * Deepgram API
52
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
55
53
  * OpenAPI spec version: 1.0.0
56
54
  */
57
- type ListenV1ResponseMetadataSummaryInfo = {
55
+ interface ListenV1ResponseMetadataSummaryInfo {
58
56
  model_uuid?: string;
59
57
  input_tokens?: number;
60
58
  output_tokens?: number;
61
- };
59
+ }
62
60
 
63
61
  /**
64
62
  * Generated by orval v7.9.0 🍺
65
63
  * Do not edit manually.
66
- * Deepgram API Specification
67
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
68
-
64
+ * Deepgram API
65
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
69
66
  * OpenAPI spec version: 1.0.0
70
67
  */
71
- type ListenV1ResponseMetadataSentimentInfo = {
68
+ interface ListenV1ResponseMetadataSentimentInfo {
72
69
  model_uuid?: string;
73
70
  input_tokens?: number;
74
71
  output_tokens?: number;
75
- };
72
+ }
76
73
 
77
74
  /**
78
75
  * Generated by orval v7.9.0 🍺
79
76
  * Do not edit manually.
80
- * Deepgram API Specification
81
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
82
-
77
+ * Deepgram API
78
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
83
79
  * OpenAPI spec version: 1.0.0
84
80
  */
85
- type ListenV1ResponseMetadataTopicsInfo = {
81
+ interface ListenV1ResponseMetadataTopicsInfo {
86
82
  model_uuid?: string;
87
83
  input_tokens?: number;
88
84
  output_tokens?: number;
89
- };
85
+ }
90
86
 
91
87
  /**
92
88
  * Generated by orval v7.9.0 🍺
93
89
  * Do not edit manually.
94
- * Deepgram API Specification
95
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
96
-
90
+ * Deepgram API
91
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
97
92
  * OpenAPI spec version: 1.0.0
98
93
  */
99
- type ListenV1ResponseMetadataIntentsInfo = {
94
+ interface ListenV1ResponseMetadataIntentsInfo {
100
95
  model_uuid?: string;
101
96
  input_tokens?: number;
102
97
  output_tokens?: number;
103
- };
98
+ }
104
99
 
105
100
  /**
106
101
  * Generated by orval v7.9.0 🍺
107
102
  * Do not edit manually.
108
- * Deepgram API Specification
109
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
110
-
103
+ * Deepgram API
104
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
111
105
  * OpenAPI spec version: 1.0.0
112
106
  */
113
107
 
114
108
  interface ListenV1ResponseMetadata {
115
- /** @deprecated */
116
109
  transaction_key?: string;
117
110
  request_id: string;
118
111
  sha256: string;
@@ -131,192 +124,179 @@ interface ListenV1ResponseMetadata {
131
124
  /**
132
125
  * Generated by orval v7.9.0 🍺
133
126
  * Do not edit manually.
134
- * Deepgram API Specification
135
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
136
-
127
+ * Deepgram API
128
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
137
129
  * OpenAPI spec version: 1.0.0
138
130
  */
139
- type ListenV1ResponseResultsChannelsItemSearchItemHitsItem = {
131
+ interface ListenV1ResponseResultsChannelsItemsSearchItemsHitsItems {
140
132
  confidence?: number;
141
133
  start?: number;
142
134
  end?: number;
143
135
  snippet?: string;
144
- };
136
+ }
145
137
 
146
138
  /**
147
139
  * Generated by orval v7.9.0 🍺
148
140
  * Do not edit manually.
149
- * Deepgram API Specification
150
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
151
-
141
+ * Deepgram API
142
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
152
143
  * OpenAPI spec version: 1.0.0
153
144
  */
154
145
 
155
- type ListenV1ResponseResultsChannelsItemSearchItem = {
146
+ interface ListenV1ResponseResultsChannelsItemsSearchItems {
156
147
  query?: string;
157
- hits?: ListenV1ResponseResultsChannelsItemSearchItemHitsItem[];
158
- };
148
+ hits?: ListenV1ResponseResultsChannelsItemsSearchItemsHitsItems[];
149
+ }
159
150
 
160
151
  /**
161
152
  * Generated by orval v7.9.0 🍺
162
153
  * Do not edit manually.
163
- * Deepgram API Specification
164
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
165
-
154
+ * Deepgram API
155
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
166
156
  * OpenAPI spec version: 1.0.0
167
157
  */
168
- type ListenV1ResponseResultsChannelsItemAlternativesItemWordsItem = {
158
+ interface ListenV1ResponseResultsChannelsItemsAlternativesItemsWordsItems {
169
159
  word?: string;
170
160
  start?: number;
171
161
  end?: number;
172
162
  confidence?: number;
173
- };
163
+ }
174
164
 
175
165
  /**
176
166
  * Generated by orval v7.9.0 🍺
177
167
  * Do not edit manually.
178
- * Deepgram API Specification
179
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
180
-
168
+ * Deepgram API
169
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
181
170
  * OpenAPI spec version: 1.0.0
182
171
  */
183
- type ListenV1ResponseResultsChannelsItemAlternativesItemParagraphsParagraphsItemSentencesItem = {
172
+ interface ListenV1ResponseResultsChannelsItemsAlternativesItemsParagraphsParagraphsItemsSentencesItems {
184
173
  text?: string;
185
174
  start?: number;
186
175
  end?: number;
187
- };
176
+ }
188
177
 
189
178
  /**
190
179
  * Generated by orval v7.9.0 🍺
191
180
  * Do not edit manually.
192
- * Deepgram API Specification
193
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
194
-
181
+ * Deepgram API
182
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
195
183
  * OpenAPI spec version: 1.0.0
196
184
  */
197
185
 
198
- type ListenV1ResponseResultsChannelsItemAlternativesItemParagraphsParagraphsItem = {
199
- sentences?: ListenV1ResponseResultsChannelsItemAlternativesItemParagraphsParagraphsItemSentencesItem[];
186
+ interface ListenV1ResponseResultsChannelsItemsAlternativesItemsParagraphsParagraphsItems {
187
+ sentences?: ListenV1ResponseResultsChannelsItemsAlternativesItemsParagraphsParagraphsItemsSentencesItems[];
200
188
  speaker?: number;
201
189
  num_words?: number;
202
190
  start?: number;
203
191
  end?: number;
204
- };
192
+ }
205
193
 
206
194
  /**
207
195
  * Generated by orval v7.9.0 🍺
208
196
  * Do not edit manually.
209
- * Deepgram API Specification
210
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
211
-
197
+ * Deepgram API
198
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
212
199
  * OpenAPI spec version: 1.0.0
213
200
  */
214
201
 
215
- type ListenV1ResponseResultsChannelsItemAlternativesItemParagraphs = {
202
+ interface ListenV1ResponseResultsChannelsItemsAlternativesItemsParagraphs {
216
203
  transcript?: string;
217
- paragraphs?: ListenV1ResponseResultsChannelsItemAlternativesItemParagraphsParagraphsItem[];
218
- };
204
+ paragraphs?: ListenV1ResponseResultsChannelsItemsAlternativesItemsParagraphsParagraphsItems[];
205
+ }
219
206
 
220
207
  /**
221
208
  * Generated by orval v7.9.0 🍺
222
209
  * Do not edit manually.
223
- * Deepgram API Specification
224
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
225
-
210
+ * Deepgram API
211
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
226
212
  * OpenAPI spec version: 1.0.0
227
213
  */
228
- type ListenV1ResponseResultsChannelsItemAlternativesItemEntitiesItem = {
214
+ interface ListenV1ResponseResultsChannelsItemsAlternativesItemsEntitiesItems {
229
215
  label?: string;
230
216
  value?: string;
231
217
  raw_value?: string;
232
218
  confidence?: number;
233
219
  start_word?: number;
234
220
  end_word?: number;
235
- };
221
+ }
236
222
 
237
223
  /**
238
224
  * Generated by orval v7.9.0 🍺
239
225
  * Do not edit manually.
240
- * Deepgram API Specification
241
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
242
-
226
+ * Deepgram API
227
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
243
228
  * OpenAPI spec version: 1.0.0
244
229
  */
245
- type ListenV1ResponseResultsChannelsItemAlternativesItemSummariesItem = {
230
+ interface ListenV1ResponseResultsChannelsItemsAlternativesItemsSummariesItems {
246
231
  summary?: string;
247
232
  start_word?: number;
248
233
  end_word?: number;
249
- };
234
+ }
250
235
 
251
236
  /**
252
237
  * Generated by orval v7.9.0 🍺
253
238
  * Do not edit manually.
254
- * Deepgram API Specification
255
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
256
-
239
+ * Deepgram API
240
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
257
241
  * OpenAPI spec version: 1.0.0
258
242
  */
259
- type ListenV1ResponseResultsChannelsItemAlternativesItemTopicsItem = {
243
+ interface ListenV1ResponseResultsChannelsItemsAlternativesItemsTopicsItems {
260
244
  text?: string;
261
245
  start_word?: number;
262
246
  end_word?: number;
263
247
  topics?: string[];
264
- };
248
+ }
265
249
 
266
250
  /**
267
251
  * Generated by orval v7.9.0 🍺
268
252
  * Do not edit manually.
269
- * Deepgram API Specification
270
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
271
-
253
+ * Deepgram API
254
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
272
255
  * OpenAPI spec version: 1.0.0
273
256
  */
274
257
 
275
- type ListenV1ResponseResultsChannelsItemAlternativesItem = {
258
+ interface ListenV1ResponseResultsChannelsItemsAlternativesItems {
276
259
  transcript?: string;
277
260
  confidence?: number;
278
- words?: ListenV1ResponseResultsChannelsItemAlternativesItemWordsItem[];
279
- paragraphs?: ListenV1ResponseResultsChannelsItemAlternativesItemParagraphs;
280
- entities?: ListenV1ResponseResultsChannelsItemAlternativesItemEntitiesItem[];
281
- summaries?: ListenV1ResponseResultsChannelsItemAlternativesItemSummariesItem[];
282
- topics?: ListenV1ResponseResultsChannelsItemAlternativesItemTopicsItem[];
283
- };
261
+ words?: ListenV1ResponseResultsChannelsItemsAlternativesItemsWordsItems[];
262
+ paragraphs?: ListenV1ResponseResultsChannelsItemsAlternativesItemsParagraphs;
263
+ entities?: ListenV1ResponseResultsChannelsItemsAlternativesItemsEntitiesItems[];
264
+ summaries?: ListenV1ResponseResultsChannelsItemsAlternativesItemsSummariesItems[];
265
+ topics?: ListenV1ResponseResultsChannelsItemsAlternativesItemsTopicsItems[];
266
+ }
284
267
 
285
268
  /**
286
269
  * Generated by orval v7.9.0 🍺
287
270
  * Do not edit manually.
288
- * Deepgram API Specification
289
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
290
-
271
+ * Deepgram API
272
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
291
273
  * OpenAPI spec version: 1.0.0
292
274
  */
293
275
 
294
- type ListenV1ResponseResultsChannelsItem = {
295
- search?: ListenV1ResponseResultsChannelsItemSearchItem[];
296
- alternatives?: ListenV1ResponseResultsChannelsItemAlternativesItem[];
276
+ interface ListenV1ResponseResultsChannelsItems {
277
+ search?: ListenV1ResponseResultsChannelsItemsSearchItems[];
278
+ alternatives?: ListenV1ResponseResultsChannelsItemsAlternativesItems[];
297
279
  detected_language?: string;
298
- };
280
+ }
299
281
 
300
282
  /**
301
283
  * Generated by orval v7.9.0 🍺
302
284
  * Do not edit manually.
303
- * Deepgram API Specification
304
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
305
-
285
+ * Deepgram API
286
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
306
287
  * OpenAPI spec version: 1.0.0
307
288
  */
308
289
 
309
- type ListenV1ResponseResultsChannels = ListenV1ResponseResultsChannelsItem[];
290
+ type ListenV1ResponseResultsChannels = ListenV1ResponseResultsChannelsItems[];
310
291
 
311
292
  /**
312
293
  * Generated by orval v7.9.0 🍺
313
294
  * Do not edit manually.
314
- * Deepgram API Specification
315
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
316
-
295
+ * Deepgram API
296
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
317
297
  * OpenAPI spec version: 1.0.0
318
298
  */
319
- type ListenV1ResponseResultsUtterancesItemWordsItem = {
299
+ interface ListenV1ResponseResultsUtterancesItemsWordsItems {
320
300
  word?: string;
321
301
  start?: number;
322
302
  end?: number;
@@ -324,45 +304,42 @@ type ListenV1ResponseResultsUtterancesItemWordsItem = {
324
304
  speaker?: number;
325
305
  speaker_confidence?: number;
326
306
  punctuated_word?: string;
327
- };
307
+ }
328
308
 
329
309
  /**
330
310
  * Generated by orval v7.9.0 🍺
331
311
  * Do not edit manually.
332
- * Deepgram API Specification
333
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
334
-
312
+ * Deepgram API
313
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
335
314
  * OpenAPI spec version: 1.0.0
336
315
  */
337
316
 
338
- type ListenV1ResponseResultsUtterancesItem = {
317
+ interface ListenV1ResponseResultsUtterancesItems {
339
318
  start?: number;
340
319
  end?: number;
341
320
  confidence?: number;
342
321
  channel?: number;
343
322
  transcript?: string;
344
- words?: ListenV1ResponseResultsUtterancesItemWordsItem[];
323
+ words?: ListenV1ResponseResultsUtterancesItemsWordsItems[];
345
324
  speaker?: number;
346
325
  id?: string;
347
- };
326
+ }
348
327
 
349
328
  /**
350
329
  * Generated by orval v7.9.0 🍺
351
330
  * Do not edit manually.
352
- * Deepgram API Specification
353
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
354
-
331
+ * Deepgram API
332
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
355
333
  * OpenAPI spec version: 1.0.0
356
334
  */
357
335
 
358
- type ListenV1ResponseResultsUtterances = ListenV1ResponseResultsUtterancesItem[];
336
+ type ListenV1ResponseResultsUtterances = ListenV1ResponseResultsUtterancesItems[];
359
337
 
360
338
  /**
361
339
  * Generated by orval v7.9.0 🍺
362
340
  * Do not edit manually.
363
- * Deepgram API Specification
364
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
365
-
341
+ * Deepgram API
342
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
366
343
  * OpenAPI spec version: 1.0.0
367
344
  */
368
345
  interface ListenV1ResponseResultsSummary {
@@ -373,64 +350,59 @@ interface ListenV1ResponseResultsSummary {
373
350
  /**
374
351
  * Generated by orval v7.9.0 🍺
375
352
  * Do not edit manually.
376
- * Deepgram API Specification
377
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
378
-
353
+ * Deepgram API
354
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
379
355
  * OpenAPI spec version: 1.0.0
380
356
  */
381
- type SharedTopicsResultsTopicsSegmentsItemTopicsItem = {
357
+ interface SharedTopicsResultsTopicsSegmentsItemsTopicsItems {
382
358
  topic?: string;
383
359
  confidence_score?: number;
384
- };
360
+ }
385
361
 
386
362
  /**
387
363
  * Generated by orval v7.9.0 🍺
388
364
  * Do not edit manually.
389
- * Deepgram API Specification
390
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
391
-
365
+ * Deepgram API
366
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
392
367
  * OpenAPI spec version: 1.0.0
393
368
  */
394
369
 
395
- type SharedTopicsResultsTopicsSegmentsItem = {
370
+ interface SharedTopicsResultsTopicsSegmentsItems {
396
371
  text?: string;
397
372
  start_word?: number;
398
373
  end_word?: number;
399
- topics?: SharedTopicsResultsTopicsSegmentsItemTopicsItem[];
400
- };
374
+ topics?: SharedTopicsResultsTopicsSegmentsItemsTopicsItems[];
375
+ }
401
376
 
402
377
  /**
403
378
  * Generated by orval v7.9.0 🍺
404
379
  * Do not edit manually.
405
- * Deepgram API Specification
406
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
407
-
380
+ * Deepgram API
381
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
408
382
  * OpenAPI spec version: 1.0.0
409
383
  */
410
384
 
411
- type SharedTopicsResultsTopics = {
412
- segments?: SharedTopicsResultsTopicsSegmentsItem[];
413
- };
385
+ interface SharedTopicsResultsTopics {
386
+ segments?: SharedTopicsResultsTopicsSegmentsItems[];
387
+ }
414
388
 
415
389
  /**
416
390
  * Generated by orval v7.9.0 🍺
417
391
  * Do not edit manually.
418
- * Deepgram API Specification
419
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
420
-
392
+ * Deepgram API
393
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
421
394
  * OpenAPI spec version: 1.0.0
422
395
  */
423
396
 
424
- type SharedTopicsResults = {
397
+ interface SharedTopicsResults {
425
398
  topics?: SharedTopicsResultsTopics;
426
- };
399
+ }
427
400
 
428
401
  /**
429
402
  * Generated by orval v7.9.0 🍺
430
403
  * Do not edit manually.
431
- * Deepgram API Specification
432
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
433
-
404
+ * Deepgram API
405
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
434
406
  * OpenAPI spec version: 1.0.0
435
407
  */
436
408
 
@@ -444,64 +416,59 @@ interface SharedTopics {
444
416
  /**
445
417
  * Generated by orval v7.9.0 🍺
446
418
  * Do not edit manually.
447
- * Deepgram API Specification
448
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
449
-
419
+ * Deepgram API
420
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
450
421
  * OpenAPI spec version: 1.0.0
451
422
  */
452
- type SharedIntentsResultsIntentsSegmentsItemIntentsItem = {
423
+ interface SharedIntentsResultsIntentsSegmentsItemsIntentsItems {
453
424
  intent?: string;
454
425
  confidence_score?: number;
455
- };
426
+ }
456
427
 
457
428
  /**
458
429
  * Generated by orval v7.9.0 🍺
459
430
  * Do not edit manually.
460
- * Deepgram API Specification
461
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
462
-
431
+ * Deepgram API
432
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
463
433
  * OpenAPI spec version: 1.0.0
464
434
  */
465
435
 
466
- type SharedIntentsResultsIntentsSegmentsItem = {
436
+ interface SharedIntentsResultsIntentsSegmentsItems {
467
437
  text?: string;
468
438
  start_word?: number;
469
439
  end_word?: number;
470
- intents?: SharedIntentsResultsIntentsSegmentsItemIntentsItem[];
471
- };
440
+ intents?: SharedIntentsResultsIntentsSegmentsItemsIntentsItems[];
441
+ }
472
442
 
473
443
  /**
474
444
  * Generated by orval v7.9.0 🍺
475
445
  * Do not edit manually.
476
- * Deepgram API Specification
477
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
478
-
446
+ * Deepgram API
447
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
479
448
  * OpenAPI spec version: 1.0.0
480
449
  */
481
450
 
482
- type SharedIntentsResultsIntents = {
483
- segments?: SharedIntentsResultsIntentsSegmentsItem[];
484
- };
451
+ interface SharedIntentsResultsIntents {
452
+ segments?: SharedIntentsResultsIntentsSegmentsItems[];
453
+ }
485
454
 
486
455
  /**
487
456
  * Generated by orval v7.9.0 🍺
488
457
  * Do not edit manually.
489
- * Deepgram API Specification
490
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
491
-
458
+ * Deepgram API
459
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
492
460
  * OpenAPI spec version: 1.0.0
493
461
  */
494
462
 
495
- type SharedIntentsResults = {
463
+ interface SharedIntentsResults {
496
464
  intents?: SharedIntentsResultsIntents;
497
- };
465
+ }
498
466
 
499
467
  /**
500
468
  * Generated by orval v7.9.0 🍺
501
469
  * Do not edit manually.
502
- * Deepgram API Specification
503
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
504
-
470
+ * Deepgram API
471
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
505
472
  * OpenAPI spec version: 1.0.0
506
473
  */
507
474
 
@@ -515,38 +482,35 @@ interface SharedIntents {
515
482
  /**
516
483
  * Generated by orval v7.9.0 🍺
517
484
  * Do not edit manually.
518
- * Deepgram API Specification
519
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
520
-
485
+ * Deepgram API
486
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
521
487
  * OpenAPI spec version: 1.0.0
522
488
  */
523
- type SharedSentimentsSegmentsItem = {
489
+ interface SharedSentimentsSegmentsItems {
524
490
  text?: string;
525
491
  start_word?: number;
526
492
  end_word?: number;
527
493
  sentiment?: string;
528
494
  sentiment_score?: number;
529
- };
495
+ }
530
496
 
531
497
  /**
532
498
  * Generated by orval v7.9.0 🍺
533
499
  * Do not edit manually.
534
- * Deepgram API Specification
535
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
536
-
500
+ * Deepgram API
501
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
537
502
  * OpenAPI spec version: 1.0.0
538
503
  */
539
- type SharedSentimentsAverage = {
504
+ interface SharedSentimentsAverage {
540
505
  sentiment?: string;
541
506
  sentiment_score?: number;
542
- };
507
+ }
543
508
 
544
509
  /**
545
510
  * Generated by orval v7.9.0 🍺
546
511
  * Do not edit manually.
547
- * Deepgram API Specification
548
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
549
-
512
+ * Deepgram API
513
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
550
514
  * OpenAPI spec version: 1.0.0
551
515
  */
552
516
 
@@ -554,16 +518,15 @@ type SharedSentimentsAverage = {
554
518
  * Output whenever `sentiment=true` is used
555
519
  */
556
520
  interface SharedSentiments {
557
- segments?: SharedSentimentsSegmentsItem[];
521
+ segments?: SharedSentimentsSegmentsItems[];
558
522
  average?: SharedSentimentsAverage;
559
523
  }
560
524
 
561
525
  /**
562
526
  * Generated by orval v7.9.0 🍺
563
527
  * Do not edit manually.
564
- * Deepgram API Specification
565
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
566
-
528
+ * Deepgram API
529
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
567
530
  * OpenAPI spec version: 1.0.0
568
531
  */
569
532
 
@@ -579,9 +542,8 @@ interface ListenV1ResponseResults {
579
542
  /**
580
543
  * Generated by orval v7.9.0 🍺
581
544
  * Do not edit manually.
582
- * Deepgram API Specification
583
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
584
-
545
+ * Deepgram API
546
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
585
547
  * OpenAPI spec version: 1.0.0
586
548
  */
587
549
 
@@ -853,18 +815,6 @@ interface CustomVocabularyConfigDTO {
853
815
  default_intensity?: number;
854
816
  }
855
817
 
856
- /**
857
- * Generated by orval v7.9.0 🍺
858
- * Do not edit manually.
859
- * Gladia Control API
860
- * OpenAPI spec version: 1.0
861
- */
862
-
863
- interface CodeSwitchingConfigDTO {
864
- /** Specify the languages you want to use when detecting multiple languages */
865
- languages?: TranscriptionLanguageCodeEnum[];
866
- }
867
-
868
818
  /**
869
819
  * Generated by orval v7.9.0 🍺
870
820
  * Do not edit manually.
@@ -959,7 +909,7 @@ interface SubtitlesConfigDTO {
959
909
  * @maximum 5
960
910
  */
961
911
  maximum_rows_per_caption?: number;
962
- /** Style of the subtitles. Compliance mode refers to : https://loc.gov/preservation/digital/formats//fdd/fdd000569.shtml#:~:text=SRT%20files%20are%20basic%20text,alongside%2C%20example%3A%20%22MyVideo123 */
912
+ /** Style of the subtitles. Compliance mode refers to : https://loc.gov/preservation/digital/formats//fdd/fdd000569.shtml#:~:text=SRT%20files%20are%20basic%20text,alongside%2C%20example%3A%20%22MyVideo123 */
963
913
  style?: SubtitlesStyleEnum;
964
914
  }
965
915
 
@@ -1201,12 +1151,14 @@ interface CustomSpellingConfigDTO {
1201
1151
  * Gladia Control API
1202
1152
  * OpenAPI spec version: 1.0
1203
1153
  */
1204
- interface StructuredDataExtractionConfigDTO {
1154
+ interface AudioToLlmListConfigDTO {
1205
1155
  /**
1206
- * The list of classes to extract from the audio transcription
1156
+ * The list of prompts applied on the audio transcription
1207
1157
  * @minItems 1
1208
1158
  */
1209
- classes: unknown[][];
1159
+ prompts: unknown[][];
1160
+ /** The model to use for the prompt execution. You can find the list of supported models [here](https://openrouter.ai/models). */
1161
+ model?: string;
1210
1162
  }
1211
1163
 
1212
1164
  /**
@@ -1215,12 +1167,122 @@ interface StructuredDataExtractionConfigDTO {
1215
1167
  * Gladia Control API
1216
1168
  * OpenAPI spec version: 1.0
1217
1169
  */
1218
- interface AudioToLlmListConfigDTO {
1219
- /**
1220
- * The list of prompts applied on the audio transcription
1221
- * @minItems 1
1222
- */
1223
- prompts: unknown[][];
1170
+ /**
1171
+ * The entity types to redact
1172
+ */
1173
+ type PiiRedactionEntityTypeEnum = (typeof PiiRedactionEntityTypeEnum)[keyof typeof PiiRedactionEntityTypeEnum];
1174
+ declare const PiiRedactionEntityTypeEnum: {
1175
+ readonly APPI: "APPI";
1176
+ readonly APPI_SENSITIVE: "APPI_SENSITIVE";
1177
+ readonly CCI: "CCI";
1178
+ readonly CORE_ENTITIES: "CORE_ENTITIES";
1179
+ readonly CPRA: "CPRA";
1180
+ readonly GDPR: "GDPR";
1181
+ readonly GDPR_SENSITIVE: "GDPR_SENSITIVE";
1182
+ readonly HEALTH_INFORMATION: "HEALTH_INFORMATION";
1183
+ readonly HIPAA_SAFE_HARBOR: "HIPAA_SAFE_HARBOR";
1184
+ readonly LIDI: "LIDI";
1185
+ readonly NUMERICAL_EXCL_PCI: "NUMERICAL_EXCL_PCI";
1186
+ readonly PCI: "PCI";
1187
+ readonly QUEBEC_PRIVACY_ACT: "QUEBEC_PRIVACY_ACT";
1188
+ readonly ACCOUNT_NUMBER: "ACCOUNT_NUMBER";
1189
+ readonly AGE: "AGE";
1190
+ readonly DATE: "DATE";
1191
+ readonly DATE_INTERVAL: "DATE_INTERVAL";
1192
+ readonly DOB: "DOB";
1193
+ readonly DRIVER_LICENSE: "DRIVER_LICENSE";
1194
+ readonly DURATION: "DURATION";
1195
+ readonly EMAIL_ADDRESS: "EMAIL_ADDRESS";
1196
+ readonly EVENT: "EVENT";
1197
+ readonly FILENAME: "FILENAME";
1198
+ readonly GENDER: "GENDER";
1199
+ readonly HEALTHCARE_NUMBER: "HEALTHCARE_NUMBER";
1200
+ readonly IP_ADDRESS: "IP_ADDRESS";
1201
+ readonly LANGUAGE: "LANGUAGE";
1202
+ readonly LOCATION: "LOCATION";
1203
+ readonly LOCATION_ADDRESS: "LOCATION_ADDRESS";
1204
+ readonly LOCATION_ADDRESS_STREET: "LOCATION_ADDRESS_STREET";
1205
+ readonly LOCATION_CITY: "LOCATION_CITY";
1206
+ readonly LOCATION_COORDINATE: "LOCATION_COORDINATE";
1207
+ readonly LOCATION_COUNTRY: "LOCATION_COUNTRY";
1208
+ readonly LOCATION_STATE: "LOCATION_STATE";
1209
+ readonly LOCATION_ZIP: "LOCATION_ZIP";
1210
+ readonly MARITAL_STATUS: "MARITAL_STATUS";
1211
+ readonly MONEY: "MONEY";
1212
+ readonly NAME: "NAME";
1213
+ readonly NAME_FAMILY: "NAME_FAMILY";
1214
+ readonly NAME_GIVEN: "NAME_GIVEN";
1215
+ readonly NAME_MEDICAL_PROFESSIONAL: "NAME_MEDICAL_PROFESSIONAL";
1216
+ readonly NUMERICAL_PII: "NUMERICAL_PII";
1217
+ readonly OCCUPATION: "OCCUPATION";
1218
+ readonly ORGANIZATION: "ORGANIZATION";
1219
+ readonly ORGANIZATION_MEDICAL_FACILITY: "ORGANIZATION_MEDICAL_FACILITY";
1220
+ readonly ORIGIN: "ORIGIN";
1221
+ readonly PASSPORT_NUMBER: "PASSPORT_NUMBER";
1222
+ readonly PASSWORD: "PASSWORD";
1223
+ readonly PHONE_NUMBER: "PHONE_NUMBER";
1224
+ readonly PHYSICAL_ATTRIBUTE: "PHYSICAL_ATTRIBUTE";
1225
+ readonly POLITICAL_AFFILIATION: "POLITICAL_AFFILIATION";
1226
+ readonly RELIGION: "RELIGION";
1227
+ readonly SEXUALITY: "SEXUALITY";
1228
+ readonly SSN: "SSN";
1229
+ readonly TIME: "TIME";
1230
+ readonly URL: "URL";
1231
+ readonly USERNAME: "USERNAME";
1232
+ readonly VEHICLE_ID: "VEHICLE_ID";
1233
+ readonly ZODIAC_SIGN: "ZODIAC_SIGN";
1234
+ readonly BLOOD_TYPE: "BLOOD_TYPE";
1235
+ readonly CONDITION: "CONDITION";
1236
+ readonly DOSE: "DOSE";
1237
+ readonly DRUG: "DRUG";
1238
+ readonly INJURY: "INJURY";
1239
+ readonly MEDICAL_PROCESS: "MEDICAL_PROCESS";
1240
+ readonly STATISTICS: "STATISTICS";
1241
+ readonly BANK_ACCOUNT: "BANK_ACCOUNT";
1242
+ readonly CREDIT_CARD: "CREDIT_CARD";
1243
+ readonly CREDIT_CARD_EXPIRATION: "CREDIT_CARD_EXPIRATION";
1244
+ readonly CVV: "CVV";
1245
+ readonly ROUTING_NUMBER: "ROUTING_NUMBER";
1246
+ readonly CORPORATE_ACTION: "CORPORATE_ACTION";
1247
+ readonly DAY: "DAY";
1248
+ readonly EFFECT: "EFFECT";
1249
+ readonly FINANCIAL_METRIC: "FINANCIAL_METRIC";
1250
+ readonly MEDICAL_CODE: "MEDICAL_CODE";
1251
+ readonly MONTH: "MONTH";
1252
+ readonly ORGANIZATION_ID: "ORGANIZATION_ID";
1253
+ readonly PRODUCT: "PRODUCT";
1254
+ readonly PROJECT: "PROJECT";
1255
+ readonly TREND: "TREND";
1256
+ readonly YEAR: "YEAR";
1257
+ };
1258
+
1259
+ /**
1260
+ * Generated by orval v7.9.0 🍺
1261
+ * Do not edit manually.
1262
+ * Gladia Control API
1263
+ * OpenAPI spec version: 1.0
1264
+ */
1265
+ /**
1266
+ * The type of processed text to return (marker or mask)
1267
+ */
1268
+ type PiiRedactionConfigDTOProcessedTextType = (typeof PiiRedactionConfigDTOProcessedTextType)[keyof typeof PiiRedactionConfigDTOProcessedTextType];
1269
+ declare const PiiRedactionConfigDTOProcessedTextType: {
1270
+ readonly MARKER: "MARKER";
1271
+ readonly MASK: "MASK";
1272
+ };
1273
+
1274
+ /**
1275
+ * Generated by orval v7.9.0 🍺
1276
+ * Do not edit manually.
1277
+ * Gladia Control API
1278
+ * OpenAPI spec version: 1.0
1279
+ */
1280
+
1281
+ interface PiiRedactionConfigDTO {
1282
+ /** The entity types to redact */
1283
+ entity_types?: PiiRedactionEntityTypeEnum;
1284
+ /** The type of processed text to return (marker or mask) */
1285
+ processed_text_type?: PiiRedactionConfigDTOProcessedTextType;
1224
1286
  }
1225
1287
 
1226
1288
  /**
@@ -1245,35 +1307,10 @@ interface LanguageConfig {
1245
1307
  */
1246
1308
 
1247
1309
  interface PreRecordedRequestParamsResponse {
1248
- /**
1249
- * **[Deprecated]** Context to feed the transcription model with for possible better accuracy
1250
- * @deprecated
1251
- */
1252
- context_prompt?: string;
1253
1310
  /** **[Beta]** Can be either boolean to enable custom_vocabulary for this audio or an array with specific vocabulary list to feed the transcription model with */
1254
1311
  custom_vocabulary?: boolean;
1255
1312
  /** **[Beta]** Custom vocabulary configuration, if `custom_vocabulary` is enabled */
1256
1313
  custom_vocabulary_config?: CustomVocabularyConfigDTO;
1257
- /**
1258
- * **[Deprecated]** Use `language_config` instead. Detect the language from the given audio
1259
- * @deprecated
1260
- */
1261
- detect_language?: boolean;
1262
- /**
1263
- * **[Deprecated]** Use `language_config` instead.Detect multiple languages in the given audio
1264
- * @deprecated
1265
- */
1266
- enable_code_switching?: boolean;
1267
- /**
1268
- * **[Deprecated]** Use `language_config` instead. Specify the configuration for code switching
1269
- * @deprecated
1270
- */
1271
- code_switching_config?: CodeSwitchingConfigDTO;
1272
- /**
1273
- * **[Deprecated]** Use `language_config` instead. Set the spoken language for the given audio (ISO 639 standard)
1274
- * @deprecated
1275
- */
1276
- language?: TranscriptionLanguageCodeEnum;
1277
1314
  /**
1278
1315
  * **[Deprecated]** Use `callback`/`callback_config` instead. Callback URL we will do a `POST` request to with the result of the transcription
1279
1316
  * @deprecated
@@ -1299,32 +1336,24 @@ interface PreRecordedRequestParamsResponse {
1299
1336
  summarization?: boolean;
1300
1337
  /** **[Beta]** Summarization configuration, if `summarization` is enabled */
1301
1338
  summarization_config?: SummarizationConfigDTO;
1302
- /** **[Alpha]** Enable moderation for this audio */
1303
- moderation?: boolean;
1304
1339
  /** **[Alpha]** Enable named entity recognition for this audio */
1305
1340
  named_entity_recognition?: boolean;
1306
- /** **[Alpha]** Enable chapterization for this audio */
1307
- chapterization?: boolean;
1308
- /** **[Alpha]** Enable names consistency for this audio */
1309
- name_consistency?: boolean;
1310
1341
  /** **[Alpha]** Enable custom spelling for this audio */
1311
1342
  custom_spelling?: boolean;
1312
1343
  /** **[Alpha]** Custom spelling configuration, if `custom_spelling` is enabled */
1313
1344
  custom_spelling_config?: CustomSpellingConfigDTO;
1314
- /** **[Alpha]** Enable structured data extraction for this audio */
1315
- structured_data_extraction?: boolean;
1316
- /** **[Alpha]** Structured data extraction configuration, if `structured_data_extraction` is enabled */
1317
- structured_data_extraction_config?: StructuredDataExtractionConfigDTO;
1318
1345
  /** Enable sentiment analysis for this audio */
1319
1346
  sentiment_analysis?: boolean;
1320
1347
  /** **[Alpha]** Enable audio to llm processing for this audio */
1321
1348
  audio_to_llm?: boolean;
1322
1349
  /** **[Alpha]** Audio to llm configuration, if `audio_to_llm` is enabled */
1323
1350
  audio_to_llm_config?: AudioToLlmListConfigDTO;
1351
+ /** Enable PII redaction for this audio */
1352
+ pii_redaction?: boolean;
1353
+ /** PII redaction configuration, if `pii_redaction` is enabled */
1354
+ pii_redaction_config?: PiiRedactionConfigDTO;
1324
1355
  /** Enable sentences for this audio */
1325
1356
  sentences?: boolean;
1326
- /** **[Alpha]** Allows to change the output display_mode for this audio. The output will be reordered, creating new utterances when speakers overlapped */
1327
- display_mode?: boolean;
1328
1357
  /** **[Alpha]** Use enhanced punctuation for this audio */
1329
1358
  punctuation_enhanced?: boolean;
1330
1359
  /** Specify the language configuration */
@@ -1671,6 +1700,19 @@ interface ModerationDTO {
1671
1700
  */
1672
1701
  type NamedEntityRecognitionDTOError = AddonErrorDTO | null;
1673
1702
 
1703
+ /**
1704
+ * Generated by orval v7.9.0 🍺
1705
+ * Do not edit manually.
1706
+ * Gladia Control API
1707
+ * OpenAPI spec version: 1.0
1708
+ */
1709
+ interface NamedEntityRecognitionResult {
1710
+ entity_type: string;
1711
+ text: string;
1712
+ start: number;
1713
+ end: number;
1714
+ }
1715
+
1674
1716
  /**
1675
1717
  * Generated by orval v7.9.0 🍺
1676
1718
  * Do not edit manually.
@@ -1690,8 +1732,11 @@ interface NamedEntityRecognitionDTO {
1690
1732
  * @nullable
1691
1733
  */
1692
1734
  error: NamedEntityRecognitionDTOError;
1693
- /** If `named_entity_recognition` has been enabled, the detected entities. */
1694
- entity: string;
1735
+ /**
1736
+ * If `named_entity_recognition` has been enabled, the detected entities.
1737
+ * @nullable
1738
+ */
1739
+ results: NamedEntityRecognitionResult[] | null;
1695
1740
  }
1696
1741
 
1697
1742
  /**
@@ -1726,7 +1771,7 @@ interface NamesConsistencyDTO {
1726
1771
  * @nullable
1727
1772
  */
1728
1773
  error: NamesConsistencyDTOError;
1729
- /** If `name_consistency` has been enabled, Gladia will improve the consistency of the names across the transcription */
1774
+ /** Deprecated, If `name_consistency` has been enabled, Gladia will improve the consistency of the names across the transcription */
1730
1775
  results: string;
1731
1776
  }
1732
1777
 
@@ -3993,21 +4038,6 @@ Note: This parameter is only supported for the Universal-3 Pro model.
3993
4038
  */
3994
4039
  type TranscriptRemoveAudioTagsProperty = TranscriptRemoveAudioTags | null;
3995
4040
 
3996
- /**
3997
- * Generated by orval v7.9.0 🍺
3998
- * Do not edit manually.
3999
- * AssemblyAI API
4000
- * AssemblyAI Speech-to-Text API - Batch transcription endpoints. Filtered from the official AssemblyAI docs spec.
4001
- * OpenAPI spec version: 1.0.0
4002
- */
4003
- /**
4004
- * The temperature that was used for the model's response. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for more details.
4005
-
4006
- Note: This parameter can only be used with the Universal-3 Pro model.
4007
-
4008
- */
4009
- type TranscriptTemperature = number | null;
4010
-
4011
4041
  /**
4012
4042
  * Generated by orval v7.9.0 🍺
4013
4043
  * Do not edit manually.
@@ -4415,11 +4445,6 @@ interface Transcript {
4415
4445
  Note: This parameter is only supported for the Universal-3 Pro model.
4416
4446
  */
4417
4447
  remove_audio_tags?: TranscriptRemoveAudioTagsProperty;
4418
- /** The temperature that was used for the model's response. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for more details.
4419
-
4420
- Note: This parameter can only be used with the Universal-3 Pro model.
4421
- */
4422
- temperature?: TranscriptTemperature;
4423
4448
  /** The textual transcript of your media file */
4424
4449
  text?: TranscriptText;
4425
4450
  /** True while a request is throttled and false when a request is no longer throttled */
@@ -4769,529 +4794,199 @@ declare const StreamingSupportedModels: {
4769
4794
  /**
4770
4795
  * Generated by orval v7.9.0 🍺
4771
4796
  * Do not edit manually.
4772
- * Deepgram API Specification
4773
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
4774
-
4797
+ * Deepgram API
4798
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
4775
4799
  * OpenAPI spec version: 1.0.0
4776
4800
  */
4777
- /**
4778
- * URL to which we'll make the callback request
4779
- */
4780
- type SharedCallbackParameter = string;
4801
+ type V1ListenPostParametersCallbackMethod = (typeof V1ListenPostParametersCallbackMethod)[keyof typeof V1ListenPostParametersCallbackMethod];
4802
+ declare const V1ListenPostParametersCallbackMethod: {
4803
+ readonly POST: "POST";
4804
+ readonly PUT: "PUT";
4805
+ };
4781
4806
 
4782
4807
  /**
4783
4808
  * Generated by orval v7.9.0 🍺
4784
4809
  * Do not edit manually.
4785
- * Deepgram API Specification
4786
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
4787
-
4810
+ * Deepgram API
4811
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
4788
4812
  * OpenAPI spec version: 1.0.0
4789
4813
  */
4814
+ type V1ListenPostParametersExtra = string | string[];
4815
+
4790
4816
  /**
4791
- * SharedCallbackMethodParameter type definition
4792
- */
4793
- /**
4794
- * SharedCallbackMethodParameter type definition
4795
- */
4796
- /**
4797
- * SharedCallbackMethodParameter type definition
4798
- */
4799
- /**
4800
- * SharedCallbackMethodParameter type definition
4801
- */
4802
- /**
4803
- * SharedCallbackMethodParameter type definition
4804
- */
4805
- /**
4806
- * SharedCallbackMethodParameter type definition
4807
- */
4808
- /**
4809
- * SharedCallbackMethodParameter type definition
4810
- */
4811
- /**
4812
- * SharedCallbackMethodParameter type definition
4813
- */
4814
- /**
4815
- * SharedCallbackMethodParameter type definition
4816
- */
4817
- /**
4818
- * SharedCallbackMethodParameter type definition
4817
+ * Generated by orval v7.9.0 🍺
4818
+ * Do not edit manually.
4819
+ * Deepgram API
4820
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
4821
+ * OpenAPI spec version: 1.0.0
4819
4822
  */
4823
+ type V1ListenPostParametersSummarize0 = (typeof V1ListenPostParametersSummarize0)[keyof typeof V1ListenPostParametersSummarize0];
4824
+ declare const V1ListenPostParametersSummarize0: {
4825
+ readonly v2: "v2";
4826
+ };
4827
+
4820
4828
  /**
4821
- * SharedCallbackMethodParameter type definition
4829
+ * Generated by orval v7.9.0 🍺
4830
+ * Do not edit manually.
4831
+ * Deepgram API
4832
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
4833
+ * OpenAPI spec version: 1.0.0
4822
4834
  */
4835
+
4836
+ type V1ListenPostParametersSummarize = V1ListenPostParametersSummarize0 | boolean;
4837
+
4823
4838
  /**
4824
- * SharedCallbackMethodParameter type definition
4839
+ * Generated by orval v7.9.0 🍺
4840
+ * Do not edit manually.
4841
+ * Deepgram API
4842
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
4843
+ * OpenAPI spec version: 1.0.0
4825
4844
  */
4845
+ type V1ListenPostParametersTag = string | string[];
4846
+
4826
4847
  /**
4827
- * SharedCallbackMethodParameter type definition
4848
+ * Generated by orval v7.9.0 🍺
4849
+ * Do not edit manually.
4850
+ * Deepgram API
4851
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
4852
+ * OpenAPI spec version: 1.0.0
4828
4853
  */
4854
+ type V1ListenPostParametersCustomTopic = string | string[];
4855
+
4829
4856
  /**
4830
- * SharedCallbackMethodParameter type definition
4857
+ * Generated by orval v7.9.0 🍺
4858
+ * Do not edit manually.
4859
+ * Deepgram API
4860
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
4861
+ * OpenAPI spec version: 1.0.0
4831
4862
  */
4832
- type SharedCallbackMethodParameter = typeof SharedCallbackMethodParameter[keyof typeof SharedCallbackMethodParameter];
4833
- declare const SharedCallbackMethodParameter: {
4834
- readonly POST: "POST";
4835
- readonly PUT: "PUT";
4863
+ type V1ListenPostParametersCustomTopicMode = (typeof V1ListenPostParametersCustomTopicMode)[keyof typeof V1ListenPostParametersCustomTopicMode];
4864
+ declare const V1ListenPostParametersCustomTopicMode: {
4865
+ readonly extended: "extended";
4866
+ readonly strict: "strict";
4836
4867
  };
4837
4868
 
4838
4869
  /**
4839
4870
  * Generated by orval v7.9.0 🍺
4840
4871
  * Do not edit manually.
4841
- * Deepgram API Specification
4842
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
4843
-
4872
+ * Deepgram API
4873
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
4844
4874
  * OpenAPI spec version: 1.0.0
4845
4875
  */
4846
- type SharedExtraParameter = string | string[];
4876
+ type V1ListenPostParametersCustomIntent = string | string[];
4847
4877
 
4848
4878
  /**
4849
4879
  * Generated by orval v7.9.0 🍺
4850
4880
  * Do not edit manually.
4851
- * Deepgram API Specification
4852
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
4853
-
4881
+ * Deepgram API
4882
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
4854
4883
  * OpenAPI spec version: 1.0.0
4855
4884
  */
4885
+ type V1ListenPostParametersCustomIntentMode = (typeof V1ListenPostParametersCustomIntentMode)[keyof typeof V1ListenPostParametersCustomIntentMode];
4886
+ declare const V1ListenPostParametersCustomIntentMode: {
4887
+ readonly extended: "extended";
4888
+ readonly strict: "strict";
4889
+ };
4890
+
4856
4891
  /**
4857
- * Recognizes the sentiment throughout a transcript or text
4892
+ * Generated by orval v7.9.0 🍺
4893
+ * Do not edit manually.
4894
+ * Deepgram API
4895
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
4896
+ * OpenAPI spec version: 1.0.0
4858
4897
  */
4859
- type SharedSentimentParameter = boolean;
4898
+ type V1ListenPostParametersDetectLanguage = boolean | string[];
4860
4899
 
4861
4900
  /**
4862
4901
  * Generated by orval v7.9.0 🍺
4863
4902
  * Do not edit manually.
4864
- * Deepgram API Specification
4865
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
4866
-
4903
+ * Deepgram API
4904
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
4867
4905
  * OpenAPI spec version: 1.0.0
4868
4906
  */
4869
- type SharedSummarizeParameter = "v2" | boolean;
4907
+ type V1ListenPostParametersEncoding = (typeof V1ListenPostParametersEncoding)[keyof typeof V1ListenPostParametersEncoding];
4908
+ declare const V1ListenPostParametersEncoding: {
4909
+ readonly linear16: "linear16";
4910
+ readonly flac: "flac";
4911
+ readonly mulaw: "mulaw";
4912
+ readonly "amr-nb": "amr-nb";
4913
+ readonly "amr-wb": "amr-wb";
4914
+ readonly opus: "opus";
4915
+ readonly speex: "speex";
4916
+ readonly g729: "g729";
4917
+ };
4870
4918
 
4871
4919
  /**
4872
4920
  * Generated by orval v7.9.0 🍺
4873
4921
  * Do not edit manually.
4874
- * Deepgram API Specification
4875
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
4876
-
4922
+ * Deepgram API
4923
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
4877
4924
  * OpenAPI spec version: 1.0.0
4878
4925
  */
4879
- type SharedTagParameter = string | string[];
4926
+ type V1ListenPostParametersKeywords = string | string[];
4880
4927
 
4881
4928
  /**
4882
4929
  * Generated by orval v7.9.0 🍺
4883
4930
  * Do not edit manually.
4884
- * Deepgram API Specification
4885
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
4886
-
4931
+ * Deepgram API
4932
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
4887
4933
  * OpenAPI spec version: 1.0.0
4888
4934
  */
4889
4935
  /**
4890
- * Detect topics throughout a transcript or text
4936
+ * Our public models available to all accounts
4891
4937
  */
4892
- type SharedTopicsParameter = boolean;
4938
+ type V1ListenPostParametersModel0 = (typeof V1ListenPostParametersModel0)[keyof typeof V1ListenPostParametersModel0];
4939
+ declare const V1ListenPostParametersModel0: {
4940
+ readonly "nova-3": "nova-3";
4941
+ readonly "nova-3-general": "nova-3-general";
4942
+ readonly "nova-3-medical": "nova-3-medical";
4943
+ readonly "nova-2": "nova-2";
4944
+ readonly "nova-2-general": "nova-2-general";
4945
+ readonly "nova-2-meeting": "nova-2-meeting";
4946
+ readonly "nova-2-finance": "nova-2-finance";
4947
+ readonly "nova-2-conversationalai": "nova-2-conversationalai";
4948
+ readonly "nova-2-voicemail": "nova-2-voicemail";
4949
+ readonly "nova-2-video": "nova-2-video";
4950
+ readonly "nova-2-medical": "nova-2-medical";
4951
+ readonly "nova-2-drivethru": "nova-2-drivethru";
4952
+ readonly "nova-2-automotive": "nova-2-automotive";
4953
+ readonly nova: "nova";
4954
+ readonly "nova-general": "nova-general";
4955
+ readonly "nova-phonecall": "nova-phonecall";
4956
+ readonly "nova-medical": "nova-medical";
4957
+ readonly enhanced: "enhanced";
4958
+ readonly "enhanced-general": "enhanced-general";
4959
+ readonly "enhanced-meeting": "enhanced-meeting";
4960
+ readonly "enhanced-phonecall": "enhanced-phonecall";
4961
+ readonly "enhanced-finance": "enhanced-finance";
4962
+ readonly base: "base";
4963
+ readonly meeting: "meeting";
4964
+ readonly phonecall: "phonecall";
4965
+ readonly finance: "finance";
4966
+ readonly conversationalai: "conversationalai";
4967
+ readonly voicemail: "voicemail";
4968
+ readonly video: "video";
4969
+ };
4893
4970
 
4894
4971
  /**
4895
4972
  * Generated by orval v7.9.0 🍺
4896
4973
  * Do not edit manually.
4897
- * Deepgram API Specification
4898
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
4899
-
4974
+ * Deepgram API
4975
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
4900
4976
  * OpenAPI spec version: 1.0.0
4901
4977
  */
4902
- type SharedCustomTopicParameter = string | string[];
4978
+
4979
+ type V1ListenPostParametersModel = V1ListenPostParametersModel0 | string;
4903
4980
 
4904
4981
  /**
4905
4982
  * Generated by orval v7.9.0 🍺
4906
4983
  * Do not edit manually.
4907
- * Deepgram API Specification
4908
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
4909
-
4984
+ * Deepgram API
4985
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
4910
4986
  * OpenAPI spec version: 1.0.0
4911
4987
  */
4912
- /**
4913
- * SharedCustomTopicModeParameter type definition
4914
- */
4915
- /**
4916
- * SharedCustomTopicModeParameter type definition
4917
- */
4918
- /**
4919
- * SharedCustomTopicModeParameter type definition
4920
- */
4921
- /**
4922
- * SharedCustomTopicModeParameter type definition
4923
- */
4924
- /**
4925
- * SharedCustomTopicModeParameter type definition
4926
- */
4927
- /**
4928
- * SharedCustomTopicModeParameter type definition
4929
- */
4930
- /**
4931
- * SharedCustomTopicModeParameter type definition
4932
- */
4933
- /**
4934
- * SharedCustomTopicModeParameter type definition
4935
- */
4936
- /**
4937
- * SharedCustomTopicModeParameter type definition
4938
- */
4939
- /**
4940
- * SharedCustomTopicModeParameter type definition
4941
- */
4942
- /**
4943
- * SharedCustomTopicModeParameter type definition
4944
- */
4945
- /**
4946
- * SharedCustomTopicModeParameter type definition
4947
- */
4948
- /**
4949
- * SharedCustomTopicModeParameter type definition
4950
- */
4951
- /**
4952
- * SharedCustomTopicModeParameter type definition
4953
- */
4954
- type SharedCustomTopicModeParameter = typeof SharedCustomTopicModeParameter[keyof typeof SharedCustomTopicModeParameter];
4955
- declare const SharedCustomTopicModeParameter: {
4956
- readonly extended: "extended";
4957
- readonly strict: "strict";
4958
- };
4959
-
4960
- /**
4961
- * Generated by orval v7.9.0 🍺
4962
- * Do not edit manually.
4963
- * Deepgram API Specification
4964
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
4965
-
4966
- * OpenAPI spec version: 1.0.0
4967
- */
4968
- /**
4969
- * Recognizes speaker intent throughout a transcript or text
4970
- */
4971
- type SharedIntentsParameter = boolean;
4972
-
4973
- /**
4974
- * Generated by orval v7.9.0 🍺
4975
- * Do not edit manually.
4976
- * Deepgram API Specification
4977
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
4978
-
4979
- * OpenAPI spec version: 1.0.0
4980
- */
4981
- type SharedCustomIntentParameter = string | string[];
4982
-
4983
- /**
4984
- * Generated by orval v7.9.0 🍺
4985
- * Do not edit manually.
4986
- * Deepgram API Specification
4987
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
4988
-
4989
- * OpenAPI spec version: 1.0.0
4990
- */
4991
- /**
4992
- * SharedCustomIntentModeParameter type definition
4993
- */
4994
- /**
4995
- * SharedCustomIntentModeParameter type definition
4996
- */
4997
- /**
4998
- * SharedCustomIntentModeParameter type definition
4999
- */
5000
- /**
5001
- * SharedCustomIntentModeParameter type definition
5002
- */
5003
- /**
5004
- * SharedCustomIntentModeParameter type definition
5005
- */
5006
- /**
5007
- * SharedCustomIntentModeParameter type definition
5008
- */
5009
- /**
5010
- * SharedCustomIntentModeParameter type definition
5011
- */
5012
- /**
5013
- * SharedCustomIntentModeParameter type definition
5014
- */
5015
- /**
5016
- * SharedCustomIntentModeParameter type definition
5017
- */
5018
- /**
5019
- * SharedCustomIntentModeParameter type definition
5020
- */
5021
- /**
5022
- * SharedCustomIntentModeParameter type definition
5023
- */
5024
- /**
5025
- * SharedCustomIntentModeParameter type definition
5026
- */
5027
- /**
5028
- * SharedCustomIntentModeParameter type definition
5029
- */
5030
- /**
5031
- * SharedCustomIntentModeParameter type definition
5032
- */
5033
- type SharedCustomIntentModeParameter = typeof SharedCustomIntentModeParameter[keyof typeof SharedCustomIntentModeParameter];
5034
- declare const SharedCustomIntentModeParameter: {
5035
- readonly extended: "extended";
5036
- readonly strict: "strict";
5037
- };
5038
-
5039
- /**
5040
- * Generated by orval v7.9.0 🍺
5041
- * Do not edit manually.
5042
- * Deepgram API Specification
5043
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5044
-
5045
- * OpenAPI spec version: 1.0.0
5046
- */
5047
- /**
5048
- * Identifies and extracts key entities from content in submitted audio
5049
- */
5050
- type ListenV1DetectEntitiesParameter = boolean;
5051
-
5052
- /**
5053
- * Generated by orval v7.9.0 🍺
5054
- * Do not edit manually.
5055
- * Deepgram API Specification
5056
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5057
-
5058
- * OpenAPI spec version: 1.0.0
5059
- */
5060
- type ListenV1DetectLanguageParameter = boolean | string[];
5061
-
5062
- /**
5063
- * Generated by orval v7.9.0 🍺
5064
- * Do not edit manually.
5065
- * Deepgram API Specification
5066
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5067
-
5068
- * OpenAPI spec version: 1.0.0
5069
- */
5070
- /**
5071
- * Recognize speaker changes. Each word in the transcript will be assigned a speaker number starting at 0
5072
- */
5073
- type ListenV1DiarizeParameter = boolean;
5074
-
5075
- /**
5076
- * Generated by orval v7.9.0 🍺
5077
- * Do not edit manually.
5078
- * Deepgram API Specification
5079
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5080
-
5081
- * OpenAPI spec version: 1.0.0
5082
- */
5083
- /**
5084
- * Dictation mode for controlling formatting with dictated speech
5085
- */
5086
- type ListenV1DictationParameter = boolean;
5087
-
5088
- /**
5089
- * Generated by orval v7.9.0 🍺
5090
- * Do not edit manually.
5091
- * Deepgram API Specification
5092
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5093
-
5094
- * OpenAPI spec version: 1.0.0
5095
- */
5096
- /**
5097
- * ListenV1EncodingParameter type definition
5098
- */
5099
- /**
5100
- * ListenV1EncodingParameter type definition
5101
- */
5102
- /**
5103
- * ListenV1EncodingParameter type definition
5104
- */
5105
- /**
5106
- * ListenV1EncodingParameter type definition
5107
- */
5108
- /**
5109
- * ListenV1EncodingParameter type definition
5110
- */
5111
- /**
5112
- * ListenV1EncodingParameter type definition
5113
- */
5114
- /**
5115
- * ListenV1EncodingParameter type definition
5116
- */
5117
- /**
5118
- * ListenV1EncodingParameter type definition
5119
- */
5120
- /**
5121
- * ListenV1EncodingParameter type definition
5122
- */
5123
- /**
5124
- * ListenV1EncodingParameter type definition
5125
- */
5126
- /**
5127
- * ListenV1EncodingParameter type definition
5128
- */
5129
- /**
5130
- * ListenV1EncodingParameter type definition
5131
- */
5132
- /**
5133
- * ListenV1EncodingParameter type definition
5134
- */
5135
- /**
5136
- * ListenV1EncodingParameter type definition
5137
- */
5138
- type ListenV1EncodingParameter = typeof ListenV1EncodingParameter[keyof typeof ListenV1EncodingParameter];
5139
- declare const ListenV1EncodingParameter: {
5140
- readonly linear16: "linear16";
5141
- readonly flac: "flac";
5142
- readonly mulaw: "mulaw";
5143
- readonly opus: "opus";
5144
- readonly speex: "speex";
5145
- readonly g729: "g729";
5146
- };
5147
-
5148
- /**
5149
- * Generated by orval v7.9.0 🍺
5150
- * Do not edit manually.
5151
- * Deepgram API Specification
5152
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5153
-
5154
- * OpenAPI spec version: 1.0.0
5155
- */
5156
- /**
5157
- * Filler Words can help transcribe interruptions in your audio, like "uh" and "um"
5158
- */
5159
- type ListenV1FillerWordsParameter = boolean;
5160
-
5161
- /**
5162
- * Generated by orval v7.9.0 🍺
5163
- * Do not edit manually.
5164
- * Deepgram API Specification
5165
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5166
-
5167
- * OpenAPI spec version: 1.0.0
5168
- */
5169
- /**
5170
- * Key term prompting can boost or suppress specialized terminology and brands. Only compatible with Nova-3
5171
- */
5172
- type ListenV1KeytermParameter = string[];
5173
-
5174
- /**
5175
- * Generated by orval v7.9.0 🍺
5176
- * Do not edit manually.
5177
- * Deepgram API Specification
5178
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5179
-
5180
- * OpenAPI spec version: 1.0.0
5181
- */
5182
- type ListenV1KeywordsParameter = string | string[];
5183
-
5184
- /**
5185
- * Generated by orval v7.9.0 🍺
5186
- * Do not edit manually.
5187
- * Deepgram API Specification
5188
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5189
-
5190
- * OpenAPI spec version: 1.0.0
5191
- */
5192
- /**
5193
- * The [BCP-47 language tag](https://tools.ietf.org/html/bcp47) that hints at the primary spoken language. Depending on the Model and API endpoint you choose only certain languages are available
5194
- */
5195
- type ListenV1LanguageParameter = string;
5196
-
5197
- /**
5198
- * Generated by orval v7.9.0 🍺
5199
- * Do not edit manually.
5200
- * Deepgram API Specification
5201
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5202
-
5203
- * OpenAPI spec version: 1.0.0
5204
- */
5205
- /**
5206
- * Spoken measurements will be converted to their corresponding abbreviations
5207
- */
5208
- type ListenV1MeasurementsParameter = boolean;
5209
-
5210
- /**
5211
- * Generated by orval v7.9.0 🍺
5212
- * Do not edit manually.
5213
- * Deepgram API Specification
5214
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5215
-
5216
- * OpenAPI spec version: 1.0.0
5217
- */
5218
- type ListenV1ModelParameter = "nova-3" | "nova-3-general" | "nova-3-medical" | "nova-2" | "nova-2-general" | "nova-2-meeting" | "nova-2-finance" | "nova-2-conversationalai" | "nova-2-voicemail" | "nova-2-video" | "nova-2-medical" | "nova-2-drivethru" | "nova-2-automotive" | "nova" | "nova-general" | "nova-phonecall" | "nova-medical" | "enhanced" | "enhanced-general" | "enhanced-meeting" | "enhanced-phonecall" | "enhanced-finance" | "base" | "meeting" | "phonecall" | "finance" | "conversationalai" | "voicemail" | "video" | string;
5219
-
5220
- /**
5221
- * Generated by orval v7.9.0 🍺
5222
- * Do not edit manually.
5223
- * Deepgram API Specification
5224
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5225
-
5226
- * OpenAPI spec version: 1.0.0
5227
- */
5228
- /**
5229
- * Transcribe each audio channel independently
5230
- */
5231
- type ListenV1MultichannelParameter = boolean;
5232
-
5233
- /**
5234
- * Generated by orval v7.9.0 🍺
5235
- * Do not edit manually.
5236
- * Deepgram API Specification
5237
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5238
-
5239
- * OpenAPI spec version: 1.0.0
5240
- */
5241
- /**
5242
- * Numerals converts numbers from written format to numerical format
5243
- */
5244
- type ListenV1NumeralsParameter = boolean;
5245
-
5246
- /**
5247
- * Generated by orval v7.9.0 🍺
5248
- * Do not edit manually.
5249
- * Deepgram API Specification
5250
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5251
-
5252
- * OpenAPI spec version: 1.0.0
5253
- */
5254
- /**
5255
- * Splits audio into paragraphs to improve transcript readability
5256
- */
5257
- type ListenV1ParagraphsParameter = boolean;
5258
-
5259
- /**
5260
- * Generated by orval v7.9.0 🍺
5261
- * Do not edit manually.
5262
- * Deepgram API Specification
5263
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5264
-
5265
- * OpenAPI spec version: 1.0.0
5266
- */
5267
- /**
5268
- * Profanity Filter looks for recognized profanity and converts it to the nearest recognized non-profane word or removes it from the transcript completely
5269
- */
5270
- type ListenV1ProfanityFilterParameter = boolean;
5271
-
5272
- /**
5273
- * Generated by orval v7.9.0 🍺
5274
- * Do not edit manually.
5275
- * Deepgram API Specification
5276
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5277
-
5278
- * OpenAPI spec version: 1.0.0
5279
- */
5280
- /**
5281
- * Add punctuation and capitalization to the transcript
5282
- */
5283
- type ListenV1PunctuateParameter = boolean;
5284
-
5285
- /**
5286
- * Generated by orval v7.9.0 🍺
5287
- * Do not edit manually.
5288
- * Deepgram API Specification
5289
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5290
-
5291
- * OpenAPI spec version: 1.0.0
5292
- */
5293
- type ListenV1RedactParameterOneOfItem = (typeof ListenV1RedactParameterOneOfItem)[keyof typeof ListenV1RedactParameterOneOfItem];
5294
- declare const ListenV1RedactParameterOneOfItem: {
4988
+ type V1ListenPostParametersRedactSchemaOneOf1Items = (typeof V1ListenPostParametersRedactSchemaOneOf1Items)[keyof typeof V1ListenPostParametersRedactSchemaOneOf1Items];
4989
+ declare const V1ListenPostParametersRedactSchemaOneOf1Items: {
5295
4990
  readonly pci: "pci";
5296
4991
  readonly pii: "pii";
5297
4992
  readonly numbers: "numbers";
@@ -5300,250 +4995,219 @@ declare const ListenV1RedactParameterOneOfItem: {
5300
4995
  /**
5301
4996
  * Generated by orval v7.9.0 🍺
5302
4997
  * Do not edit manually.
5303
- * Deepgram API Specification
5304
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5305
-
4998
+ * Deepgram API
4999
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
5306
5000
  * OpenAPI spec version: 1.0.0
5307
5001
  */
5308
5002
 
5309
- type ListenV1RedactParameter = string | ListenV1RedactParameterOneOfItem[];
5003
+ type V1ListenPostParametersRedact1 = V1ListenPostParametersRedactSchemaOneOf1Items[];
5310
5004
 
5311
5005
  /**
5312
5006
  * Generated by orval v7.9.0 🍺
5313
5007
  * Do not edit manually.
5314
- * Deepgram API Specification
5315
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5316
-
5008
+ * Deepgram API
5009
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
5317
5010
  * OpenAPI spec version: 1.0.0
5318
5011
  */
5319
- type ListenV1ReplaceParameter = string | string[];
5320
5012
 
5321
- /**
5322
- * Generated by orval v7.9.0 🍺
5323
- * Do not edit manually.
5324
- * Deepgram API Specification
5325
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5326
-
5327
- * OpenAPI spec version: 1.0.0
5328
- */
5329
- type ListenV1SearchParameter = string | string[];
5013
+ type V1ListenPostParametersRedact = string | V1ListenPostParametersRedact1;
5330
5014
 
5331
5015
  /**
5332
5016
  * Generated by orval v7.9.0 🍺
5333
5017
  * Do not edit manually.
5334
- * Deepgram API Specification
5335
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5336
-
5018
+ * Deepgram API
5019
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
5337
5020
  * OpenAPI spec version: 1.0.0
5338
5021
  */
5339
- /**
5340
- * Apply formatting to transcript output. When set to true, additional formatting will be applied to transcripts to improve readability
5341
- */
5342
- type ListenV1SmartFormatParameter = boolean;
5022
+ type V1ListenPostParametersReplace = string | string[];
5343
5023
 
5344
5024
  /**
5345
5025
  * Generated by orval v7.9.0 🍺
5346
5026
  * Do not edit manually.
5347
- * Deepgram API Specification
5348
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5349
-
5027
+ * Deepgram API
5028
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
5350
5029
  * OpenAPI spec version: 1.0.0
5351
5030
  */
5352
- /**
5353
- * Segments speech into meaningful semantic units
5354
- */
5355
- type ListenV1UtterancesParameter = boolean;
5031
+ type V1ListenPostParametersSearch = string | string[];
5356
5032
 
5357
5033
  /**
5358
5034
  * Generated by orval v7.9.0 🍺
5359
5035
  * Do not edit manually.
5360
- * Deepgram API Specification
5361
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5362
-
5036
+ * Deepgram API
5037
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
5363
5038
  * OpenAPI spec version: 1.0.0
5364
5039
  */
5365
5040
  /**
5366
- * Seconds to wait before detecting a pause between words in submitted audio
5041
+ * Use the latest version of a model
5367
5042
  */
5368
- type ListenV1UttSplitParameter = number;
5043
+ type V1ListenPostParametersVersion0 = (typeof V1ListenPostParametersVersion0)[keyof typeof V1ListenPostParametersVersion0];
5044
+ declare const V1ListenPostParametersVersion0: {
5045
+ readonly latest: "latest";
5046
+ };
5369
5047
 
5370
5048
  /**
5371
5049
  * Generated by orval v7.9.0 🍺
5372
5050
  * Do not edit manually.
5373
- * Deepgram API Specification
5374
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5375
-
5051
+ * Deepgram API
5052
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
5376
5053
  * OpenAPI spec version: 1.0.0
5377
5054
  */
5378
- type ListenV1VersionParameter = "latest" | string;
5379
5055
 
5380
- /**
5381
- * Generated by orval v7.9.0 🍺
5382
- * Do not edit manually.
5383
- * Deepgram API Specification
5384
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5385
-
5386
- * OpenAPI spec version: 1.0.0
5387
- */
5388
- /**
5389
- * Opts out requests from the Deepgram Model Improvement Program. Refer to our Docs for pricing impacts before setting this to true. https://dpgr.am/deepgram-mip
5390
- */
5391
- type SharedMipOptOutParameter = boolean;
5056
+ type V1ListenPostParametersVersion = V1ListenPostParametersVersion0 | string;
5392
5057
 
5393
5058
  /**
5394
5059
  * Generated by orval v7.9.0 🍺
5395
5060
  * Do not edit manually.
5396
- * Deepgram API Specification
5397
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
5398
-
5061
+ * Deepgram API
5062
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
5399
5063
  * OpenAPI spec version: 1.0.0
5400
5064
  */
5401
5065
 
5402
- type ListenV1MediaTranscribeParams = {
5066
+ type ListenTranscribeParams = {
5403
5067
  /**
5404
5068
  * URL to which we'll make the callback request
5405
5069
  */
5406
- callback?: SharedCallbackParameter;
5070
+ callback?: string;
5407
5071
  /**
5408
5072
  * HTTP method by which the callback request will be made
5409
5073
  */
5410
- callback_method?: SharedCallbackMethodParameter;
5074
+ callback_method?: V1ListenPostParametersCallbackMethod;
5411
5075
  /**
5412
5076
  * Arbitrary key-value pairs that are attached to the API response for usage in downstream processing
5413
5077
  */
5414
- extra?: SharedExtraParameter;
5078
+ extra?: V1ListenPostParametersExtra;
5415
5079
  /**
5416
5080
  * Recognizes the sentiment throughout a transcript or text
5417
5081
  */
5418
- sentiment?: SharedSentimentParameter;
5082
+ sentiment?: boolean;
5419
5083
  /**
5420
5084
  * Summarize content. For Listen API, supports string version option. For Read API, accepts boolean only.
5421
5085
  */
5422
- summarize?: SharedSummarizeParameter;
5086
+ summarize?: V1ListenPostParametersSummarize;
5423
5087
  /**
5424
5088
  * Label your requests for the purpose of identification during usage reporting
5425
5089
  */
5426
- tag?: SharedTagParameter;
5090
+ tag?: V1ListenPostParametersTag;
5427
5091
  /**
5428
5092
  * Detect topics throughout a transcript or text
5429
5093
  */
5430
- topics?: SharedTopicsParameter;
5094
+ topics?: boolean;
5431
5095
  /**
5432
5096
  * Custom topics you want the model to detect within your input audio or text if present Submit up to `100`.
5433
5097
  */
5434
- custom_topic?: SharedCustomTopicParameter;
5098
+ custom_topic?: V1ListenPostParametersCustomTopic;
5435
5099
  /**
5436
5100
  * Sets how the model will interpret strings submitted to the `custom_topic` param. When `strict`, the model will only return topics submitted using the `custom_topic` param. When `extended`, the model will return its own detected topics in addition to those submitted using the `custom_topic` param
5437
5101
  */
5438
- custom_topic_mode?: SharedCustomTopicModeParameter;
5102
+ custom_topic_mode?: V1ListenPostParametersCustomTopicMode;
5439
5103
  /**
5440
5104
  * Recognizes speaker intent throughout a transcript or text
5441
5105
  */
5442
- intents?: SharedIntentsParameter;
5106
+ intents?: boolean;
5443
5107
  /**
5444
5108
  * Custom intents you want the model to detect within your input audio if present
5445
5109
  */
5446
- custom_intent?: SharedCustomIntentParameter;
5110
+ custom_intent?: V1ListenPostParametersCustomIntent;
5447
5111
  /**
5448
5112
  * Sets how the model will interpret intents submitted to the `custom_intent` param. When `strict`, the model will only return intents submitted using the `custom_intent` param. When `extended`, the model will return its own detected intents in the `custom_intent` param.
5449
5113
  */
5450
- custom_intent_mode?: SharedCustomIntentModeParameter;
5114
+ custom_intent_mode?: V1ListenPostParametersCustomIntentMode;
5451
5115
  /**
5452
5116
  * Identifies and extracts key entities from content in submitted audio
5453
5117
  */
5454
- detect_entities?: ListenV1DetectEntitiesParameter;
5118
+ detect_entities?: boolean;
5455
5119
  /**
5456
5120
  * Identifies the dominant language spoken in submitted audio
5457
5121
  */
5458
- detect_language?: ListenV1DetectLanguageParameter;
5122
+ detect_language?: V1ListenPostParametersDetectLanguage;
5459
5123
  /**
5460
5124
  * Recognize speaker changes. Each word in the transcript will be assigned a speaker number starting at 0
5461
5125
  */
5462
- diarize?: ListenV1DiarizeParameter;
5126
+ diarize?: boolean;
5463
5127
  /**
5464
5128
  * Dictation mode for controlling formatting with dictated speech
5465
5129
  */
5466
- dictation?: ListenV1DictationParameter;
5130
+ dictation?: boolean;
5467
5131
  /**
5468
5132
  * Specify the expected encoding of your submitted audio
5469
5133
  */
5470
- encoding?: ListenV1EncodingParameter;
5134
+ encoding?: V1ListenPostParametersEncoding;
5471
5135
  /**
5472
5136
  * Filler Words can help transcribe interruptions in your audio, like "uh" and "um"
5473
5137
  */
5474
- filler_words?: ListenV1FillerWordsParameter;
5138
+ filler_words?: boolean;
5475
5139
  /**
5476
5140
  * Key term prompting can boost or suppress specialized terminology and brands. Only compatible with Nova-3
5477
5141
  */
5478
- keyterm?: ListenV1KeytermParameter;
5142
+ keyterm?: string[];
5479
5143
  /**
5480
5144
  * Keywords can boost or suppress specialized terminology and brands
5481
5145
  */
5482
- keywords?: ListenV1KeywordsParameter;
5146
+ keywords?: V1ListenPostParametersKeywords;
5483
5147
  /**
5484
5148
  * The [BCP-47 language tag](https://tools.ietf.org/html/bcp47) that hints at the primary spoken language. Depending on the Model and API endpoint you choose only certain languages are available
5485
5149
  */
5486
- language?: ListenV1LanguageParameter;
5150
+ language?: string;
5487
5151
  /**
5488
5152
  * Spoken measurements will be converted to their corresponding abbreviations
5489
5153
  */
5490
- measurements?: ListenV1MeasurementsParameter;
5154
+ measurements?: boolean;
5491
5155
  /**
5492
5156
  * AI model used to process submitted audio
5493
5157
  */
5494
- model?: ListenV1ModelParameter;
5158
+ model?: V1ListenPostParametersModel;
5495
5159
  /**
5496
5160
  * Transcribe each audio channel independently
5497
5161
  */
5498
- multichannel?: ListenV1MultichannelParameter;
5162
+ multichannel?: boolean;
5499
5163
  /**
5500
5164
  * Numerals converts numbers from written format to numerical format
5501
5165
  */
5502
- numerals?: ListenV1NumeralsParameter;
5166
+ numerals?: boolean;
5503
5167
  /**
5504
5168
  * Splits audio into paragraphs to improve transcript readability
5505
5169
  */
5506
- paragraphs?: ListenV1ParagraphsParameter;
5170
+ paragraphs?: boolean;
5507
5171
  /**
5508
5172
  * Profanity Filter looks for recognized profanity and converts it to the nearest recognized non-profane word or removes it from the transcript completely
5509
5173
  */
5510
- profanity_filter?: ListenV1ProfanityFilterParameter;
5174
+ profanity_filter?: boolean;
5511
5175
  /**
5512
5176
  * Add punctuation and capitalization to the transcript
5513
5177
  */
5514
- punctuate?: ListenV1PunctuateParameter;
5178
+ punctuate?: boolean;
5515
5179
  /**
5516
5180
  * Redaction removes sensitive information from your transcripts
5517
5181
  */
5518
- redact?: ListenV1RedactParameter;
5182
+ redact?: V1ListenPostParametersRedact;
5519
5183
  /**
5520
5184
  * Search for terms or phrases in submitted audio and replaces them
5521
5185
  */
5522
- replace?: ListenV1ReplaceParameter;
5186
+ replace?: V1ListenPostParametersReplace;
5523
5187
  /**
5524
5188
  * Search for terms or phrases in submitted audio
5525
5189
  */
5526
- search?: ListenV1SearchParameter;
5190
+ search?: V1ListenPostParametersSearch;
5527
5191
  /**
5528
5192
  * Apply formatting to transcript output. When set to true, additional formatting will be applied to transcripts to improve readability
5529
5193
  */
5530
- smart_format?: ListenV1SmartFormatParameter;
5194
+ smart_format?: boolean;
5531
5195
  /**
5532
5196
  * Segments speech into meaningful semantic units
5533
5197
  */
5534
- utterances?: ListenV1UtterancesParameter;
5198
+ utterances?: boolean;
5535
5199
  /**
5536
5200
  * Seconds to wait before detecting a pause between words in submitted audio
5537
5201
  */
5538
- utt_split?: ListenV1UttSplitParameter;
5202
+ utt_split?: number;
5539
5203
  /**
5540
5204
  * Version of an AI model to use
5541
5205
  */
5542
- version?: ListenV1VersionParameter;
5206
+ version?: V1ListenPostParametersVersion;
5543
5207
  /**
5544
5208
  * Opts out requests from the Deepgram Model Improvement Program. Refer to our Docs for pricing impacts before setting this to true. https://dpgr.am/deepgram-mip
5545
5209
  */
5546
- mip_opt_out?: SharedMipOptOutParameter;
5210
+ mip_opt_out?: boolean;
5547
5211
  };
5548
5212
 
5549
5213
  /**
@@ -5943,11 +5607,6 @@ interface TranscriptParams {
5943
5607
  Note: This parameter is only supported for the Universal-3 Pro model.
5944
5608
  */
5945
5609
  remove_audio_tags?: TranscriptParamsRemoveAudioTags;
5946
- /** Control the amount of randomness injected into the model's response. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for more details.
5947
-
5948
- Note: This parameter can only be used with the Universal-3 Pro model.
5949
- */
5950
- temperature?: number;
5951
5610
  /** 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 */
5952
5611
  webhook_auth_header_name?: TranscriptParamsWebhookAuthHeaderName;
5953
5612
  /** The header value to send back with the transcript completed or failed [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) requests for added security */
@@ -5984,35 +5643,10 @@ type InitTranscriptionRequestCustomMetadata = {
5984
5643
  */
5985
5644
 
5986
5645
  interface InitTranscriptionRequest {
5987
- /**
5988
- * **[Deprecated]** Context to feed the transcription model with for possible better accuracy
5989
- * @deprecated
5990
- */
5991
- context_prompt?: string;
5992
5646
  /** **[Beta]** Can be either boolean to enable custom_vocabulary for this audio or an array with specific vocabulary list to feed the transcription model with */
5993
5647
  custom_vocabulary?: boolean;
5994
5648
  /** **[Beta]** Custom vocabulary configuration, if `custom_vocabulary` is enabled */
5995
5649
  custom_vocabulary_config?: CustomVocabularyConfigDTO;
5996
- /**
5997
- * **[Deprecated]** Use `language_config` instead. Detect the language from the given audio
5998
- * @deprecated
5999
- */
6000
- detect_language?: boolean;
6001
- /**
6002
- * **[Deprecated]** Use `language_config` instead.Detect multiple languages in the given audio
6003
- * @deprecated
6004
- */
6005
- enable_code_switching?: boolean;
6006
- /**
6007
- * **[Deprecated]** Use `language_config` instead. Specify the configuration for code switching
6008
- * @deprecated
6009
- */
6010
- code_switching_config?: CodeSwitchingConfigDTO;
6011
- /**
6012
- * **[Deprecated]** Use `language_config` instead. Set the spoken language for the given audio (ISO 639 standard)
6013
- * @deprecated
6014
- */
6015
- language?: TranscriptionLanguageCodeEnum;
6016
5650
  /**
6017
5651
  * **[Deprecated]** Use `callback`/`callback_config` instead. Callback URL we will do a `POST` request to with the result of the transcription
6018
5652
  * @deprecated
@@ -6038,34 +5672,26 @@ interface InitTranscriptionRequest {
6038
5672
  summarization?: boolean;
6039
5673
  /** **[Beta]** Summarization configuration, if `summarization` is enabled */
6040
5674
  summarization_config?: SummarizationConfigDTO;
6041
- /** **[Alpha]** Enable moderation for this audio */
6042
- moderation?: boolean;
6043
5675
  /** **[Alpha]** Enable named entity recognition for this audio */
6044
5676
  named_entity_recognition?: boolean;
6045
- /** **[Alpha]** Enable chapterization for this audio */
6046
- chapterization?: boolean;
6047
- /** **[Alpha]** Enable names consistency for this audio */
6048
- name_consistency?: boolean;
6049
5677
  /** **[Alpha]** Enable custom spelling for this audio */
6050
5678
  custom_spelling?: boolean;
6051
5679
  /** **[Alpha]** Custom spelling configuration, if `custom_spelling` is enabled */
6052
5680
  custom_spelling_config?: CustomSpellingConfigDTO;
6053
- /** **[Alpha]** Enable structured data extraction for this audio */
6054
- structured_data_extraction?: boolean;
6055
- /** **[Alpha]** Structured data extraction configuration, if `structured_data_extraction` is enabled */
6056
- structured_data_extraction_config?: StructuredDataExtractionConfigDTO;
6057
5681
  /** Enable sentiment analysis for this audio */
6058
5682
  sentiment_analysis?: boolean;
6059
5683
  /** **[Alpha]** Enable audio to llm processing for this audio */
6060
5684
  audio_to_llm?: boolean;
6061
5685
  /** **[Alpha]** Audio to llm configuration, if `audio_to_llm` is enabled */
6062
5686
  audio_to_llm_config?: AudioToLlmListConfigDTO;
5687
+ /** Enable PII redaction for this audio */
5688
+ pii_redaction?: boolean;
5689
+ /** PII redaction configuration, if `pii_redaction` is enabled */
5690
+ pii_redaction_config?: PiiRedactionConfigDTO;
6063
5691
  /** Custom metadata you can attach to this transcription */
6064
5692
  custom_metadata?: InitTranscriptionRequestCustomMetadata;
6065
5693
  /** Enable sentences for this audio */
6066
5694
  sentences?: boolean;
6067
- /** **[Alpha]** Allows to change the output display_mode for this audio. The output will be reordered, creating new utterances when speakers overlapped */
6068
- display_mode?: boolean;
6069
5695
  /** **[Alpha]** Use enhanced punctuation for this audio */
6070
5696
  punctuation_enhanced?: boolean;
6071
5697
  /** Specify the language configuration */
@@ -6195,7 +5821,7 @@ interface VadConfig {
6195
5821
  /**
6196
5822
  * Controls how the audio is cut into chunks. When set to `"auto"`, the server first normalizes loudness and then uses voice activity detection (VAD) to choose boundaries. `server_vad` object can be provided to tweak VAD detection parameters manually. If unset, the audio is transcribed as a single block. Required when using `gpt-4o-transcribe-diarize` for inputs longer than 30 seconds.
6197
5823
  */
6198
- type TranscriptionChunkingStrategyAnyOf = "auto" | VadConfig;
5824
+ type CreateTranscriptionRequestChunkingStrategyAnyOf = "auto" | VadConfig;
6199
5825
 
6200
5826
  /**
6201
5827
  * Generated by orval v7.9.0 🍺
@@ -6205,7 +5831,7 @@ type TranscriptionChunkingStrategyAnyOf = "auto" | VadConfig;
6205
5831
  * OpenAPI spec version: 2.3.0
6206
5832
  */
6207
5833
 
6208
- type TranscriptionChunkingStrategy = TranscriptionChunkingStrategyAnyOf | null;
5834
+ type CreateTranscriptionRequestChunkingStrategy = CreateTranscriptionRequestChunkingStrategyAnyOf | null;
6209
5835
 
6210
5836
  /**
6211
5837
  * Generated by orval v7.9.0 🍺
@@ -6225,7 +5851,7 @@ interface CreateTranscriptionRequest {
6225
5851
  /** The language of the input audio. Supplying the input language in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format will improve accuracy and latency.
6226
5852
  */
6227
5853
  language?: string;
6228
- /** An optional text to guide the model's style or continue a previous audio segment. The [prompt](https://platform.openai.com/docs/guides/speech-to-text#prompting) should match the audio language. This field is not supported when using `gpt-4o-transcribe-diarize`.
5854
+ /** An optional text to guide the model's style or continue a previous audio segment. The [prompt](/docs/guides/speech-to-text#prompting) should match the audio language. This field is not supported when using `gpt-4o-transcribe-diarize`.
6229
5855
  */
6230
5856
  prompt?: string;
6231
5857
  response_format?: AudioResponseFormat;
@@ -6244,7 +5870,7 @@ interface CreateTranscriptionRequest {
6244
5870
  */
6245
5871
  timestamp_granularities?: CreateTranscriptionRequestTimestampGranularitiesItem[];
6246
5872
  stream?: CreateTranscriptionRequestStream;
6247
- chunking_strategy?: TranscriptionChunkingStrategy;
5873
+ chunking_strategy?: CreateTranscriptionRequestChunkingStrategy;
6248
5874
  /**
6249
5875
  * Optional list of speaker names that correspond to the audio samples provided in `known_speaker_references[]`. Each entry should be a short identifier (for example `customer` or `agent`). Up to 4 speakers are supported.
6250
5876
 
@@ -6266,9 +5892,13 @@ interface CreateTranscriptionRequest {
6266
5892
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6267
5893
  * OpenAPI spec version: 1.0
6268
5894
  */
6269
- type DocxExportOptionsFormat = (typeof DocxExportOptionsFormat)[keyof typeof DocxExportOptionsFormat];
6270
- declare const DocxExportOptionsFormat: {
6271
- readonly docx: "docx";
5895
+ /**
5896
+ * The ID of the model to use for transcription.
5897
+ */
5898
+ type BodySpeechToTextV1SpeechToTextPostModelId = (typeof BodySpeechToTextV1SpeechToTextPostModelId)[keyof typeof BodySpeechToTextV1SpeechToTextPostModelId];
5899
+ declare const BodySpeechToTextV1SpeechToTextPostModelId: {
5900
+ readonly scribe_v1: "scribe_v1";
5901
+ readonly scribe_v2: "scribe_v2";
6272
5902
  };
6273
5903
 
6274
5904
  /**
@@ -6278,7 +5908,10 @@ declare const DocxExportOptionsFormat: {
6278
5908
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6279
5909
  * OpenAPI spec version: 1.0
6280
5910
  */
6281
- type DocxExportOptionsMaxSegmentChars = number | null;
5911
+ /**
5912
+ * 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 3.0GB.
5913
+ */
5914
+ type BodySpeechToTextV1SpeechToTextPostFile = Blob | null;
6282
5915
 
6283
5916
  /**
6284
5917
  * Generated by orval v7.9.0 🍺
@@ -6287,7 +5920,10 @@ type DocxExportOptionsMaxSegmentChars = number | null;
6287
5920
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6288
5921
  * OpenAPI spec version: 1.0
6289
5922
  */
6290
- type DocxExportOptionsMaxSegmentDurationS = number | null;
5923
+ /**
5924
+ * 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.
5925
+ */
5926
+ type BodySpeechToTextV1SpeechToTextPostLanguageCode = string | null;
6291
5927
 
6292
5928
  /**
6293
5929
  * Generated by orval v7.9.0 🍺
@@ -6296,7 +5932,10 @@ type DocxExportOptionsMaxSegmentDurationS = number | null;
6296
5932
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6297
5933
  * OpenAPI spec version: 1.0
6298
5934
  */
6299
- type DocxExportOptionsSegmentOnSilenceLongerThanS = number | null;
5935
+ /**
5936
+ * The maximum amount of speakers talking in the uploaded file. Can help with predicting who speaks when. The maximum amount of speakers that can be predicted is 32. Defaults to null, in this case the amount of speakers is set to the maximum value the model supports.
5937
+ */
5938
+ type BodySpeechToTextV1SpeechToTextPostNumSpeakers = number | null;
6300
5939
 
6301
5940
  /**
6302
5941
  * Generated by orval v7.9.0 🍺
@@ -6305,15 +5944,27 @@ type DocxExportOptionsSegmentOnSilenceLongerThanS = number | null;
6305
5944
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6306
5945
  * OpenAPI spec version: 1.0
6307
5946
  */
5947
+ /**
5948
+ * The granularity of the timestamps in the transcription. 'word' provides word-level timestamps and 'character' provides character-level timestamps per word.
5949
+ */
5950
+ type BodySpeechToTextV1SpeechToTextPostTimestampsGranularity = (typeof BodySpeechToTextV1SpeechToTextPostTimestampsGranularity)[keyof typeof BodySpeechToTextV1SpeechToTextPostTimestampsGranularity];
5951
+ declare const BodySpeechToTextV1SpeechToTextPostTimestampsGranularity: {
5952
+ readonly none: "none";
5953
+ readonly word: "word";
5954
+ readonly character: "character";
5955
+ };
6308
5956
 
6309
- interface DocxExportOptions {
6310
- include_speakers?: boolean;
6311
- include_timestamps?: boolean;
6312
- format: DocxExportOptionsFormat;
6313
- segment_on_silence_longer_than_s?: DocxExportOptionsSegmentOnSilenceLongerThanS;
6314
- max_segment_duration_s?: DocxExportOptionsMaxSegmentDurationS;
6315
- max_segment_chars?: DocxExportOptionsMaxSegmentChars;
6316
- }
5957
+ /**
5958
+ * Generated by orval v7.9.0 🍺
5959
+ * Do not edit manually.
5960
+ * ElevenLabs Speech-to-Text API
5961
+ * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
5962
+ * OpenAPI spec version: 1.0
5963
+ */
5964
+ /**
5965
+ * Diarization threshold to apply during speaker diarization. A higher value means there will be a lower chance of one speaker being diarized as two different speakers but also a higher chance of two different speakers being diarized as one speaker (less total speakers predicted). A low value means there will be a higher chance of one speaker being diarized as two different speakers but also a lower chance of two different speakers being diarized as one speaker (more total speakers predicted). Can only be set when diarize=True and num_speakers=None. Defaults to None, in which case we will choose a threshold based on the model_id (0.22 usually).
5966
+ */
5967
+ type BodySpeechToTextV1SpeechToTextPostDiarizationThreshold = number | null;
6317
5968
 
6318
5969
  /**
6319
5970
  * Generated by orval v7.9.0 🍺
@@ -6322,9 +5973,9 @@ interface DocxExportOptions {
6322
5973
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6323
5974
  * OpenAPI spec version: 1.0
6324
5975
  */
6325
- type HtmlExportOptionsFormat = (typeof HtmlExportOptionsFormat)[keyof typeof HtmlExportOptionsFormat];
6326
- declare const HtmlExportOptionsFormat: {
6327
- readonly html: "html";
5976
+ type SegmentedJsonExportOptionsFormat = (typeof SegmentedJsonExportOptionsFormat)[keyof typeof SegmentedJsonExportOptionsFormat];
5977
+ declare const SegmentedJsonExportOptionsFormat: {
5978
+ readonly segmented_json: "segmented_json";
6328
5979
  };
6329
5980
 
6330
5981
  /**
@@ -6334,7 +5985,7 @@ declare const HtmlExportOptionsFormat: {
6334
5985
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6335
5986
  * OpenAPI spec version: 1.0
6336
5987
  */
6337
- type HtmlExportOptionsMaxSegmentChars = number | null;
5988
+ type SegmentedJsonExportOptionsSegmentOnSilenceLongerThanS = number | null;
6338
5989
 
6339
5990
  /**
6340
5991
  * Generated by orval v7.9.0 🍺
@@ -6343,7 +5994,7 @@ type HtmlExportOptionsMaxSegmentChars = number | null;
6343
5994
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6344
5995
  * OpenAPI spec version: 1.0
6345
5996
  */
6346
- type HtmlExportOptionsMaxSegmentDurationS = number | null;
5997
+ type SegmentedJsonExportOptionsMaxSegmentDurationS = number | null;
6347
5998
 
6348
5999
  /**
6349
6000
  * Generated by orval v7.9.0 🍺
@@ -6352,7 +6003,7 @@ type HtmlExportOptionsMaxSegmentDurationS = number | null;
6352
6003
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6353
6004
  * OpenAPI spec version: 1.0
6354
6005
  */
6355
- type HtmlExportOptionsSegmentOnSilenceLongerThanS = number | null;
6006
+ type SegmentedJsonExportOptionsMaxSegmentChars = number | null;
6356
6007
 
6357
6008
  /**
6358
6009
  * Generated by orval v7.9.0 🍺
@@ -6362,13 +6013,13 @@ type HtmlExportOptionsSegmentOnSilenceLongerThanS = number | null;
6362
6013
  * OpenAPI spec version: 1.0
6363
6014
  */
6364
6015
 
6365
- interface HtmlExportOptions {
6016
+ interface SegmentedJsonExportOptions {
6366
6017
  include_speakers?: boolean;
6367
6018
  include_timestamps?: boolean;
6368
- format: HtmlExportOptionsFormat;
6369
- segment_on_silence_longer_than_s?: HtmlExportOptionsSegmentOnSilenceLongerThanS;
6370
- max_segment_duration_s?: HtmlExportOptionsMaxSegmentDurationS;
6371
- max_segment_chars?: HtmlExportOptionsMaxSegmentChars;
6019
+ format: SegmentedJsonExportOptionsFormat;
6020
+ segment_on_silence_longer_than_s?: SegmentedJsonExportOptionsSegmentOnSilenceLongerThanS;
6021
+ max_segment_duration_s?: SegmentedJsonExportOptionsMaxSegmentDurationS;
6022
+ max_segment_chars?: SegmentedJsonExportOptionsMaxSegmentChars;
6372
6023
  }
6373
6024
 
6374
6025
  /**
@@ -6378,9 +6029,9 @@ interface HtmlExportOptions {
6378
6029
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6379
6030
  * OpenAPI spec version: 1.0
6380
6031
  */
6381
- type PdfExportOptionsFormat = (typeof PdfExportOptionsFormat)[keyof typeof PdfExportOptionsFormat];
6382
- declare const PdfExportOptionsFormat: {
6383
- readonly pdf: "pdf";
6032
+ type DocxExportOptionsFormat = (typeof DocxExportOptionsFormat)[keyof typeof DocxExportOptionsFormat];
6033
+ declare const DocxExportOptionsFormat: {
6034
+ readonly docx: "docx";
6384
6035
  };
6385
6036
 
6386
6037
  /**
@@ -6390,7 +6041,7 @@ declare const PdfExportOptionsFormat: {
6390
6041
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6391
6042
  * OpenAPI spec version: 1.0
6392
6043
  */
6393
- type PdfExportOptionsMaxSegmentChars = number | null;
6044
+ type DocxExportOptionsSegmentOnSilenceLongerThanS = number | null;
6394
6045
 
6395
6046
  /**
6396
6047
  * Generated by orval v7.9.0 🍺
@@ -6399,7 +6050,7 @@ type PdfExportOptionsMaxSegmentChars = number | null;
6399
6050
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6400
6051
  * OpenAPI spec version: 1.0
6401
6052
  */
6402
- type PdfExportOptionsMaxSegmentDurationS = number | null;
6053
+ type DocxExportOptionsMaxSegmentDurationS = number | null;
6403
6054
 
6404
6055
  /**
6405
6056
  * Generated by orval v7.9.0 🍺
@@ -6408,7 +6059,7 @@ type PdfExportOptionsMaxSegmentDurationS = number | null;
6408
6059
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6409
6060
  * OpenAPI spec version: 1.0
6410
6061
  */
6411
- type PdfExportOptionsSegmentOnSilenceLongerThanS = number | null;
6062
+ type DocxExportOptionsMaxSegmentChars = number | null;
6412
6063
 
6413
6064
  /**
6414
6065
  * Generated by orval v7.9.0 🍺
@@ -6418,13 +6069,13 @@ type PdfExportOptionsSegmentOnSilenceLongerThanS = number | null;
6418
6069
  * OpenAPI spec version: 1.0
6419
6070
  */
6420
6071
 
6421
- interface PdfExportOptions {
6422
- include_speakers?: boolean;
6423
- include_timestamps?: boolean;
6424
- format: PdfExportOptionsFormat;
6425
- segment_on_silence_longer_than_s?: PdfExportOptionsSegmentOnSilenceLongerThanS;
6426
- max_segment_duration_s?: PdfExportOptionsMaxSegmentDurationS;
6427
- max_segment_chars?: PdfExportOptionsMaxSegmentChars;
6072
+ interface DocxExportOptions {
6073
+ include_speakers?: boolean;
6074
+ include_timestamps?: boolean;
6075
+ format: DocxExportOptionsFormat;
6076
+ segment_on_silence_longer_than_s?: DocxExportOptionsSegmentOnSilenceLongerThanS;
6077
+ max_segment_duration_s?: DocxExportOptionsMaxSegmentDurationS;
6078
+ max_segment_chars?: DocxExportOptionsMaxSegmentChars;
6428
6079
  }
6429
6080
 
6430
6081
  /**
@@ -6434,9 +6085,9 @@ interface PdfExportOptions {
6434
6085
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6435
6086
  * OpenAPI spec version: 1.0
6436
6087
  */
6437
- type SegmentedJsonExportOptionsFormat = (typeof SegmentedJsonExportOptionsFormat)[keyof typeof SegmentedJsonExportOptionsFormat];
6438
- declare const SegmentedJsonExportOptionsFormat: {
6439
- readonly segmented_json: "segmented_json";
6088
+ type PdfExportOptionsFormat = (typeof PdfExportOptionsFormat)[keyof typeof PdfExportOptionsFormat];
6089
+ declare const PdfExportOptionsFormat: {
6090
+ readonly pdf: "pdf";
6440
6091
  };
6441
6092
 
6442
6093
  /**
@@ -6446,7 +6097,7 @@ declare const SegmentedJsonExportOptionsFormat: {
6446
6097
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6447
6098
  * OpenAPI spec version: 1.0
6448
6099
  */
6449
- type SegmentedJsonExportOptionsMaxSegmentChars = number | null;
6100
+ type PdfExportOptionsSegmentOnSilenceLongerThanS = number | null;
6450
6101
 
6451
6102
  /**
6452
6103
  * Generated by orval v7.9.0 🍺
@@ -6455,7 +6106,7 @@ type SegmentedJsonExportOptionsMaxSegmentChars = number | null;
6455
6106
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6456
6107
  * OpenAPI spec version: 1.0
6457
6108
  */
6458
- type SegmentedJsonExportOptionsMaxSegmentDurationS = number | null;
6109
+ type PdfExportOptionsMaxSegmentDurationS = number | null;
6459
6110
 
6460
6111
  /**
6461
6112
  * Generated by orval v7.9.0 🍺
@@ -6464,7 +6115,7 @@ type SegmentedJsonExportOptionsMaxSegmentDurationS = number | null;
6464
6115
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6465
6116
  * OpenAPI spec version: 1.0
6466
6117
  */
6467
- type SegmentedJsonExportOptionsSegmentOnSilenceLongerThanS = number | null;
6118
+ type PdfExportOptionsMaxSegmentChars = number | null;
6468
6119
 
6469
6120
  /**
6470
6121
  * Generated by orval v7.9.0 🍺
@@ -6474,13 +6125,13 @@ type SegmentedJsonExportOptionsSegmentOnSilenceLongerThanS = number | null;
6474
6125
  * OpenAPI spec version: 1.0
6475
6126
  */
6476
6127
 
6477
- interface SegmentedJsonExportOptions {
6128
+ interface PdfExportOptions {
6478
6129
  include_speakers?: boolean;
6479
6130
  include_timestamps?: boolean;
6480
- format: SegmentedJsonExportOptionsFormat;
6481
- segment_on_silence_longer_than_s?: SegmentedJsonExportOptionsSegmentOnSilenceLongerThanS;
6482
- max_segment_duration_s?: SegmentedJsonExportOptionsMaxSegmentDurationS;
6483
- max_segment_chars?: SegmentedJsonExportOptionsMaxSegmentChars;
6131
+ format: PdfExportOptionsFormat;
6132
+ segment_on_silence_longer_than_s?: PdfExportOptionsSegmentOnSilenceLongerThanS;
6133
+ max_segment_duration_s?: PdfExportOptionsMaxSegmentDurationS;
6134
+ max_segment_chars?: PdfExportOptionsMaxSegmentChars;
6484
6135
  }
6485
6136
 
6486
6137
  /**
@@ -6490,10 +6141,7 @@ interface SegmentedJsonExportOptions {
6490
6141
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6491
6142
  * OpenAPI spec version: 1.0
6492
6143
  */
6493
- type SrtExportOptionsFormat = (typeof SrtExportOptionsFormat)[keyof typeof SrtExportOptionsFormat];
6494
- declare const SrtExportOptionsFormat: {
6495
- readonly srt: "srt";
6496
- };
6144
+ type TxtExportOptionsMaxCharactersPerLine = number | null;
6497
6145
 
6498
6146
  /**
6499
6147
  * Generated by orval v7.9.0 🍺
@@ -6502,7 +6150,10 @@ declare const SrtExportOptionsFormat: {
6502
6150
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6503
6151
  * OpenAPI spec version: 1.0
6504
6152
  */
6505
- type SrtExportOptionsMaxCharactersPerLine = number | null;
6153
+ type TxtExportOptionsFormat = (typeof TxtExportOptionsFormat)[keyof typeof TxtExportOptionsFormat];
6154
+ declare const TxtExportOptionsFormat: {
6155
+ readonly txt: "txt";
6156
+ };
6506
6157
 
6507
6158
  /**
6508
6159
  * Generated by orval v7.9.0 🍺
@@ -6511,7 +6162,7 @@ type SrtExportOptionsMaxCharactersPerLine = number | null;
6511
6162
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6512
6163
  * OpenAPI spec version: 1.0
6513
6164
  */
6514
- type SrtExportOptionsMaxSegmentChars = number | null;
6165
+ type TxtExportOptionsSegmentOnSilenceLongerThanS = number | null;
6515
6166
 
6516
6167
  /**
6517
6168
  * Generated by orval v7.9.0 🍺
@@ -6520,7 +6171,7 @@ type SrtExportOptionsMaxSegmentChars = number | null;
6520
6171
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6521
6172
  * OpenAPI spec version: 1.0
6522
6173
  */
6523
- type SrtExportOptionsMaxSegmentDurationS = number | null;
6174
+ type TxtExportOptionsMaxSegmentDurationS = number | null;
6524
6175
 
6525
6176
  /**
6526
6177
  * Generated by orval v7.9.0 🍺
@@ -6529,7 +6180,7 @@ type SrtExportOptionsMaxSegmentDurationS = number | null;
6529
6180
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6530
6181
  * OpenAPI spec version: 1.0
6531
6182
  */
6532
- type SrtExportOptionsSegmentOnSilenceLongerThanS = number | null;
6183
+ type TxtExportOptionsMaxSegmentChars = number | null;
6533
6184
 
6534
6185
  /**
6535
6186
  * Generated by orval v7.9.0 🍺
@@ -6539,14 +6190,14 @@ type SrtExportOptionsSegmentOnSilenceLongerThanS = number | null;
6539
6190
  * OpenAPI spec version: 1.0
6540
6191
  */
6541
6192
 
6542
- interface SrtExportOptions {
6543
- max_characters_per_line?: SrtExportOptionsMaxCharactersPerLine;
6193
+ interface TxtExportOptions {
6194
+ max_characters_per_line?: TxtExportOptionsMaxCharactersPerLine;
6544
6195
  include_speakers?: boolean;
6545
6196
  include_timestamps?: boolean;
6546
- format: SrtExportOptionsFormat;
6547
- segment_on_silence_longer_than_s?: SrtExportOptionsSegmentOnSilenceLongerThanS;
6548
- max_segment_duration_s?: SrtExportOptionsMaxSegmentDurationS;
6549
- max_segment_chars?: SrtExportOptionsMaxSegmentChars;
6197
+ format: TxtExportOptionsFormat;
6198
+ segment_on_silence_longer_than_s?: TxtExportOptionsSegmentOnSilenceLongerThanS;
6199
+ max_segment_duration_s?: TxtExportOptionsMaxSegmentDurationS;
6200
+ max_segment_chars?: TxtExportOptionsMaxSegmentChars;
6550
6201
  }
6551
6202
 
6552
6203
  /**
@@ -6556,9 +6207,9 @@ interface SrtExportOptions {
6556
6207
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6557
6208
  * OpenAPI spec version: 1.0
6558
6209
  */
6559
- type TxtExportOptionsFormat = (typeof TxtExportOptionsFormat)[keyof typeof TxtExportOptionsFormat];
6560
- declare const TxtExportOptionsFormat: {
6561
- readonly txt: "txt";
6210
+ type HtmlExportOptionsFormat = (typeof HtmlExportOptionsFormat)[keyof typeof HtmlExportOptionsFormat];
6211
+ declare const HtmlExportOptionsFormat: {
6212
+ readonly html: "html";
6562
6213
  };
6563
6214
 
6564
6215
  /**
@@ -6568,7 +6219,7 @@ declare const TxtExportOptionsFormat: {
6568
6219
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6569
6220
  * OpenAPI spec version: 1.0
6570
6221
  */
6571
- type TxtExportOptionsMaxCharactersPerLine = number | null;
6222
+ type HtmlExportOptionsSegmentOnSilenceLongerThanS = number | null;
6572
6223
 
6573
6224
  /**
6574
6225
  * Generated by orval v7.9.0 🍺
@@ -6577,7 +6228,7 @@ type TxtExportOptionsMaxCharactersPerLine = number | null;
6577
6228
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6578
6229
  * OpenAPI spec version: 1.0
6579
6230
  */
6580
- type TxtExportOptionsMaxSegmentChars = number | null;
6231
+ type HtmlExportOptionsMaxSegmentDurationS = number | null;
6581
6232
 
6582
6233
  /**
6583
6234
  * Generated by orval v7.9.0 🍺
@@ -6586,7 +6237,7 @@ type TxtExportOptionsMaxSegmentChars = number | null;
6586
6237
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6587
6238
  * OpenAPI spec version: 1.0
6588
6239
  */
6589
- type TxtExportOptionsMaxSegmentDurationS = number | null;
6240
+ type HtmlExportOptionsMaxSegmentChars = number | null;
6590
6241
 
6591
6242
  /**
6592
6243
  * Generated by orval v7.9.0 🍺
@@ -6595,7 +6246,15 @@ type TxtExportOptionsMaxSegmentDurationS = number | null;
6595
6246
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6596
6247
  * OpenAPI spec version: 1.0
6597
6248
  */
6598
- type TxtExportOptionsSegmentOnSilenceLongerThanS = number | null;
6249
+
6250
+ interface HtmlExportOptions {
6251
+ include_speakers?: boolean;
6252
+ include_timestamps?: boolean;
6253
+ format: HtmlExportOptionsFormat;
6254
+ segment_on_silence_longer_than_s?: HtmlExportOptionsSegmentOnSilenceLongerThanS;
6255
+ max_segment_duration_s?: HtmlExportOptionsMaxSegmentDurationS;
6256
+ max_segment_chars?: HtmlExportOptionsMaxSegmentChars;
6257
+ }
6599
6258
 
6600
6259
  /**
6601
6260
  * Generated by orval v7.9.0 🍺
@@ -6604,16 +6263,7 @@ type TxtExportOptionsSegmentOnSilenceLongerThanS = number | null;
6604
6263
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6605
6264
  * OpenAPI spec version: 1.0
6606
6265
  */
6607
-
6608
- interface TxtExportOptions {
6609
- max_characters_per_line?: TxtExportOptionsMaxCharactersPerLine;
6610
- include_speakers?: boolean;
6611
- include_timestamps?: boolean;
6612
- format: TxtExportOptionsFormat;
6613
- segment_on_silence_longer_than_s?: TxtExportOptionsSegmentOnSilenceLongerThanS;
6614
- max_segment_duration_s?: TxtExportOptionsMaxSegmentDurationS;
6615
- max_segment_chars?: TxtExportOptionsMaxSegmentChars;
6616
- }
6266
+ type SrtExportOptionsMaxCharactersPerLine = number | null;
6617
6267
 
6618
6268
  /**
6619
6269
  * Generated by orval v7.9.0 🍺
@@ -6622,8 +6272,10 @@ interface TxtExportOptions {
6622
6272
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6623
6273
  * OpenAPI spec version: 1.0
6624
6274
  */
6625
-
6626
- type ExportOptions = SegmentedJsonExportOptions | DocxExportOptions | PdfExportOptions | TxtExportOptions | HtmlExportOptions | SrtExportOptions;
6275
+ type SrtExportOptionsFormat = (typeof SrtExportOptionsFormat)[keyof typeof SrtExportOptionsFormat];
6276
+ declare const SrtExportOptionsFormat: {
6277
+ readonly srt: "srt";
6278
+ };
6627
6279
 
6628
6280
  /**
6629
6281
  * Generated by orval v7.9.0 🍺
@@ -6632,11 +6284,16 @@ type ExportOptions = SegmentedJsonExportOptions | DocxExportOptions | PdfExportO
6632
6284
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6633
6285
  * OpenAPI spec version: 1.0
6634
6286
  */
6287
+ type SrtExportOptionsSegmentOnSilenceLongerThanS = number | null;
6635
6288
 
6636
6289
  /**
6637
- * @maxItems 10
6290
+ * Generated by orval v7.9.0 🍺
6291
+ * Do not edit manually.
6292
+ * ElevenLabs Speech-to-Text API
6293
+ * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6294
+ * OpenAPI spec version: 1.0
6638
6295
  */
6639
- type AdditionalFormats = ExportOptions[];
6296
+ type SrtExportOptionsMaxSegmentDurationS = number | null;
6640
6297
 
6641
6298
  /**
6642
6299
  * Generated by orval v7.9.0 🍺
@@ -6645,10 +6302,7 @@ type AdditionalFormats = ExportOptions[];
6645
6302
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6646
6303
  * OpenAPI spec version: 1.0
6647
6304
  */
6648
- /**
6649
- * 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.
6650
- */
6651
- type BodySpeechToTextV1SpeechToTextPostCloudStorageUrl = string | null;
6305
+ type SrtExportOptionsMaxSegmentChars = number | null;
6652
6306
 
6653
6307
  /**
6654
6308
  * Generated by orval v7.9.0 🍺
@@ -6657,10 +6311,16 @@ type BodySpeechToTextV1SpeechToTextPostCloudStorageUrl = string | null;
6657
6311
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6658
6312
  * OpenAPI spec version: 1.0
6659
6313
  */
6660
- /**
6661
- * Diarization threshold to apply during speaker diarization. A higher value means there will be a lower chance of one speaker being diarized as two different speakers but also a higher chance of two different speakers being diarized as one speaker (less total speakers predicted). A low value means there will be a higher chance of one speaker being diarized as two different speakers but also a lower chance of two different speakers being diarized as one speaker (more total speakers predicted). Can only be set when diarize=True and num_speakers=None. Defaults to None, in which case we will choose a threshold based on the model_id (0.22 usually).
6662
- */
6663
- type BodySpeechToTextV1SpeechToTextPostDiarizationThreshold = number | null;
6314
+
6315
+ interface SrtExportOptions {
6316
+ max_characters_per_line?: SrtExportOptionsMaxCharactersPerLine;
6317
+ include_speakers?: boolean;
6318
+ include_timestamps?: boolean;
6319
+ format: SrtExportOptionsFormat;
6320
+ segment_on_silence_longer_than_s?: SrtExportOptionsSegmentOnSilenceLongerThanS;
6321
+ max_segment_duration_s?: SrtExportOptionsMaxSegmentDurationS;
6322
+ max_segment_chars?: SrtExportOptionsMaxSegmentChars;
6323
+ }
6664
6324
 
6665
6325
  /**
6666
6326
  * Generated by orval v7.9.0 🍺
@@ -6669,10 +6329,8 @@ type BodySpeechToTextV1SpeechToTextPostDiarizationThreshold = number | null;
6669
6329
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6670
6330
  * OpenAPI spec version: 1.0
6671
6331
  */
6672
- /**
6673
- * Detect entities in the transcript. Can be 'all' to detect all entities, a single entity type or category string, or a list of entity types/categories. Categories include 'pii', 'phi', 'pci', 'other', 'offensive_language'. When enabled, detected entities will be returned in the 'entities' field with their text, type, and character positions. Usage of this parameter will incur additional costs.
6674
- */
6675
- type BodySpeechToTextV1SpeechToTextPostEntityDetection = string | string[] | null;
6332
+
6333
+ type ExportOptions = SegmentedJsonExportOptions | DocxExportOptions | PdfExportOptions | TxtExportOptions | HtmlExportOptions | SrtExportOptions;
6676
6334
 
6677
6335
  /**
6678
6336
  * Generated by orval v7.9.0 🍺
@@ -6681,10 +6339,11 @@ type BodySpeechToTextV1SpeechToTextPostEntityDetection = string | string[] | nul
6681
6339
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6682
6340
  * OpenAPI spec version: 1.0
6683
6341
  */
6342
+
6684
6343
  /**
6685
- * The file to transcribe. 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 3.0GB.
6344
+ * @maxItems 10
6686
6345
  */
6687
- type BodySpeechToTextV1SpeechToTextPostFile = Blob | null;
6346
+ type AdditionalFormats = ExportOptions[];
6688
6347
 
6689
6348
  /**
6690
6349
  * Generated by orval v7.9.0 🍺
@@ -6710,9 +6369,10 @@ declare const BodySpeechToTextV1SpeechToTextPostFileFormat: {
6710
6369
  * OpenAPI spec version: 1.0
6711
6370
  */
6712
6371
  /**
6713
- * 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.
6372
+ * 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.
6373
+ * @deprecated
6714
6374
  */
6715
- type BodySpeechToTextV1SpeechToTextPostLanguageCode = string | null;
6375
+ type BodySpeechToTextV1SpeechToTextPostCloudStorageUrl = string | null;
6716
6376
 
6717
6377
  /**
6718
6378
  * Generated by orval v7.9.0 🍺
@@ -6722,13 +6382,9 @@ type BodySpeechToTextV1SpeechToTextPostLanguageCode = string | null;
6722
6382
  * OpenAPI spec version: 1.0
6723
6383
  */
6724
6384
  /**
6725
- * The ID of the model to use for transcription.
6385
+ * The URL of an audio or video file to transcribe. Supports hosted video or audio files, YouTube video URLs, TikTok video URLs, and other video hosting services.
6726
6386
  */
6727
- type BodySpeechToTextV1SpeechToTextPostModelId = (typeof BodySpeechToTextV1SpeechToTextPostModelId)[keyof typeof BodySpeechToTextV1SpeechToTextPostModelId];
6728
- declare const BodySpeechToTextV1SpeechToTextPostModelId: {
6729
- readonly scribe_v1: "scribe_v1";
6730
- readonly scribe_v2: "scribe_v2";
6731
- };
6387
+ type BodySpeechToTextV1SpeechToTextPostSourceUrl = string | null;
6732
6388
 
6733
6389
  /**
6734
6390
  * Generated by orval v7.9.0 🍺
@@ -6738,9 +6394,9 @@ declare const BodySpeechToTextV1SpeechToTextPostModelId: {
6738
6394
  * OpenAPI spec version: 1.0
6739
6395
  */
6740
6396
  /**
6741
- * The maximum amount of speakers talking in the uploaded file. Can help with predicting who speaks when. The maximum amount of speakers that can be predicted is 32. Defaults to null, in this case the amount of speakers is set to the maximum value the model supports.
6397
+ * Optional specific webhook ID to send the transcription result to. Only valid when webhook is set to true. If not provided, transcription will be sent to all configured speech-to-text webhooks.
6742
6398
  */
6743
- type BodySpeechToTextV1SpeechToTextPostNumSpeakers = number | null;
6399
+ type BodySpeechToTextV1SpeechToTextPostWebhookId = string | null;
6744
6400
 
6745
6401
  /**
6746
6402
  * Generated by orval v7.9.0 🍺
@@ -6750,9 +6406,9 @@ type BodySpeechToTextV1SpeechToTextPostNumSpeakers = number | null;
6750
6406
  * OpenAPI spec version: 1.0
6751
6407
  */
6752
6408
  /**
6753
- * If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. Must be an integer between 0 and 2147483647.
6409
+ * Controls the randomness of the transcription output. Accepts values between 0.0 and 2.0, where higher values result in more diverse and less deterministic results. If omitted, we will use a temperature based on the model you selected which is usually 0.
6754
6410
  */
6755
- type BodySpeechToTextV1SpeechToTextPostSeed = number | null;
6411
+ type BodySpeechToTextV1SpeechToTextPostTemperature = number | null;
6756
6412
 
6757
6413
  /**
6758
6414
  * Generated by orval v7.9.0 🍺
@@ -6762,9 +6418,9 @@ type BodySpeechToTextV1SpeechToTextPostSeed = number | null;
6762
6418
  * OpenAPI spec version: 1.0
6763
6419
  */
6764
6420
  /**
6765
- * Controls the randomness of the transcription output. Accepts values between 0.0 and 2.0, where higher values result in more diverse and less deterministic results. If omitted, we will use a temperature based on the model you selected which is usually 0.
6421
+ * If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. Must be an integer between 0 and 2147483647.
6766
6422
  */
6767
- type BodySpeechToTextV1SpeechToTextPostTemperature = number | null;
6423
+ type BodySpeechToTextV1SpeechToTextPostSeed = number | null;
6768
6424
 
6769
6425
  /**
6770
6426
  * Generated by orval v7.9.0 🍺
@@ -6773,14 +6429,8 @@ type BodySpeechToTextV1SpeechToTextPostTemperature = number | null;
6773
6429
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6774
6430
  * OpenAPI spec version: 1.0
6775
6431
  */
6776
- /**
6777
- * The granularity of the timestamps in the transcription. 'word' provides word-level timestamps and 'character' provides character-level timestamps per word.
6778
- */
6779
- type BodySpeechToTextV1SpeechToTextPostTimestampsGranularity = (typeof BodySpeechToTextV1SpeechToTextPostTimestampsGranularity)[keyof typeof BodySpeechToTextV1SpeechToTextPostTimestampsGranularity];
6780
- declare const BodySpeechToTextV1SpeechToTextPostTimestampsGranularity: {
6781
- readonly none: "none";
6782
- readonly word: "word";
6783
- readonly character: "character";
6432
+ type BodySpeechToTextV1SpeechToTextPostWebhookMetadataAnyOf = {
6433
+ [key: string]: unknown;
6784
6434
  };
6785
6435
 
6786
6436
  /**
@@ -6790,10 +6440,11 @@ declare const BodySpeechToTextV1SpeechToTextPostTimestampsGranularity: {
6790
6440
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6791
6441
  * OpenAPI spec version: 1.0
6792
6442
  */
6443
+
6793
6444
  /**
6794
- * Optional specific webhook ID to send the transcription result to. Only valid when webhook is set to true. If not provided, transcription will be sent to all configured speech-to-text webhooks.
6445
+ * Optional metadata to be included in the webhook response. This should be a JSON string representing an object with a maximum depth of 2 levels and maximum size of 16KB. Useful for tracking internal IDs, job references, or other contextual information.
6795
6446
  */
6796
- type BodySpeechToTextV1SpeechToTextPostWebhookId = string | null;
6447
+ type BodySpeechToTextV1SpeechToTextPostWebhookMetadata = string | BodySpeechToTextV1SpeechToTextPostWebhookMetadataAnyOf | null;
6797
6448
 
6798
6449
  /**
6799
6450
  * Generated by orval v7.9.0 🍺
@@ -6802,9 +6453,10 @@ type BodySpeechToTextV1SpeechToTextPostWebhookId = string | null;
6802
6453
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6803
6454
  * OpenAPI spec version: 1.0
6804
6455
  */
6805
- type BodySpeechToTextV1SpeechToTextPostWebhookMetadataAnyOf = {
6806
- [key: string]: unknown;
6807
- };
6456
+ /**
6457
+ * Detect entities in the transcript. Can be 'all' to detect all entities, a single entity type or category string, or a list of entity types/categories. Categories include 'pii', 'phi', 'pci', 'other', 'offensive_language'. When enabled, detected entities will be returned in the 'entities' field with their text, type, and character positions. Usage of this parameter will incur an additional 30% surcharge on the base transcription cost.
6458
+ */
6459
+ type BodySpeechToTextV1SpeechToTextPostEntityDetection = string | string[] | null;
6808
6460
 
6809
6461
  /**
6810
6462
  * Generated by orval v7.9.0 🍺
@@ -6813,11 +6465,10 @@ type BodySpeechToTextV1SpeechToTextPostWebhookMetadataAnyOf = {
6813
6465
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
6814
6466
  * OpenAPI spec version: 1.0
6815
6467
  */
6816
-
6817
6468
  /**
6818
- * Optional metadata to be included in the webhook response. This should be a JSON string representing an object with a maximum depth of 2 levels and maximum size of 16KB. Useful for tracking internal IDs, job references, or other contextual information.
6469
+ * Redact entities from the transcript text. Accepts the same format as entity_detection: 'all', a category ('pii', 'phi'), or specific entity types. Must be a subset of entity_detection. When redaction is enabled, the entities field will not be returned. Usage of this parameter will incur an additional 30% surcharge on the base transcription cost.
6819
6470
  */
6820
- type BodySpeechToTextV1SpeechToTextPostWebhookMetadata = string | BodySpeechToTextV1SpeechToTextPostWebhookMetadataAnyOf | null;
6471
+ type BodySpeechToTextV1SpeechToTextPostEntityRedaction = string | string[] | null;
6821
6472
 
6822
6473
  /**
6823
6474
  * Generated by orval v7.9.0 🍺
@@ -6830,7 +6481,7 @@ type BodySpeechToTextV1SpeechToTextPostWebhookMetadata = string | BodySpeechToTe
6830
6481
  interface BodySpeechToTextV1SpeechToTextPost {
6831
6482
  /** The ID of the model to use for transcription. */
6832
6483
  model_id: BodySpeechToTextV1SpeechToTextPostModelId;
6833
- /** The file to transcribe. 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 3.0GB. */
6484
+ /** 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 3.0GB. */
6834
6485
  file?: BodySpeechToTextV1SpeechToTextPostFile;
6835
6486
  /** 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. */
6836
6487
  language_code?: BodySpeechToTextV1SpeechToTextPostLanguageCode;
@@ -6848,8 +6499,13 @@ interface BodySpeechToTextV1SpeechToTextPost {
6848
6499
  additional_formats?: AdditionalFormats;
6849
6500
  /** 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. */
6850
6501
  file_format?: BodySpeechToTextV1SpeechToTextPostFileFormat;
6851
- /** 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. */
6502
+ /**
6503
+ * 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.
6504
+ * @deprecated
6505
+ */
6852
6506
  cloud_storage_url?: BodySpeechToTextV1SpeechToTextPostCloudStorageUrl;
6507
+ /** The URL of an audio or video file to transcribe. Supports hosted video or audio files, YouTube video URLs, TikTok video URLs, and other video hosting services. */
6508
+ source_url?: BodySpeechToTextV1SpeechToTextPostSourceUrl;
6853
6509
  /** Whether to send the transcription result to configured speech-to-text webhooks. If set the request will return early without the transcription, which will be delivered later via webhook. */
6854
6510
  webhook?: boolean;
6855
6511
  /** Optional specific webhook ID to send the transcription result to. Only valid when webhook is set to true. If not provided, transcription will be sent to all configured speech-to-text webhooks. */
@@ -6858,15 +6514,21 @@ interface BodySpeechToTextV1SpeechToTextPost {
6858
6514
  temperature?: BodySpeechToTextV1SpeechToTextPostTemperature;
6859
6515
  /** If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. Must be an integer between 0 and 2147483647. */
6860
6516
  seed?: BodySpeechToTextV1SpeechToTextPostSeed;
6861
- /** Whether the audio file contains multiple channels where each channel contains a single speaker. When enabled, each channel will be transcribed independently and the results will be combined. Each word in the response will include a 'channel_index' field indicating which channel it was spoken on. A maximum of 5 channels is supported. */
6517
+ /** Whether the audio file contains multiple channels where each channel contains a single speaker. When enabled, each channel will be transcribed independently and the results will be combined. Each word in the response will include a 'channel_index' field indicating which channel it was spoken on. A maximum of 5 channels is supported. Each channel is billed independently at the full audio duration, so cost scales linearly with the number of channels. */
6862
6518
  use_multi_channel?: boolean;
6863
6519
  /** Optional metadata to be included in the webhook response. This should be a JSON string representing an object with a maximum depth of 2 levels and maximum size of 16KB. Useful for tracking internal IDs, job references, or other contextual information. */
6864
6520
  webhook_metadata?: BodySpeechToTextV1SpeechToTextPostWebhookMetadata;
6865
- /** Detect entities in the transcript. Can be 'all' to detect all entities, a single entity type or category string, or a list of entity types/categories. Categories include 'pii', 'phi', 'pci', 'other', 'offensive_language'. When enabled, detected entities will be returned in the 'entities' field with their text, type, and character positions. Usage of this parameter will incur additional costs. */
6521
+ /** Detect entities in the transcript. Can be 'all' to detect all entities, a single entity type or category string, or a list of entity types/categories. Categories include 'pii', 'phi', 'pci', 'other', 'offensive_language'. When enabled, detected entities will be returned in the 'entities' field with their text, type, and character positions. Usage of this parameter will incur an additional 30% surcharge on the base transcription cost. */
6866
6522
  entity_detection?: BodySpeechToTextV1SpeechToTextPostEntityDetection;
6867
6523
  /** If true, the transcription will not have any filler words, false starts and non-speech sounds. Only supported with scribe_v2 model. */
6868
6524
  no_verbatim?: boolean;
6869
- /** 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 100. 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 additional costs. */
6525
+ /** Whether to detect speaker roles (agent vs customer). Requires diarize=true. Cannot be used with use_multi_channel=true. When enabled, speaker_id values will be 'agent' and 'customer' instead of 'speaker_0', 'speaker_1', etc. Usage incurs an additional 10% surcharge on base transcription cost. */
6526
+ detect_speaker_roles?: boolean;
6527
+ /** Redact entities from the transcript text. Accepts the same format as entity_detection: 'all', a category ('pii', 'phi'), or specific entity types. Must be a subset of entity_detection. When redaction is enabled, the entities field will not be returned. Usage of this parameter will incur an additional 30% surcharge on the base transcription cost. */
6528
+ entity_redaction?: BodySpeechToTextV1SpeechToTextPostEntityRedaction;
6529
+ /** 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. */
6530
+ entity_redaction_mode?: string;
6531
+ /** 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. */
6870
6532
  keyterms?: string[];
6871
6533
  }
6872
6534
 
@@ -7134,7 +6796,7 @@ declare const StreamingSupportedRegions: {
7134
6796
  * The Realtime model used for this session.
7135
6797
 
7136
6798
  */
7137
- type RealtimeSessionCreateRequestGAModel = string | "gpt-realtime" | "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-mini" | "gpt-audio-mini-2025-10-06" | "gpt-audio-mini-2025-12-15";
6799
+ 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";
7138
6800
 
7139
6801
  /**
7140
6802
  * Generated by orval v7.9.0 🍺
@@ -7283,13 +6945,13 @@ interface DeepgramStreamingOptions {
7283
6945
  * { encoding: DeepgramEncoding.linear16 }
7284
6946
  * ```
7285
6947
  */
7286
- encoding?: (typeof ListenV1EncodingParameter)[keyof typeof ListenV1EncodingParameter];
6948
+ encoding?: (typeof V1ListenPostParametersEncoding)[keyof typeof V1ListenPostParametersEncoding];
7287
6949
  /** Sample rate in Hz */
7288
6950
  sampleRate?: number;
7289
6951
  /** Number of audio channels */
7290
6952
  channels?: number;
7291
6953
  /** Language code (BCP-47 format, e.g., 'en', 'en-US', 'es') */
7292
- language?: ListenV1LanguageParameter;
6954
+ language?: string;
7293
6955
  /**
7294
6956
  * Model to use for transcription
7295
6957
  *
@@ -7306,7 +6968,7 @@ interface DeepgramStreamingOptions {
7306
6968
  */
7307
6969
  model?: DeepgramModelCode;
7308
6970
  /** Model version (e.g., 'latest') */
7309
- version?: ListenV1VersionParameter;
6971
+ version?: V1ListenPostParametersVersion;
7310
6972
  /** Enable language detection */
7311
6973
  languageDetection?: boolean;
7312
6974
  /** Enable speaker diarization */
@@ -7854,216 +7516,53 @@ type TranscriptionControllerListV2Params = {
7854
7516
  * Filter items relevant to a specific date in ISO format (YYYY-MM-DD).
7855
7517
  */
7856
7518
  date?: string;
7857
- /**
7858
- * Include items that occurred before the specified date in ISO format.
7859
- */
7860
- before_date?: string;
7861
- /**
7862
- * Filter for items after the specified date. Use with `before_date` for a range. Date in ISO format.
7863
- */
7864
- after_date?: string;
7865
- /**
7866
- * Filter the list based on item status. Accepts multiple values from the predefined list.
7867
- */
7868
- status?: TranscriptionControllerListV2StatusItem[];
7869
- custom_metadata?: {
7870
- [key: string]: unknown;
7871
- };
7872
- /**
7873
- * Filter the list based on the item type. Supports multiple values from the predefined list.
7874
- */
7875
- kind?: TranscriptionControllerListV2KindItem[];
7876
- };
7877
-
7878
- /**
7879
- * Generated by orval v7.9.0 🍺
7880
- * Do not edit manually.
7881
- * Deepgram API Specification
7882
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
7883
-
7884
- * OpenAPI spec version: 1.0.0
7885
- */
7886
- /**
7887
- * Start date of the requested date range. Formats accepted are YYYY-MM-DD, YYYY-MM-DDTHH:MM:SS, or YYYY-MM-DDTHH:MM:SS+HH:MM
7888
- */
7889
- type ManageV1StartDateTimeParameter = string;
7890
-
7891
- /**
7892
- * Generated by orval v7.9.0 🍺
7893
- * Do not edit manually.
7894
- * Deepgram API Specification
7895
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
7896
-
7897
- * OpenAPI spec version: 1.0.0
7898
- */
7899
- /**
7900
- * End date of the requested date range. Formats accepted are YYYY-MM-DD, YYYY-MM-DDTHH:MM:SS, or YYYY-MM-DDTHH:MM:SS+HH:MM
7901
- */
7902
- type ManageV1EndDateTimeParameter = string;
7903
-
7904
- /**
7905
- * Generated by orval v7.9.0 🍺
7906
- * Do not edit manually.
7907
- * Deepgram API Specification
7908
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
7909
-
7910
- * OpenAPI spec version: 1.0.0
7911
- */
7912
- /**
7913
- * Number of results to return per page. Default 10. Range [1,1000]
7914
- */
7915
- type ManageV1LimitParameter = number;
7916
-
7917
- /**
7918
- * Generated by orval v7.9.0 🍺
7919
- * Do not edit manually.
7920
- * Deepgram API Specification
7921
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
7922
-
7923
- * OpenAPI spec version: 1.0.0
7924
- */
7925
- /**
7926
- * Navigate and return the results to retrieve specific portions of information of the response
7927
- */
7928
- type ManageV1PageParameter = number;
7929
-
7930
- /**
7931
- * Generated by orval v7.9.0 🍺
7932
- * Do not edit manually.
7933
- * Deepgram API Specification
7934
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
7935
-
7936
- * OpenAPI spec version: 1.0.0
7937
- */
7938
- /**
7939
- * Filter for requests where a specific accessor was used
7940
- */
7941
- type ManageV1FilterAccessorParameter = string;
7942
-
7943
- /**
7944
- * Generated by orval v7.9.0 🍺
7945
- * Do not edit manually.
7946
- * Deepgram API Specification
7947
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
7948
-
7949
- * OpenAPI spec version: 1.0.0
7950
- */
7951
- /**
7952
- * Filter for a specific request id
7953
- */
7954
- type ManageV1FilterRequestIdParameter = string;
7519
+ /**
7520
+ * Include items that occurred before the specified date in ISO format.
7521
+ */
7522
+ before_date?: string;
7523
+ /**
7524
+ * Filter for items after the specified date. Use with `before_date` for a range. Date in ISO format.
7525
+ */
7526
+ after_date?: string;
7527
+ /**
7528
+ * Filter the list based on item status. Accepts multiple values from the predefined list.
7529
+ */
7530
+ status?: TranscriptionControllerListV2StatusItem[];
7531
+ custom_metadata?: {
7532
+ [key: string]: unknown;
7533
+ };
7534
+ /**
7535
+ * Filter the list based on the item type. Supports multiple values from the predefined list.
7536
+ */
7537
+ kind?: TranscriptionControllerListV2KindItem[];
7538
+ };
7955
7539
 
7956
7540
  /**
7957
7541
  * Generated by orval v7.9.0 🍺
7958
7542
  * Do not edit manually.
7959
- * Deepgram API Specification
7960
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
7961
-
7543
+ * Deepgram API
7544
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
7962
7545
  * OpenAPI spec version: 1.0.0
7963
7546
  */
7964
7547
  /**
7965
7548
  * Deployment type for the requests
7966
7549
  */
7967
- /**
7968
- * ManageV1FilterDeploymentParameter type definition
7969
- */
7970
- /**
7971
- * ManageV1FilterDeploymentParameter type definition
7972
- */
7973
- /**
7974
- * ManageV1FilterDeploymentParameter type definition
7975
- */
7976
- /**
7977
- * ManageV1FilterDeploymentParameter type definition
7978
- */
7979
- /**
7980
- * ManageV1FilterDeploymentParameter type definition
7981
- */
7982
- /**
7983
- * ManageV1FilterDeploymentParameter type definition
7984
- */
7985
- /**
7986
- * ManageV1FilterDeploymentParameter type definition
7987
- */
7988
- /**
7989
- * ManageV1FilterDeploymentParameter type definition
7990
- */
7991
- /**
7992
- * ManageV1FilterDeploymentParameter type definition
7993
- */
7994
- /**
7995
- * ManageV1FilterDeploymentParameter type definition
7996
- */
7997
- /**
7998
- * ManageV1FilterDeploymentParameter type definition
7999
- */
8000
- /**
8001
- * ManageV1FilterDeploymentParameter type definition
8002
- */
8003
- /**
8004
- * ManageV1FilterDeploymentParameter type definition
8005
- */
8006
- /**
8007
- * ManageV1FilterDeploymentParameter type definition
8008
- */
8009
- type ManageV1FilterDeploymentParameter = typeof ManageV1FilterDeploymentParameter[keyof typeof ManageV1FilterDeploymentParameter];
8010
- declare const ManageV1FilterDeploymentParameter: {
7550
+ type V1ProjectsProjectIdRequestsGetParametersDeployment = (typeof V1ProjectsProjectIdRequestsGetParametersDeployment)[keyof typeof V1ProjectsProjectIdRequestsGetParametersDeployment];
7551
+ declare const V1ProjectsProjectIdRequestsGetParametersDeployment: {
8011
7552
  readonly hosted: "hosted";
8012
7553
  readonly beta: "beta";
7554
+ readonly "self-hosted": "self-hosted";
8013
7555
  };
8014
7556
 
8015
7557
  /**
8016
7558
  * Generated by orval v7.9.0 🍺
8017
7559
  * Do not edit manually.
8018
- * Deepgram API Specification
8019
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
8020
-
7560
+ * Deepgram API
7561
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
8021
7562
  * OpenAPI spec version: 1.0.0
8022
7563
  */
8023
- /**
8024
- * ManageV1FilterEndpointParameter type definition
8025
- */
8026
- /**
8027
- * ManageV1FilterEndpointParameter type definition
8028
- */
8029
- /**
8030
- * ManageV1FilterEndpointParameter type definition
8031
- */
8032
- /**
8033
- * ManageV1FilterEndpointParameter type definition
8034
- */
8035
- /**
8036
- * ManageV1FilterEndpointParameter type definition
8037
- */
8038
- /**
8039
- * ManageV1FilterEndpointParameter type definition
8040
- */
8041
- /**
8042
- * ManageV1FilterEndpointParameter type definition
8043
- */
8044
- /**
8045
- * ManageV1FilterEndpointParameter type definition
8046
- */
8047
- /**
8048
- * ManageV1FilterEndpointParameter type definition
8049
- */
8050
- /**
8051
- * ManageV1FilterEndpointParameter type definition
8052
- */
8053
- /**
8054
- * ManageV1FilterEndpointParameter type definition
8055
- */
8056
- /**
8057
- * ManageV1FilterEndpointParameter type definition
8058
- */
8059
- /**
8060
- * ManageV1FilterEndpointParameter type definition
8061
- */
8062
- /**
8063
- * ManageV1FilterEndpointParameter type definition
8064
- */
8065
- type ManageV1FilterEndpointParameter = typeof ManageV1FilterEndpointParameter[keyof typeof ManageV1FilterEndpointParameter];
8066
- declare const ManageV1FilterEndpointParameter: {
7564
+ type V1ProjectsProjectIdRequestsGetParametersEndpoint = (typeof V1ProjectsProjectIdRequestsGetParametersEndpoint)[keyof typeof V1ProjectsProjectIdRequestsGetParametersEndpoint];
7565
+ declare const V1ProjectsProjectIdRequestsGetParametersEndpoint: {
8067
7566
  readonly listen: "listen";
8068
7567
  readonly read: "read";
8069
7568
  readonly speak: "speak";
@@ -8073,58 +7572,15 @@ declare const ManageV1FilterEndpointParameter: {
8073
7572
  /**
8074
7573
  * Generated by orval v7.9.0 🍺
8075
7574
  * Do not edit manually.
8076
- * Deepgram API Specification
8077
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
8078
-
7575
+ * Deepgram API
7576
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
8079
7577
  * OpenAPI spec version: 1.0.0
8080
7578
  */
8081
7579
  /**
8082
7580
  * Method type for the request
8083
7581
  */
8084
- /**
8085
- * ManageV1FilterMethodParameter type definition
8086
- */
8087
- /**
8088
- * ManageV1FilterMethodParameter type definition
8089
- */
8090
- /**
8091
- * ManageV1FilterMethodParameter type definition
8092
- */
8093
- /**
8094
- * ManageV1FilterMethodParameter type definition
8095
- */
8096
- /**
8097
- * ManageV1FilterMethodParameter type definition
8098
- */
8099
- /**
8100
- * ManageV1FilterMethodParameter type definition
8101
- */
8102
- /**
8103
- * ManageV1FilterMethodParameter type definition
8104
- */
8105
- /**
8106
- * ManageV1FilterMethodParameter type definition
8107
- */
8108
- /**
8109
- * ManageV1FilterMethodParameter type definition
8110
- */
8111
- /**
8112
- * ManageV1FilterMethodParameter type definition
8113
- */
8114
- /**
8115
- * ManageV1FilterMethodParameter type definition
8116
- */
8117
- /**
8118
- * ManageV1FilterMethodParameter type definition
8119
- */
8120
- /**
8121
- * ManageV1FilterMethodParameter type definition
8122
- */
8123
- /**
8124
- * ManageV1FilterMethodParameter type definition
8125
- */
8126
- type ManageV1FilterMethodParameter = typeof ManageV1FilterMethodParameter[keyof typeof ManageV1FilterMethodParameter];
8127
- declare const ManageV1FilterMethodParameter: {
7582
+ type V1ProjectsProjectIdRequestsGetParametersMethod = (typeof V1ProjectsProjectIdRequestsGetParametersMethod)[keyof typeof V1ProjectsProjectIdRequestsGetParametersMethod];
7583
+ declare const V1ProjectsProjectIdRequestsGetParametersMethod: {
8128
7584
  readonly sync: "sync";
8129
7585
  readonly async: "async";
8130
7586
  readonly streaming: "streaming";
@@ -8133,55 +7589,12 @@ declare const ManageV1FilterMethodParameter: {
8133
7589
  /**
8134
7590
  * Generated by orval v7.9.0 🍺
8135
7591
  * Do not edit manually.
8136
- * Deepgram API Specification
8137
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
8138
-
7592
+ * Deepgram API
7593
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
8139
7594
  * OpenAPI spec version: 1.0.0
8140
7595
  */
8141
- /**
8142
- * ManageV1FilterStatusParameter type definition
8143
- */
8144
- /**
8145
- * ManageV1FilterStatusParameter type definition
8146
- */
8147
- /**
8148
- * ManageV1FilterStatusParameter type definition
8149
- */
8150
- /**
8151
- * ManageV1FilterStatusParameter type definition
8152
- */
8153
- /**
8154
- * ManageV1FilterStatusParameter type definition
8155
- */
8156
- /**
8157
- * ManageV1FilterStatusParameter type definition
8158
- */
8159
- /**
8160
- * ManageV1FilterStatusParameter type definition
8161
- */
8162
- /**
8163
- * ManageV1FilterStatusParameter type definition
8164
- */
8165
- /**
8166
- * ManageV1FilterStatusParameter type definition
8167
- */
8168
- /**
8169
- * ManageV1FilterStatusParameter type definition
8170
- */
8171
- /**
8172
- * ManageV1FilterStatusParameter type definition
8173
- */
8174
- /**
8175
- * ManageV1FilterStatusParameter type definition
8176
- */
8177
- /**
8178
- * ManageV1FilterStatusParameter type definition
8179
- */
8180
- /**
8181
- * ManageV1FilterStatusParameter type definition
8182
- */
8183
- type ManageV1FilterStatusParameter = typeof ManageV1FilterStatusParameter[keyof typeof ManageV1FilterStatusParameter];
8184
- declare const ManageV1FilterStatusParameter: {
7596
+ type V1ProjectsProjectIdRequestsGetParametersStatus = (typeof V1ProjectsProjectIdRequestsGetParametersStatus)[keyof typeof V1ProjectsProjectIdRequestsGetParametersStatus];
7597
+ declare const V1ProjectsProjectIdRequestsGetParametersStatus: {
8185
7598
  readonly succeeded: "succeeded";
8186
7599
  readonly failed: "failed";
8187
7600
  };
@@ -8189,53 +7602,52 @@ declare const ManageV1FilterStatusParameter: {
8189
7602
  /**
8190
7603
  * Generated by orval v7.9.0 🍺
8191
7604
  * Do not edit manually.
8192
- * Deepgram API Specification
8193
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
8194
-
7605
+ * Deepgram API
7606
+ * Deepgram API - Transcription, TTS, text analysis, and request history endpoints. Filtered from the official Deepgram API spec.
8195
7607
  * OpenAPI spec version: 1.0.0
8196
7608
  */
8197
7609
 
8198
- type ManageV1ProjectsRequestsListParams = {
7610
+ type ListProjectRequestsParams = {
8199
7611
  /**
8200
7612
  * Start date of the requested date range. Formats accepted are YYYY-MM-DD, YYYY-MM-DDTHH:MM:SS, or YYYY-MM-DDTHH:MM:SS+HH:MM
8201
7613
  */
8202
- start?: ManageV1StartDateTimeParameter;
7614
+ start?: string;
8203
7615
  /**
8204
7616
  * End date of the requested date range. Formats accepted are YYYY-MM-DD, YYYY-MM-DDTHH:MM:SS, or YYYY-MM-DDTHH:MM:SS+HH:MM
8205
7617
  */
8206
- end?: ManageV1EndDateTimeParameter;
7618
+ end?: string;
8207
7619
  /**
8208
7620
  * Number of results to return per page. Default 10. Range [1,1000]
8209
7621
  */
8210
- limit?: ManageV1LimitParameter;
7622
+ limit?: number;
8211
7623
  /**
8212
7624
  * Navigate and return the results to retrieve specific portions of information of the response
8213
7625
  */
8214
- page?: ManageV1PageParameter;
7626
+ page?: number;
8215
7627
  /**
8216
7628
  * Filter for requests where a specific accessor was used
8217
7629
  */
8218
- accessor?: ManageV1FilterAccessorParameter;
7630
+ accessor?: string;
8219
7631
  /**
8220
7632
  * Filter for a specific request id
8221
7633
  */
8222
- request_id?: ManageV1FilterRequestIdParameter;
7634
+ request_id?: string;
8223
7635
  /**
8224
7636
  * Filter for requests where a specific deployment was used
8225
7637
  */
8226
- deployment?: ManageV1FilterDeploymentParameter;
7638
+ deployment?: V1ProjectsProjectIdRequestsGetParametersDeployment;
8227
7639
  /**
8228
7640
  * Filter for requests where a specific endpoint was used
8229
7641
  */
8230
- endpoint?: ManageV1FilterEndpointParameter;
7642
+ endpoint?: V1ProjectsProjectIdRequestsGetParametersEndpoint;
8231
7643
  /**
8232
7644
  * Filter for requests where a specific method was used
8233
7645
  */
8234
- method?: ManageV1FilterMethodParameter;
7646
+ method?: V1ProjectsProjectIdRequestsGetParametersMethod;
8235
7647
  /**
8236
7648
  * Filter for requests that succeeded (status code < 300) or failed (status code >=400)
8237
7649
  */
8238
- status?: ManageV1FilterStatusParameter;
7650
+ status?: V1ProjectsProjectIdRequestsGetParametersStatus;
8239
7651
  };
8240
7652
 
8241
7653
  /**
@@ -8449,7 +7861,7 @@ interface ListTranscriptsOptions {
8449
7861
  /** Gladia-specific list options */
8450
7862
  gladia?: Partial<TranscriptionControllerListV2Params>;
8451
7863
  /** Deepgram-specific list options (request history) */
8452
- deepgram?: Partial<ManageV1ProjectsRequestsListParams>;
7864
+ deepgram?: Partial<ListProjectRequestsParams>;
8453
7865
  }
8454
7866
  /**
8455
7867
  * Common transcription options across all providers
@@ -8490,7 +7902,7 @@ interface TranscribeOptions {
8490
7902
  * Code switching configuration (Gladia-specific)
8491
7903
  * @see GladiaCodeSwitchingConfig
8492
7904
  */
8493
- codeSwitchingConfig?: CodeSwitchingConfigDTO;
7905
+ codeSwitchingConfig?: LanguageConfig;
8494
7906
  /** Enable speaker diarization */
8495
7907
  diarization?: boolean;
8496
7908
  /** Expected number of speakers (for diarization) */
@@ -8519,7 +7931,7 @@ interface TranscribeOptions {
8519
7931
  * Deepgram-specific options (passed directly to API)
8520
7932
  * @see https://developers.deepgram.com/reference/listen-file
8521
7933
  */
8522
- deepgram?: Partial<ListenV1MediaTranscribeParams>;
7934
+ deepgram?: Partial<ListenTranscribeParams>;
8523
7935
  /**
8524
7936
  * AssemblyAI-specific options (passed directly to API)
8525
7937
  * @see https://www.assemblyai.com/docs/api-reference/transcripts/submit
@@ -10627,21 +10039,10 @@ interface DetectedEntity {
10627
10039
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
10628
10040
  * OpenAPI spec version: 1.0
10629
10041
  */
10630
-
10631
- type SpeechToTextChunkResponseModelAdditionalFormatsAnyOfItem = AdditionalFormatResponseModel | null;
10632
-
10633
- /**
10634
- * Generated by orval v7.9.0 🍺
10635
- * Do not edit manually.
10636
- * ElevenLabs Speech-to-Text API
10637
- * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
10638
- * OpenAPI spec version: 1.0
10639
- */
10640
-
10641
10042
  /**
10642
- * Requested additional formats of the transcript.
10043
+ * The start time of the word or sound in seconds.
10643
10044
  */
10644
- type SpeechToTextChunkResponseModelAdditionalFormats = SpeechToTextChunkResponseModelAdditionalFormatsAnyOfItem[] | null;
10045
+ type SpeechToTextWordResponseModelStart = number | null;
10645
10046
 
10646
10047
  /**
10647
10048
  * Generated by orval v7.9.0 🍺
@@ -10651,9 +10052,9 @@ type SpeechToTextChunkResponseModelAdditionalFormats = SpeechToTextChunkResponse
10651
10052
  * OpenAPI spec version: 1.0
10652
10053
  */
10653
10054
  /**
10654
- * The channel index this transcript belongs to (for multichannel audio).
10055
+ * The end time of the word or sound in seconds.
10655
10056
  */
10656
- type SpeechToTextChunkResponseModelChannelIndex = number | null;
10057
+ type SpeechToTextWordResponseModelEnd = number | null;
10657
10058
 
10658
10059
  /**
10659
10060
  * Generated by orval v7.9.0 🍺
@@ -10662,11 +10063,15 @@ type SpeechToTextChunkResponseModelChannelIndex = number | null;
10662
10063
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
10663
10064
  * OpenAPI spec version: 1.0
10664
10065
  */
10665
-
10666
10066
  /**
10667
- * List of detected entities with their text, type, and character positions in the transcript.
10067
+ * The type of the word or sound. 'audio_event' is used for non-word sounds like laughter or footsteps.
10668
10068
  */
10669
- type SpeechToTextChunkResponseModelEntities = DetectedEntity[] | null;
10069
+ type SpeechToTextWordResponseModelType = (typeof SpeechToTextWordResponseModelType)[keyof typeof SpeechToTextWordResponseModelType];
10070
+ declare const SpeechToTextWordResponseModelType: {
10071
+ readonly word: "word";
10072
+ readonly spacing: "spacing";
10073
+ readonly audio_event: "audio_event";
10074
+ };
10670
10075
 
10671
10076
  /**
10672
10077
  * Generated by orval v7.9.0 🍺
@@ -10676,9 +10081,9 @@ type SpeechToTextChunkResponseModelEntities = DetectedEntity[] | null;
10676
10081
  * OpenAPI spec version: 1.0
10677
10082
  */
10678
10083
  /**
10679
- * The transcription ID of the response.
10084
+ * Unique identifier for the speaker of this word.
10680
10085
  */
10681
- type SpeechToTextChunkResponseModelTranscriptionId = string | null;
10086
+ type SpeechToTextWordResponseModelSpeakerId = string | null;
10682
10087
 
10683
10088
  /**
10684
10089
  * Generated by orval v7.9.0 🍺
@@ -10688,9 +10093,9 @@ type SpeechToTextChunkResponseModelTranscriptionId = string | null;
10688
10093
  * OpenAPI spec version: 1.0
10689
10094
  */
10690
10095
  /**
10691
- * The end time of the character in seconds.
10096
+ * The start time of the character in seconds.
10692
10097
  */
10693
- type SpeechToTextCharacterResponseModelEnd = number | null;
10098
+ type SpeechToTextCharacterResponseModelStart = number | null;
10694
10099
 
10695
10100
  /**
10696
10101
  * Generated by orval v7.9.0 🍺
@@ -10700,9 +10105,9 @@ type SpeechToTextCharacterResponseModelEnd = number | null;
10700
10105
  * OpenAPI spec version: 1.0
10701
10106
  */
10702
10107
  /**
10703
- * The start time of the character in seconds.
10108
+ * The end time of the character in seconds.
10704
10109
  */
10705
- type SpeechToTextCharacterResponseModelStart = number | null;
10110
+ type SpeechToTextCharacterResponseModelEnd = number | null;
10706
10111
 
10707
10112
  /**
10708
10113
  * Generated by orval v7.9.0 🍺
@@ -10741,10 +10146,26 @@ type SpeechToTextWordResponseModelCharacters = SpeechToTextCharacterResponseMode
10741
10146
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
10742
10147
  * OpenAPI spec version: 1.0
10743
10148
  */
10149
+
10744
10150
  /**
10745
- * The end time of the word or sound in seconds.
10151
+ * Word-level detail of the transcription with timing information.
10746
10152
  */
10747
- type SpeechToTextWordResponseModelEnd = number | null;
10153
+ interface SpeechToTextWordResponseModel {
10154
+ /** The word or sound that was transcribed. */
10155
+ text: string;
10156
+ /** The start time of the word or sound in seconds. */
10157
+ start?: SpeechToTextWordResponseModelStart;
10158
+ /** The end time of the word or sound in seconds. */
10159
+ end?: SpeechToTextWordResponseModelEnd;
10160
+ /** The type of the word or sound. 'audio_event' is used for non-word sounds like laughter or footsteps. */
10161
+ type: SpeechToTextWordResponseModelType;
10162
+ /** Unique identifier for the speaker of this word. */
10163
+ speaker_id?: SpeechToTextWordResponseModelSpeakerId;
10164
+ /** The log of the probability with which this word was predicted. Logprobs are in range [-infinity, 0], higher logprobs indicate a higher confidence the model has in its predictions. */
10165
+ logprob: number;
10166
+ /** The characters that make up the word and their timing information. */
10167
+ characters?: SpeechToTextWordResponseModelCharacters;
10168
+ }
10748
10169
 
10749
10170
  /**
10750
10171
  * Generated by orval v7.9.0 🍺
@@ -10754,9 +10175,9 @@ type SpeechToTextWordResponseModelEnd = number | null;
10754
10175
  * OpenAPI spec version: 1.0
10755
10176
  */
10756
10177
  /**
10757
- * Unique identifier for the speaker of this word.
10178
+ * The channel index this transcript belongs to (for multichannel audio).
10758
10179
  */
10759
- type SpeechToTextWordResponseModelSpeakerId = string | null;
10180
+ type SpeechToTextChunkResponseModelChannelIndex = number | null;
10760
10181
 
10761
10182
  /**
10762
10183
  * Generated by orval v7.9.0 🍺
@@ -10765,10 +10186,21 @@ type SpeechToTextWordResponseModelSpeakerId = string | null;
10765
10186
  * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
10766
10187
  * OpenAPI spec version: 1.0
10767
10188
  */
10189
+
10190
+ type SpeechToTextChunkResponseModelAdditionalFormatsAnyOfItem = AdditionalFormatResponseModel | null;
10191
+
10768
10192
  /**
10769
- * The start time of the word or sound in seconds.
10193
+ * Generated by orval v7.9.0 🍺
10194
+ * Do not edit manually.
10195
+ * ElevenLabs Speech-to-Text API
10196
+ * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
10197
+ * OpenAPI spec version: 1.0
10770
10198
  */
10771
- type SpeechToTextWordResponseModelStart = number | null;
10199
+
10200
+ /**
10201
+ * Requested additional formats of the transcript.
10202
+ */
10203
+ type SpeechToTextChunkResponseModelAdditionalFormats = SpeechToTextChunkResponseModelAdditionalFormatsAnyOfItem[] | null;
10772
10204
 
10773
10205
  /**
10774
10206
  * Generated by orval v7.9.0 🍺
@@ -10778,14 +10210,9 @@ type SpeechToTextWordResponseModelStart = number | null;
10778
10210
  * OpenAPI spec version: 1.0
10779
10211
  */
10780
10212
  /**
10781
- * The type of the word or sound. 'audio_event' is used for non-word sounds like laughter or footsteps.
10213
+ * The transcription ID of the response.
10782
10214
  */
10783
- type SpeechToTextWordResponseModelType = (typeof SpeechToTextWordResponseModelType)[keyof typeof SpeechToTextWordResponseModelType];
10784
- declare const SpeechToTextWordResponseModelType: {
10785
- readonly word: "word";
10786
- readonly spacing: "spacing";
10787
- readonly audio_event: "audio_event";
10788
- };
10215
+ type SpeechToTextChunkResponseModelTranscriptionId = string | null;
10789
10216
 
10790
10217
  /**
10791
10218
  * Generated by orval v7.9.0 🍺
@@ -10796,24 +10223,21 @@ declare const SpeechToTextWordResponseModelType: {
10796
10223
  */
10797
10224
 
10798
10225
  /**
10799
- * Word-level detail of the transcription with timing information.
10226
+ * List of detected entities with their text, type, and character positions in the transcript.
10800
10227
  */
10801
- interface SpeechToTextWordResponseModel {
10802
- /** The word or sound that was transcribed. */
10803
- text: string;
10804
- /** The start time of the word or sound in seconds. */
10805
- start?: SpeechToTextWordResponseModelStart;
10806
- /** The end time of the word or sound in seconds. */
10807
- end?: SpeechToTextWordResponseModelEnd;
10808
- /** The type of the word or sound. 'audio_event' is used for non-word sounds like laughter or footsteps. */
10809
- type: SpeechToTextWordResponseModelType;
10810
- /** Unique identifier for the speaker of this word. */
10811
- speaker_id?: SpeechToTextWordResponseModelSpeakerId;
10812
- /** The log of the probability with which this word was predicted. Logprobs are in range [-infinity, 0], higher logprobs indicate a higher confidence the model has in its predictions. */
10813
- logprob: number;
10814
- /** The characters that make up the word and their timing information. */
10815
- characters?: SpeechToTextWordResponseModelCharacters;
10816
- }
10228
+ type SpeechToTextChunkResponseModelEntities = DetectedEntity[] | null;
10229
+
10230
+ /**
10231
+ * Generated by orval v7.9.0 🍺
10232
+ * Do not edit manually.
10233
+ * ElevenLabs Speech-to-Text API
10234
+ * ElevenLabs Speech-to-Text API - Batch and realtime transcription endpoints. Filtered from the official ElevenLabs API spec.
10235
+ * OpenAPI spec version: 1.0
10236
+ */
10237
+ /**
10238
+ * The duration of the audio that was transcribed in seconds.
10239
+ */
10240
+ type SpeechToTextChunkResponseModelAudioDurationSecs = number | null;
10817
10241
 
10818
10242
  /**
10819
10243
  * Generated by orval v7.9.0 🍺
@@ -10843,6 +10267,8 @@ interface SpeechToTextChunkResponseModel {
10843
10267
  transcription_id?: SpeechToTextChunkResponseModelTranscriptionId;
10844
10268
  /** List of detected entities with their text, type, and character positions in the transcript. */
10845
10269
  entities?: SpeechToTextChunkResponseModelEntities;
10270
+ /** The duration of the audio that was transcribed in seconds. */
10271
+ audio_duration_secs?: SpeechToTextChunkResponseModelAudioDurationSecs;
10846
10272
  }
10847
10273
 
10848
- export { type CustomSpellingConfigDTO as $, type AssemblyAIStreamingOptions as A, type AudioToLlmListDTOError as B, type CallbackConfig as C, type DeepgramStreamingOptions as D, type AudioToLlmResultDTO as E, type FileResponse as F, type GladiaStreamingOptions as G, type CallbackConfigDto as H, CallbackMethodEnum as I, type CallbackTranscriptionErrorPayload as J, type CallbackTranscriptionErrorPayloadCustomMetadata as K, type ListTranscriptsOptions as L, type MessagesConfig as M, type NamedEntityRecognitionDTO as N, CallbackTranscriptionErrorPayloadEvent as O, type PreProcessingConfig as P, type CallbackTranscriptionSuccessPayload as Q, type RealtimeProcessingConfig as R, type StreamingOptions as S, type TranscribeOptions as T, type UnifiedTranscriptResponse as U, type CallbackTranscriptionSuccessPayloadCustomMetadata as V, type WordDTO as W, CallbackTranscriptionSuccessPayloadEvent as X, type ChapterizationDTOError as Y, type ChapterizationDTOResults as Z, type CodeSwitchingConfigDTO as _, type StreamingCallbacks as a, type CustomFormattingRequestBodyCustomFormatting as a$, 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$1 as aU, type ContentSafetyLabel as aV, type ContentSafetyLabelResult as aW, type ContentSafetyLabelsResult as aX, type ContentSafetyLabelsResultSeverityScoreSummary as aY, type ContentSafetyLabelsResultSummary as aZ, type CustomFormattingRequestBody as a_, type InitTranscriptionRequest as aa, type InitTranscriptionRequestCustomMetadata as ab, type ModerationDTO as ac, type ModerationDTOError as ad, type NamedEntityRecognitionDTOError as ae, type NamesConsistencyDTO as af, type NamesConsistencyDTOError as ag, type PreRecordedRequestParamsResponse as ah, type PreRecordedResponseCustomMetadata as ai, type PreRecordedResponseFile as aj, PreRecordedResponseKind as ak, type PreRecordedResponsePostSessionMetadata as al, type PreRecordedResponseRequestParams as am, type PreRecordedResponseResult as an, PreRecordedResponseStatus as ao, type SentencesDTO as ap, type SentencesDTOError as aq, type SentimentAnalysisDTOError as ar, type SpeakerReidentificationDTO as as, type SpeakerReidentificationDTOError as at, type StreamingRequest as au, type StreamingRequestCustomMetadata as av, type StructuredDataExtractionConfigDTO as aw, type StructuredDataExtractionDTO as ax, type StructuredDataExtractionDTOError as ay, type SubtitleDTO as az, type StreamingSession as b, type TranscriptOptionalParamsSpeechUnderstandingRequest as b$, 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 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 ListenV1MeasurementsParameter 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 CreateTranscriptionRequestModel as d9, type ManageV1PageParameter as dA, ManageV1FilterEndpointParameter as dB, ManageV1FilterMethodParameter as dC, type SharedTopics as dD, type SharedIntents as dE, type SharedSentiments as dF, type SharedCallbackParameter as dG, SharedCallbackMethodParameter as dH, type SharedSentimentParameter as dI, type SharedSummarizeParameter as dJ, type SharedTagParameter as dK, type SharedTopicsParameter as dL, type SharedCustomTopicParameter as dM, SharedCustomTopicModeParameter as dN, type SharedIntentsParameter as dO, type SharedCustomIntentParameter as dP, SharedCustomIntentModeParameter as dQ, type SharedMipOptOutParameter as dR, type ListenV1DetectEntitiesParameter as dS, type ListenV1DetectLanguageParameter as dT, type ListenV1DiarizeParameter as dU, type ListenV1DictationParameter as dV, ListenV1EncodingParameter as dW, type ListenV1FillerWordsParameter as dX, type ListenV1KeytermParameter as dY, type ListenV1KeywordsParameter as dZ, type ListenV1LanguageParameter as d_, type CreateTranscriptionRequestStream as da, CreateTranscriptionRequestTimestampGranularitiesItem as db, type CreateTranscriptionResponseDiarizedJson as dc, CreateTranscriptionResponseDiarizedJsonTask as dd, type CreateTranscriptionResponseDiarizedJsonUsage as de, type CreateTranscriptionResponseJson as df, type CreateTranscriptionResponseJsonLogprobsItem as dg, type CreateTranscriptionResponseJsonUsage as dh, type CreateTranscriptionResponseVerboseJson as di, type TranscriptTextUsageDuration as dj, TranscriptTextUsageDurationType as dk, type TranscriptTextUsageTokensInputTokenDetails as dl, TranscriptTextUsageTokensType as dm, type TranscriptionChunkingStrategy as dn, type TranscriptionChunkingStrategyAnyOf 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 ManageV1FilterAccessorParameter as dx, ManageV1FilterDeploymentParameter as dy, type ManageV1LimitParameter as dz, StreamingSupportedBitDepthEnum as e, type AutoChaptersResult as e$, type ListenV1MediaTranscribeParams as e0, type ListenV1ModelParameter as e1, type ListenV1MultichannelParameter as e2, type ListenV1NumeralsParameter as e3, type ListenV1ParagraphsParameter as e4, type ListenV1ProfanityFilterParameter as e5, type ListenV1PunctuateParameter as e6, type ListenV1RedactParameter as e7, ListenV1RedactParameterOneOfItem as e8, type ListenV1ReplaceParameter as e9, type ListenV1UtterancesParameter as eA, type ListenV1VersionParameter as eB, type ManageV1EndDateTimeParameter as eC, type ManageV1FilterRequestIdParameter as eD, ManageV1FilterStatusParameter as eE, type ManageV1ProjectsRequestsListParams as eF, type ManageV1StartDateTimeParameter as eG, type SharedExtraParameter as eH, type SharedIntentsResults as eI, type SharedIntentsResultsIntents as eJ, type SharedIntentsResultsIntentsSegmentsItem as eK, type SharedIntentsResultsIntentsSegmentsItemIntentsItem as eL, type SharedSentimentsAverage as eM, type SharedSentimentsSegmentsItem as eN, type SharedTopicsResults as eO, type SharedTopicsResultsTopics as eP, type SharedTopicsResultsTopicsSegmentsItem as eQ, type SharedTopicsResultsTopicsSegmentsItemTopicsItem as eR, JobType as eS, type AlignmentConfig as eT, type TranscriptionConfig as eU, type TrackingData as eV, type OutputConfig as eW, OperatingPoint as eX, type AudioEventItem as eY, type AudioEventSummary as eZ, type AudioEventSummaryItem as e_, type ListenV1ResponseMetadata as ea, type ListenV1ResponseMetadataIntentsInfo as eb, type ListenV1ResponseMetadataModelInfo as ec, type ListenV1ResponseMetadataSentimentInfo as ed, type ListenV1ResponseMetadataSummaryInfo as ee, type ListenV1ResponseMetadataTopicsInfo as ef, type ListenV1ResponseResults as eg, type ListenV1ResponseResultsChannels as eh, type ListenV1ResponseResultsChannelsItem as ei, type ListenV1ResponseResultsChannelsItemAlternativesItem as ej, type ListenV1ResponseResultsChannelsItemAlternativesItemEntitiesItem as ek, type ListenV1ResponseResultsChannelsItemAlternativesItemParagraphs as el, type ListenV1ResponseResultsChannelsItemAlternativesItemParagraphsParagraphsItem as em, type ListenV1ResponseResultsChannelsItemAlternativesItemParagraphsParagraphsItemSentencesItem as en, type ListenV1ResponseResultsChannelsItemAlternativesItemSummariesItem as eo, type ListenV1ResponseResultsChannelsItemAlternativesItemTopicsItem as ep, type ListenV1ResponseResultsChannelsItemAlternativesItemWordsItem as eq, type ListenV1ResponseResultsChannelsItemSearchItem as er, type ListenV1ResponseResultsChannelsItemSearchItemHitsItem as es, type ListenV1ResponseResultsSummary as et, type ListenV1ResponseResultsUtterances as eu, type ListenV1ResponseResultsUtterancesItem as ev, type ListenV1ResponseResultsUtterancesItemWordsItem as ew, type ListenV1SearchParameter as ex, type ListenV1SmartFormatParameter as ey, type ListenV1UttSplitParameter as ez, StreamingSupportedSampleRateEnum as f, type BodySpeechToTextV1SpeechToTextPostFile as f$, type AutoChaptersResultError as f0, AutoChaptersResultErrorType as f1, type Chapter as f2, type JobInfo as f3, type LanguageIdentificationResult as f4, type LanguageIdentificationResultAlternative as f5, LanguageIdentificationResultError as f6, type LanguageIdentificationResultItem as f7, type LanguagePackInfo as f8, LanguagePackInfoWritingDirection as f9, type TopicDetectionError as fA, TopicDetectionErrorType as fB, type TopicDetectionResult as fC, type TopicDetectionSegment as fD, type TopicDetectionSegmentTopic as fE, type TopicDetectionSummary as fF, type TopicDetectionSummaryOverall as fG, type TrackingDataDetails as fH, type TranscriptionConfigAdditionalVocabItem as fI, TranscriptionConfigDiarization as fJ, TranscriptionConfigMaxDelayMode as fK, type TranscriptionConfigPunctuationOverrides as fL, type TranscriptionConfigSpeakerDiarizationConfig as fM, type TranscriptionConfigTranscriptFilteringConfig as fN, type TranscriptionConfigTranscriptFilteringConfigReplacementsItem as fO, type TranslationError as fP, TranslationErrorType as fQ, type TranslationSentence as fR, type WrittenFormRecognitionResult as fS, WrittenFormRecognitionResultType as fT, type SpeechToTextChunkResponseModel as fU, type AdditionalFormatResponseModel as fV, type AdditionalFormats as fW, type BodySpeechToTextV1SpeechToTextPost as fX, type BodySpeechToTextV1SpeechToTextPostCloudStorageUrl as fY, type BodySpeechToTextV1SpeechToTextPostDiarizationThreshold as fZ, type BodySpeechToTextV1SpeechToTextPostEntityDetection as f_, type OutputConfigSrtOverrides as fa, type RecognitionAlternative as fb, type RecognitionDisplay as fc, RecognitionDisplayDirection as fd, type RecognitionMetadata as fe, type RecognitionResult as ff, RecognitionResultAttachesTo as fg, RecognitionResultType as fh, type RetrieveTranscriptResponse as fi, type RetrieveTranscriptResponseAudioEventSummary as fj, type RetrieveTranscriptResponseAudioEventSummaryChannels as fk, type RetrieveTranscriptResponseTranslations as fl, type SentimentAnalysisError as fm, SentimentAnalysisErrorType as fn, type SentimentAnalysisResult as fo, type SentimentAnalysisResultSentimentAnalysis as fp, type SentimentChannelSummary as fq, type SentimentSegment as fr, type SentimentSpeakerSummary as fs, type SentimentSummary as ft, type SentimentSummaryDetail as fu, type SpokenFormRecognitionResult as fv, SpokenFormRecognitionResultType as fw, type SummarizationError as fx, SummarizationErrorType as fy, type SummarizationResult as fz, StreamingSupportedModels as g, type DeepgramExtendedData as g$, BodySpeechToTextV1SpeechToTextPostFileFormat as g0, type BodySpeechToTextV1SpeechToTextPostLanguageCode as g1, BodySpeechToTextV1SpeechToTextPostModelId as g2, type BodySpeechToTextV1SpeechToTextPostNumSpeakers as g3, type BodySpeechToTextV1SpeechToTextPostSeed as g4, type BodySpeechToTextV1SpeechToTextPostTemperature as g5, BodySpeechToTextV1SpeechToTextPostTimestampsGranularity as g6, type BodySpeechToTextV1SpeechToTextPostWebhookId as g7, type BodySpeechToTextV1SpeechToTextPostWebhookMetadata as g8, type BodySpeechToTextV1SpeechToTextPostWebhookMetadataAnyOf as g9, type SpeechToTextChunkResponseModelAdditionalFormatsAnyOfItem as gA, type SpeechToTextChunkResponseModelChannelIndex as gB, type SpeechToTextChunkResponseModelEntities as gC, type SpeechToTextChunkResponseModelTranscriptionId as gD, type SpeechToTextWordResponseModel as gE, type SpeechToTextWordResponseModelCharacters as gF, type SpeechToTextWordResponseModelEnd as gG, type SpeechToTextWordResponseModelSpeakerId as gH, type SpeechToTextWordResponseModelStart as gI, SpeechToTextWordResponseModelType as gJ, type SrtExportOptions as gK, SrtExportOptionsFormat as gL, type SrtExportOptionsMaxCharactersPerLine as gM, type SrtExportOptionsMaxSegmentChars as gN, type SrtExportOptionsMaxSegmentDurationS as gO, type SrtExportOptionsSegmentOnSilenceLongerThanS as gP, type TxtExportOptions as gQ, TxtExportOptionsFormat as gR, type TxtExportOptionsMaxCharactersPerLine as gS, type TxtExportOptionsMaxSegmentChars as gT, type TxtExportOptionsMaxSegmentDurationS as gU, type TxtExportOptionsSegmentOnSilenceLongerThanS as gV, type SpeechmaticsOperatingPoint as gW, type TranscriptionModel as gX, type TranscriptionLanguage as gY, type AssemblyAIExtendedData as gZ, type GladiaExtendedData as g_, type DetectedEntity as ga, type DocxExportOptions as gb, DocxExportOptionsFormat as gc, type DocxExportOptionsMaxSegmentChars as gd, type DocxExportOptionsMaxSegmentDurationS as ge, type DocxExportOptionsSegmentOnSilenceLongerThanS as gf, type ExportOptions as gg, type HtmlExportOptions as gh, HtmlExportOptionsFormat as gi, type HtmlExportOptionsMaxSegmentChars as gj, type HtmlExportOptionsMaxSegmentDurationS as gk, type HtmlExportOptionsSegmentOnSilenceLongerThanS as gl, type PdfExportOptions as gm, PdfExportOptionsFormat as gn, type PdfExportOptionsMaxSegmentChars as go, type PdfExportOptionsMaxSegmentDurationS as gp, type PdfExportOptionsSegmentOnSilenceLongerThanS as gq, type SegmentedJsonExportOptions as gr, SegmentedJsonExportOptionsFormat as gs, type SegmentedJsonExportOptionsMaxSegmentChars as gt, type SegmentedJsonExportOptionsMaxSegmentDurationS as gu, type SegmentedJsonExportOptionsSegmentOnSilenceLongerThanS as gv, type SpeechToTextCharacterResponseModel as gw, type SpeechToTextCharacterResponseModelEnd as gx, type SpeechToTextCharacterResponseModelStart as gy, type SpeechToTextChunkResponseModelAdditionalFormats as gz, type LanguageConfig as h, type ElevenLabsExtendedData as h0, type ProviderExtendedDataMap as h1, type StreamingProvider as h2, type BatchOnlyProvider as h3, type SessionStatus as h4, type Speaker as h5, type Word as h6, type Utterance as h7, type TranscriptionStatus as h8, type TranscriptMetadata as h9, type StreamingWord as hA, type StreamingForceEndpoint as hB, type TranscriptData as ha, type ListTranscriptsResponse as hb, type ProviderRawResponseMap as hc, type StreamEventType as hd, type SpeechEvent as he, type TranslationEvent as hf, type SentimentEvent as hg, type EntityEvent as hh, type SummarizationEvent as hi, type ChapterizationEvent as hj, type AudioAckEvent as hk, type LifecycleEvent as hl, type AudioChunk as hm, type RawWebSocketMessage as hn, type AssemblyAIUpdateConfiguration as ho, type OpenAIStreamingOptions as hp, type SonioxStreamingOptions as hq, type ElevenLabsStreamingOptions as hr, type ProviderStreamingOptions as hs, type StreamingOptionsForProvider as ht, type TranscribeStreamParams as hu, type BeginEvent as hv, type TurnEvent as hw, type TerminationEvent as hx, type ErrorEvent as hy, type StreamingEventMessage 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, StreamingSupportedRegions as t, type AddonErrorDTO as u, type AudioToLlmDTO as v, type AudioToLlmDTOError as w, type AudioToLlmDTOResults as x, type AudioToLlmListConfigDTO as y, type AudioToLlmListDTO as z };
10274
+ export { type CustomSpellingConfigDTO as $, type AssemblyAIStreamingOptions as A, type AudioToLlmListDTO as B, type CallbackConfig as C, type DeepgramStreamingOptions as D, type AudioToLlmListDTOError as E, type FileResponse as F, type GladiaStreamingOptions as G, type AudioToLlmResultDTO as H, type CallbackConfigDto as I, CallbackMethodEnum as J, type CallbackTranscriptionErrorPayload as K, type ListTranscriptsOptions as L, type MessagesConfig as M, type NamedEntityRecognitionDTO as N, type CallbackTranscriptionErrorPayloadCustomMetadata as O, type PreProcessingConfig as P, CallbackTranscriptionErrorPayloadEvent as Q, type RealtimeProcessingConfig as R, type StreamingOptions as S, type TranscribeOptions as T, type UnifiedTranscriptResponse as U, type CallbackTranscriptionSuccessPayload as V, type WordDTO as W, type CallbackTranscriptionSuccessPayloadCustomMetadata as X, CallbackTranscriptionSuccessPayloadEvent as Y, type ChapterizationDTOError as Z, type ChapterizationDTOResults as _, type StreamingCallbacks as a, type ContentSafetyLabelsResultSummary as a$, 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 StructuredDataExtractionDTOError as aA, type SubtitleDTO as aB, type SubtitlesConfigDTO as aC, SubtitlesFormatEnum as aD, SubtitlesStyleEnum as aE, type SummarizationConfigDTO as aF, type SummarizationDTOError as aG, SummaryTypesEnum as aH, TranscriptionControllerListV2KindItem as aI, type TranscriptionControllerListV2Params as aJ, TranscriptionControllerListV2StatusItem as aK, type TranscriptionResultDTO as aL, type TranslationConfigDTO as aM, type TranslationDTOError as aN, TranslationModelEnum as aO, type TranslationResultDTO as aP, type TranslationResultDTOError as aQ, TranscriptStatus as aR, type TranscriptWord as aS, AudioIntelligenceModelStatus as aT, type AutoHighlightResult as aU, type AutoHighlightsResult as aV, type Chapter$1 as aW, type ContentSafetyLabel as aX, type ContentSafetyLabelResult as aY, type ContentSafetyLabelsResult as aZ, type ContentSafetyLabelsResultSeverityScoreSummary as a_, type InitTranscriptionRequest as aa, type InitTranscriptionRequestCustomMetadata as ab, type ModerationDTO as ac, type ModerationDTOError as ad, type NamedEntityRecognitionDTOError as ae, type NamesConsistencyDTO as af, type NamesConsistencyDTOError as ag, type PiiRedactionConfigDTO as ah, PiiRedactionConfigDTOProcessedTextType as ai, PiiRedactionEntityTypeEnum as aj, type PreRecordedRequestParamsResponse as ak, type PreRecordedResponseCustomMetadata as al, type PreRecordedResponseFile as am, PreRecordedResponseKind as an, type PreRecordedResponsePostSessionMetadata as ao, type PreRecordedResponseRequestParams as ap, type PreRecordedResponseResult as aq, PreRecordedResponseStatus as ar, type SentencesDTO as as, type SentencesDTOError as at, type SentimentAnalysisDTOError as au, type SpeakerReidentificationDTO as av, type SpeakerReidentificationDTOError as aw, type StreamingRequest as ax, type StreamingRequestCustomMetadata as ay, type StructuredDataExtractionDTO as az, type StreamingSession as b, type TranscriptOptionalParamsSpeakerOptions as b$, type CustomFormattingRequestBody as b0, type CustomFormattingRequestBodyCustomFormatting as b1, type CustomFormattingResponse as b2, type CustomFormattingResponseCustomFormatting as b3, type CustomFormattingResponseCustomFormattingMapping as b4, type Entity as b5, EntityType as b6, type ListTranscriptsParams as b7, PiiPolicy as b8, RedactPiiAudioQuality as b9, type TranscriptAutoHighlightsResult as bA, type TranscriptChapters as bB, type TranscriptConfidence as bC, type TranscriptContentSafety as bD, type TranscriptContentSafetyLabels as bE, type TranscriptCustomSpelling as bF, type TranscriptCustomSpellingProperty as bG, type TranscriptCustomTopics as bH, type TranscriptDisfluencies as bI, type TranscriptDomain as bJ, type TranscriptEntities as bK, type TranscriptEntityDetection as bL, type TranscriptFilterProfanity as bM, type TranscriptFormatText as bN, type TranscriptIabCategories as bO, type TranscriptIabCategoriesResult as bP, TranscriptLanguageCode as bQ, type TranscriptLanguageCodes as bR, type TranscriptLanguageConfidence as bS, type TranscriptLanguageConfidenceThreshold as bT, type TranscriptLanguageDetection as bU, type TranscriptLanguageDetectionOptions as bV, type TranscriptMultichannel as bW, type TranscriptOptionalParamsLanguageDetectionOptions as bX, type TranscriptOptionalParamsRedactPiiAudioOptions as bY, TranscriptOptionalParamsRedactPiiAudioOptionsOverrideAudioRedactionMethod as bZ, TranscriptOptionalParamsRemoveAudioTags as b_, Sentiment as ba, type SentimentAnalysisResult$1 as bb, type SentimentAnalysisResultChannel as bc, type SentimentAnalysisResultSpeaker as bd, type SeverityScoreSummary as be, type SpeakerIdentificationRequestBody as bf, type SpeakerIdentificationRequestBodySpeakerIdentification as bg, SpeakerIdentificationRequestBodySpeakerIdentificationSpeakerType as bh, type SpeakerIdentificationRequestBodySpeakerIdentificationSpeakersItems as bi, type SpeakerIdentificationResponse as bj, type SpeakerIdentificationResponseSpeakerIdentification as bk, type SpeakerIdentificationResponseSpeakerIdentificationMapping as bl, type SpeechModel as bm, SubstitutionPolicy as bn, SummaryModel as bo, SummaryType as bp, type Timestamp as bq, type TopicDetectionModelResult as br, type TopicDetectionModelResultSummary as bs, type TopicDetectionResult$1 as bt, type TopicDetectionResultLabelsItems as bu, type Transcript as bv, type TranscriptAudioDuration as bw, type TranscriptAudioEndAt as bx, type TranscriptAudioStartFrom as by, type TranscriptAutoChapters as bz, type StreamEvent as c, type TranscriptionCustomProperties as c$, type TranscriptOptionalParamsSpeechUnderstanding as c0, type TranscriptOptionalParamsSpeechUnderstandingRequest as c1, type TranscriptParams as c2, type TranscriptParamsDomain as c3, type TranscriptParamsLanguageCode as c4, type TranscriptParamsLanguageCodes as c5, type TranscriptParamsRedactPiiSub as c6, type TranscriptParamsRemoveAudioTags as c7, type TranscriptParamsSpeakersExpected as c8, type TranscriptParamsSpeechThreshold as c9, type TranscriptTranslatedTexts as cA, type TranscriptUtterance as cB, type TranscriptUtteranceChannel as cC, type TranscriptUtteranceTranslatedTexts as cD, type TranscriptUtterances as cE, type TranscriptWebhookAuthHeaderName as cF, type TranscriptWebhookStatusCode as cG, type TranscriptWebhookUrl as cH, type TranscriptWordChannel as cI, type TranscriptWordSpeaker as cJ, type TranscriptWords as cK, type TranslationRequestBody as cL, type TranslationRequestBodyTranslation as cM, type TranslationResponse as cN, type TranslationResponseTranslation as cO, type StreamingUpdateConfiguration as cP, type Transcription as cQ, type EntityError as cR, Status as cS, type EntityReference as cT, type DiarizationProperties as cU, type DiarizationSpeakersProperties as cV, LanguageIdentificationMode as cW, type LanguageIdentificationProperties as cX, type LanguageIdentificationPropertiesSpeechModelMapping as cY, ProfanityFilterMode as cZ, PunctuationMode as c_, type TranscriptParamsWebhookAuthHeaderName as ca, type TranscriptParamsWebhookAuthHeaderValue as cb, type TranscriptPunctuate as cc, type TranscriptRedactPiiAudio as cd, type TranscriptRedactPiiAudioOptions as ce, TranscriptRedactPiiAudioOptionsOverrideAudioRedactionMethod as cf, type TranscriptRedactPiiAudioQuality as cg, type TranscriptRedactPiiPolicies as ch, TranscriptRemoveAudioTags as ci, type TranscriptRemoveAudioTagsProperty as cj, type TranscriptSentimentAnalysis as ck, type TranscriptSentimentAnalysisResults as cl, type TranscriptSpeakerLabels as cm, type TranscriptSpeakersExpected as cn, type TranscriptSpeechModel as co, type TranscriptSpeechModels as cp, type TranscriptSpeechThreshold as cq, type TranscriptSpeechUnderstanding as cr, type TranscriptSpeechUnderstandingRequest as cs, type TranscriptSpeechUnderstandingResponse as ct, type TranscriptSpeedBoost as cu, type TranscriptSummary as cv, type TranscriptSummaryModel as cw, type TranscriptSummaryType as cx, type TranscriptText as cy, type TranscriptThrottled as cz, StreamingSupportedEncodingEnum as d, type SharedIntentsResultsIntents as d$, type TranscriptionLinks as d0, type TranscriptionProperties as d1, type TranscriptTextUsageTokens as d2, type TranscriptionSegment as d3, type RealtimeSessionCreateRequestGAModel as d4, RealtimeTranscriptionSessionCreateRequestTurnDetectionType as d5, RealtimeTranscriptionSessionCreateRequestInputAudioFormat as d6, AudioResponseFormat as d7, type CreateTranscription200One as d8, type CreateTranscriptionRequest as d9, type SharedSentiments as dA, type ListProjectRequestsParams as dB, type ListenTranscribeParams as dC, type ListenV1ResponseMetadata as dD, type ListenV1ResponseMetadataIntentsInfo as dE, type ListenV1ResponseMetadataModelInfo as dF, type ListenV1ResponseMetadataSentimentInfo as dG, type ListenV1ResponseMetadataSummaryInfo as dH, type ListenV1ResponseMetadataTopicsInfo as dI, type ListenV1ResponseResults as dJ, type ListenV1ResponseResultsChannels as dK, type ListenV1ResponseResultsChannelsItems as dL, type ListenV1ResponseResultsChannelsItemsAlternativesItems as dM, type ListenV1ResponseResultsChannelsItemsAlternativesItemsEntitiesItems as dN, type ListenV1ResponseResultsChannelsItemsAlternativesItemsParagraphs as dO, type ListenV1ResponseResultsChannelsItemsAlternativesItemsParagraphsParagraphsItems as dP, type ListenV1ResponseResultsChannelsItemsAlternativesItemsParagraphsParagraphsItemsSentencesItems as dQ, type ListenV1ResponseResultsChannelsItemsAlternativesItemsSummariesItems as dR, type ListenV1ResponseResultsChannelsItemsAlternativesItemsTopicsItems as dS, type ListenV1ResponseResultsChannelsItemsAlternativesItemsWordsItems as dT, type ListenV1ResponseResultsChannelsItemsSearchItems as dU, type ListenV1ResponseResultsChannelsItemsSearchItemsHitsItems as dV, type ListenV1ResponseResultsSummary as dW, type ListenV1ResponseResultsUtterances as dX, type ListenV1ResponseResultsUtterancesItems as dY, type ListenV1ResponseResultsUtterancesItemsWordsItems as dZ, type SharedIntentsResults as d_, type CreateTranscriptionRequestChunkingStrategy as da, type CreateTranscriptionRequestChunkingStrategyAnyOf as db, type CreateTranscriptionRequestModel as dc, type CreateTranscriptionRequestStream as dd, CreateTranscriptionRequestTimestampGranularitiesItem as de, type CreateTranscriptionResponseDiarizedJson as df, CreateTranscriptionResponseDiarizedJsonTask as dg, type CreateTranscriptionResponseDiarizedJsonUsage as dh, type CreateTranscriptionResponseJson as di, type CreateTranscriptionResponseJsonLogprobsItem as dj, type CreateTranscriptionResponseJsonUsage as dk, type CreateTranscriptionResponseVerboseJson as dl, type TranscriptTextUsageDuration as dm, TranscriptTextUsageDurationType as dn, type TranscriptTextUsageTokensInputTokenDetails as dp, TranscriptTextUsageTokensType as dq, type TranscriptionDiarizedSegment as dr, TranscriptionDiarizedSegmentType as ds, TranscriptionInclude as dt, type TranscriptionWord as du, type VadConfig as dv, VadConfigType as dw, type ListenV1Response as dx, type SharedTopics as dy, type SharedIntents as dz, StreamingSupportedBitDepthEnum as e, type RetrieveTranscriptResponseAudioEventSummaryChannels as e$, type SharedIntentsResultsIntentsSegmentsItems as e0, type SharedIntentsResultsIntentsSegmentsItemsIntentsItems as e1, type SharedSentimentsAverage as e2, type SharedSentimentsSegmentsItems as e3, type SharedTopicsResults as e4, type SharedTopicsResultsTopics as e5, type SharedTopicsResultsTopicsSegmentsItems as e6, type SharedTopicsResultsTopicsSegmentsItemsTopicsItems as e7, V1ListenPostParametersCallbackMethod as e8, type V1ListenPostParametersCustomIntent as e9, type TrackingData as eA, type OutputConfig as eB, OperatingPoint as eC, type AudioEventItem as eD, type AudioEventSummary as eE, type AudioEventSummaryItem as eF, type AutoChaptersResult as eG, type AutoChaptersResultError as eH, AutoChaptersResultErrorType as eI, type Chapter as eJ, type JobInfo as eK, type LanguageIdentificationResult as eL, type LanguageIdentificationResultAlternative as eM, LanguageIdentificationResultError as eN, type LanguageIdentificationResultItem as eO, type LanguagePackInfo as eP, LanguagePackInfoWritingDirection as eQ, type OutputConfigSrtOverrides as eR, type RecognitionAlternative as eS, type RecognitionDisplay as eT, RecognitionDisplayDirection as eU, type RecognitionMetadata as eV, type RecognitionResult as eW, RecognitionResultAttachesTo as eX, RecognitionResultType as eY, type RetrieveTranscriptResponse as eZ, type RetrieveTranscriptResponseAudioEventSummary as e_, V1ListenPostParametersCustomIntentMode as ea, type V1ListenPostParametersCustomTopic as eb, V1ListenPostParametersCustomTopicMode as ec, type V1ListenPostParametersDetectLanguage as ed, V1ListenPostParametersEncoding as ee, type V1ListenPostParametersExtra as ef, type V1ListenPostParametersKeywords as eg, type V1ListenPostParametersModel as eh, V1ListenPostParametersModel0 as ei, type V1ListenPostParametersRedact as ej, type V1ListenPostParametersRedact1 as ek, V1ListenPostParametersRedactSchemaOneOf1Items as el, type V1ListenPostParametersReplace as em, type V1ListenPostParametersSearch as en, type V1ListenPostParametersSummarize as eo, V1ListenPostParametersSummarize0 as ep, type V1ListenPostParametersTag as eq, type V1ListenPostParametersVersion as er, V1ListenPostParametersVersion0 as es, V1ProjectsProjectIdRequestsGetParametersDeployment as et, V1ProjectsProjectIdRequestsGetParametersEndpoint as eu, V1ProjectsProjectIdRequestsGetParametersMethod as ev, V1ProjectsProjectIdRequestsGetParametersStatus as ew, JobType as ex, type AlignmentConfig as ey, type TranscriptionConfig as ez, StreamingSupportedSampleRateEnum as f, HtmlExportOptionsFormat as f$, type RetrieveTranscriptResponseTranslations as f0, type SentimentAnalysisError as f1, SentimentAnalysisErrorType as f2, type SentimentAnalysisResult as f3, type SentimentAnalysisResultSentimentAnalysis as f4, type SentimentChannelSummary as f5, type SentimentSegment as f6, type SentimentSpeakerSummary as f7, type SentimentSummary as f8, type SentimentSummaryDetail as f9, type AdditionalFormatResponseModel as fA, type AdditionalFormats as fB, type BodySpeechToTextV1SpeechToTextPost as fC, type BodySpeechToTextV1SpeechToTextPostCloudStorageUrl as fD, type BodySpeechToTextV1SpeechToTextPostDiarizationThreshold as fE, type BodySpeechToTextV1SpeechToTextPostEntityDetection as fF, type BodySpeechToTextV1SpeechToTextPostEntityRedaction as fG, type BodySpeechToTextV1SpeechToTextPostFile as fH, BodySpeechToTextV1SpeechToTextPostFileFormat as fI, type BodySpeechToTextV1SpeechToTextPostLanguageCode as fJ, BodySpeechToTextV1SpeechToTextPostModelId as fK, type BodySpeechToTextV1SpeechToTextPostNumSpeakers as fL, type BodySpeechToTextV1SpeechToTextPostSeed as fM, type BodySpeechToTextV1SpeechToTextPostSourceUrl as fN, type BodySpeechToTextV1SpeechToTextPostTemperature as fO, BodySpeechToTextV1SpeechToTextPostTimestampsGranularity as fP, type BodySpeechToTextV1SpeechToTextPostWebhookId as fQ, type BodySpeechToTextV1SpeechToTextPostWebhookMetadata as fR, type BodySpeechToTextV1SpeechToTextPostWebhookMetadataAnyOf as fS, type DetectedEntity as fT, type DocxExportOptions as fU, DocxExportOptionsFormat as fV, type DocxExportOptionsMaxSegmentChars as fW, type DocxExportOptionsMaxSegmentDurationS as fX, type DocxExportOptionsSegmentOnSilenceLongerThanS as fY, type ExportOptions as fZ, type HtmlExportOptions as f_, type SpokenFormRecognitionResult as fa, SpokenFormRecognitionResultType as fb, type SummarizationError as fc, SummarizationErrorType as fd, type SummarizationResult as fe, type TopicDetectionError as ff, TopicDetectionErrorType as fg, type TopicDetectionResult as fh, type TopicDetectionSegment as fi, type TopicDetectionSegmentTopic as fj, type TopicDetectionSummary as fk, type TopicDetectionSummaryOverall as fl, type TrackingDataDetails as fm, type TranscriptionConfigAdditionalVocabItem as fn, TranscriptionConfigDiarization as fo, TranscriptionConfigMaxDelayMode as fp, type TranscriptionConfigPunctuationOverrides as fq, type TranscriptionConfigSpeakerDiarizationConfig as fr, type TranscriptionConfigTranscriptFilteringConfig as fs, type TranscriptionConfigTranscriptFilteringConfigReplacementsItem as ft, type TranslationError as fu, TranslationErrorType as fv, type TranslationSentence as fw, type WrittenFormRecognitionResult as fx, WrittenFormRecognitionResultType as fy, type SpeechToTextChunkResponseModel as fz, StreamingSupportedModels as g, type EntityEvent as g$, type HtmlExportOptionsMaxSegmentChars as g0, type HtmlExportOptionsMaxSegmentDurationS as g1, type HtmlExportOptionsSegmentOnSilenceLongerThanS as g2, type PdfExportOptions as g3, PdfExportOptionsFormat as g4, type PdfExportOptionsMaxSegmentChars as g5, type PdfExportOptionsMaxSegmentDurationS as g6, type PdfExportOptionsSegmentOnSilenceLongerThanS as g7, type SegmentedJsonExportOptions as g8, SegmentedJsonExportOptionsFormat as g9, type TxtExportOptionsMaxCharactersPerLine as gA, type TxtExportOptionsMaxSegmentChars as gB, type TxtExportOptionsMaxSegmentDurationS as gC, type TxtExportOptionsSegmentOnSilenceLongerThanS as gD, type SpeechmaticsOperatingPoint as gE, type TranscriptionModel as gF, type TranscriptionLanguage as gG, type AssemblyAIExtendedData as gH, type GladiaExtendedData as gI, type DeepgramExtendedData as gJ, type ElevenLabsExtendedData as gK, type ProviderExtendedDataMap as gL, type StreamingProvider as gM, type BatchOnlyProvider as gN, type SessionStatus as gO, type Speaker as gP, type Word as gQ, type Utterance as gR, type TranscriptionStatus as gS, type TranscriptMetadata as gT, type TranscriptData as gU, type ListTranscriptsResponse as gV, type ProviderRawResponseMap as gW, type StreamEventType as gX, type SpeechEvent as gY, type TranslationEvent as gZ, type SentimentEvent as g_, type SegmentedJsonExportOptionsMaxSegmentChars as ga, type SegmentedJsonExportOptionsMaxSegmentDurationS as gb, type SegmentedJsonExportOptionsSegmentOnSilenceLongerThanS as gc, type SpeechToTextCharacterResponseModel as gd, type SpeechToTextCharacterResponseModelEnd as ge, type SpeechToTextCharacterResponseModelStart as gf, type SpeechToTextChunkResponseModelAdditionalFormats as gg, type SpeechToTextChunkResponseModelAdditionalFormatsAnyOfItem as gh, type SpeechToTextChunkResponseModelAudioDurationSecs as gi, type SpeechToTextChunkResponseModelChannelIndex as gj, type SpeechToTextChunkResponseModelEntities as gk, type SpeechToTextChunkResponseModelTranscriptionId as gl, type SpeechToTextWordResponseModel as gm, type SpeechToTextWordResponseModelCharacters as gn, type SpeechToTextWordResponseModelEnd as go, type SpeechToTextWordResponseModelSpeakerId as gp, type SpeechToTextWordResponseModelStart as gq, SpeechToTextWordResponseModelType as gr, type SrtExportOptions as gs, SrtExportOptionsFormat as gt, type SrtExportOptionsMaxCharactersPerLine as gu, type SrtExportOptionsMaxSegmentChars as gv, type SrtExportOptionsMaxSegmentDurationS as gw, type SrtExportOptionsSegmentOnSilenceLongerThanS as gx, type TxtExportOptions as gy, TxtExportOptionsFormat as gz, type LanguageConfig as h, type SummarizationEvent as h0, type ChapterizationEvent as h1, type AudioAckEvent as h2, type LifecycleEvent as h3, type AudioChunk as h4, type RawWebSocketMessage as h5, type AssemblyAIUpdateConfiguration as h6, type OpenAIStreamingOptions as h7, type SonioxStreamingOptions as h8, type ElevenLabsStreamingOptions as h9, type ProviderStreamingOptions as ha, type StreamingOptionsForProvider as hb, type TranscribeStreamParams as hc, type BeginEvent as hd, type TurnEvent as he, type TerminationEvent as hf, type ErrorEvent as hg, type StreamingEventMessage as hh, type StreamingWord as hi, type StreamingForceEndpoint as hj, 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 };