assemblyai 3.0.1 → 3.1.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +74 -48
- package/dist/index.d.ts +1 -1
- package/dist/index.esm.js +83 -11
- package/dist/index.js +83 -11
- package/dist/services/files/index.d.ts +2 -2
- package/dist/services/lemur/index.d.ts +5 -5
- package/dist/services/transcripts/index.d.ts +28 -7
- package/dist/types/asyncapi.generated.d.ts +20 -17
- package/dist/types/deprecated.d.ts +63 -0
- package/dist/types/files/index.d.ts +2 -2
- package/dist/types/index.d.ts +7 -6
- package/dist/types/openapi.generated.d.ts +223 -206
- package/dist/types/services/abstractions.d.ts +3 -3
- package/dist/types/services/index.d.ts +1 -1
- package/dist/types/transcripts/index.d.ts +36 -2
- package/package.json +10 -5
- package/src/index.ts +1 -1
- package/src/services/files/index.ts +2 -2
- package/src/services/lemur/index.ts +8 -8
- package/src/services/transcripts/index.ts +85 -19
- package/src/types/asyncapi.generated.ts +20 -17
- package/src/types/deprecated.ts +78 -0
- package/src/types/files/index.ts +2 -2
- package/src/types/index.ts +7 -6
- package/src/types/openapi.generated.ts +226 -208
- package/src/types/services/abstractions.ts +3 -3
- package/src/types/services/index.ts +1 -1
- package/src/types/transcripts/index.ts +43 -2
- package/src/utils/.gitkeep +0 -0
|
@@ -14,7 +14,7 @@ type OneOf<T extends any[]> = T extends [infer Only]
|
|
|
14
14
|
: never;
|
|
15
15
|
|
|
16
16
|
/**
|
|
17
|
-
* @description
|
|
17
|
+
* @description Either success, or unavailable in the rare case that the model failed
|
|
18
18
|
* @enum {string}
|
|
19
19
|
*/
|
|
20
20
|
export type AudioIntelligenceModelStatus = "success" | "unavailable";
|
|
@@ -34,13 +34,13 @@ export type AutoHighlightResult = {
|
|
|
34
34
|
};
|
|
35
35
|
|
|
36
36
|
/**
|
|
37
|
-
* @description An array of results for the Key Phrases model, if it
|
|
37
|
+
* @description An array of results for the Key Phrases model, if it is enabled.
|
|
38
38
|
* See [Key phrases](https://www.assemblyai.com/docs/Models/key_phrases) for more information.
|
|
39
39
|
*/
|
|
40
40
|
export type AutoHighlightsResult = {
|
|
41
41
|
/** @description A temporally-sequential array of Key Phrases */
|
|
42
42
|
results: AutoHighlightResult[];
|
|
43
|
-
}
|
|
43
|
+
};
|
|
44
44
|
|
|
45
45
|
/** @description Chapter of the audio file */
|
|
46
46
|
export type Chapter = {
|
|
@@ -72,7 +72,7 @@ export type ContentSafetyLabel = {
|
|
|
72
72
|
};
|
|
73
73
|
|
|
74
74
|
export type ContentSafetyLabelResult = {
|
|
75
|
-
/** @description An array of
|
|
75
|
+
/** @description An array of safety labels, one per sensitive topic that was detected in the section */
|
|
76
76
|
labels: ContentSafetyLabel[];
|
|
77
77
|
/** @description The sentence index at which the section ends */
|
|
78
78
|
sentences_idx_end: number;
|
|
@@ -84,128 +84,27 @@ export type ContentSafetyLabelResult = {
|
|
|
84
84
|
timestamp: Timestamp;
|
|
85
85
|
};
|
|
86
86
|
|
|
87
|
+
/**
|
|
88
|
+
* @description An array of results for the Content Moderation model, if it is enabled.
|
|
89
|
+
* See [Content moderation](https://www.assemblyai.com/docs/Models/content_moderation) for more information.
|
|
90
|
+
*/
|
|
87
91
|
export type ContentSafetyLabelsResult = {
|
|
88
92
|
results: ContentSafetyLabelResult[];
|
|
89
93
|
/** @description A summary of the Content Moderation severity results for the entire audio file */
|
|
90
94
|
severity_score_summary: {
|
|
91
95
|
[key: string]: SeverityScoreSummary;
|
|
92
96
|
};
|
|
93
|
-
/** @description
|
|
97
|
+
/** @description The status of the Content Moderation model. Either success, or unavailable in the rare case that the model failed. */
|
|
94
98
|
status: AudioIntelligenceModelStatus;
|
|
95
99
|
/** @description A summary of the Content Moderation confidence results for the entire audio file */
|
|
96
100
|
summary: {
|
|
97
101
|
[key: string]: number;
|
|
98
102
|
};
|
|
99
|
-
} | null;
|
|
100
|
-
|
|
101
|
-
export type CreateRealtimeTemporaryTokenParameters = {
|
|
102
|
-
/** @description The amount of time until the token expires in seconds. */
|
|
103
|
-
expires_in: number;
|
|
104
103
|
};
|
|
105
104
|
|
|
106
|
-
|
|
107
|
-
|
|
108
|
-
|
|
109
|
-
audio_end_at?: number;
|
|
110
|
-
/** @description The point in time, in milliseconds, to begin transcription from in your media file */
|
|
111
|
-
audio_start_from?: number;
|
|
112
|
-
/** @description Enable [Auto Chapters](https://www.assemblyai.com/docs/Models/auto_chapters), can be true or false */
|
|
113
|
-
auto_chapters?: boolean;
|
|
114
|
-
/** @description Whether Key Phrases was enabled in the transcription request, either true or false */
|
|
115
|
-
auto_highlights?: boolean;
|
|
116
|
-
/** @description The word boost parameter value, if provided in the transcription request. */
|
|
117
|
-
boost_param?: TranscriptBoostParam;
|
|
118
|
-
/** @description Enable [Content Moderation](https://www.assemblyai.com/docs/Models/content_moderation), can be true or false */
|
|
119
|
-
content_safety?: boolean;
|
|
120
|
-
/** @description Customize how words are spelled and formatted using to and from values */
|
|
121
|
-
custom_spelling?: TranscriptCustomSpelling[];
|
|
122
|
-
/** @description Whether custom topics was enabled in the transcription request, either true or false */
|
|
123
|
-
custom_topics?: boolean;
|
|
124
|
-
/** @description Transcribe Filler Words, like "umm", in your media file; can be true or false. */
|
|
125
|
-
disfluencies?: boolean;
|
|
126
|
-
/** @description Enable [Dual Channel](https://assemblyai.com/docs/Models/speech_recognition#dual-channel-transcription) transcription, can be true or false. */
|
|
127
|
-
dual_channel?: boolean;
|
|
128
|
-
/** @description Enable [Entity Detection](https://www.assemblyai.com/docs/Models/entity_detection), can be true or false */
|
|
129
|
-
entity_detection?: boolean;
|
|
130
|
-
/** @description Filter profanity from the transcribed text, can be true or false. */
|
|
131
|
-
filter_profanity?: boolean;
|
|
132
|
-
/** @description Enable Text Formatting, can be true or false. */
|
|
133
|
-
format_text?: boolean;
|
|
134
|
-
/** @description Enable [Topic Detection](https://www.assemblyai.com/docs/Models/iab_classification), can be true or false */
|
|
135
|
-
iab_categories?: boolean;
|
|
136
|
-
/**
|
|
137
|
-
* @description The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/Concepts/supported_languages).
|
|
138
|
-
* The default value is 'en_us'.
|
|
139
|
-
*/
|
|
140
|
-
language_code?: TranscriptLanguageCode;
|
|
141
|
-
/** @description Whether [Automatic language detection](https://www.assemblyai.com/docs/Models/speech_recognition#automatic-language-detection) was enabled in the transcription request, either true or false. */
|
|
142
|
-
language_detection?: boolean;
|
|
143
|
-
/** @description Enable Automatic Punctuation, can be true or false. */
|
|
144
|
-
punctuate?: boolean;
|
|
145
|
-
/** @description Redact PII from the transcribed text using the Redact PII model, can be true or false */
|
|
146
|
-
redact_pii?: boolean;
|
|
147
|
-
/** @description Generate a copy of the original media file with spoken PII "beeped" out, can be true or false. See [PII redaction](https://www.assemblyai.com/docs/Models/pii_redaction) for more details. */
|
|
148
|
-
redact_pii_audio?: boolean;
|
|
149
|
-
/**
|
|
150
|
-
* @description Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See [PII redaction](https://www.assemblyai.com/docs/Models/pii_redaction) for more details.
|
|
151
|
-
* @default mp3
|
|
152
|
-
*/
|
|
153
|
-
redact_pii_audio_quality?: string;
|
|
154
|
-
/** @description The list of PII Redaction policies to enable. See [PII redaction](https://www.assemblyai.com/docs/Models/pii_redaction) for more details. */
|
|
155
|
-
redact_pii_policies?: PiiPolicy[];
|
|
156
|
-
/** @description The replacement logic for detected PII, can be "entity_type" or "hash". See [PII redaction](https://www.assemblyai.com/docs/Models/pii_redaction) for more details. */
|
|
157
|
-
redact_pii_sub?: SubstitutionPolicy;
|
|
158
|
-
/** @description Enable [Sentiment Analysis](https://www.assemblyai.com/docs/Models/sentiment_analysis), can be true or false */
|
|
159
|
-
sentiment_analysis?: boolean;
|
|
160
|
-
/** @description Enable [Speaker diarization](https://www.assemblyai.com/docs/Models/speaker_diarization), can be true or false */
|
|
161
|
-
speaker_labels?: boolean;
|
|
162
|
-
/**
|
|
163
|
-
* @description Tells the speaker label model how many speakers it should attempt to identify, up to 10. See [Speaker diarization](https://www.assemblyai.com/docs/Models/speaker_diarization) for more details.
|
|
164
|
-
* @default null
|
|
165
|
-
*/
|
|
166
|
-
speakers_expected?: number | null;
|
|
167
|
-
/**
|
|
168
|
-
* Format: float
|
|
169
|
-
* @description Reject audio files that contain less than this fraction of speech.
|
|
170
|
-
* Valid values are in the range [0, 1] inclusive.
|
|
171
|
-
*
|
|
172
|
-
* @default null
|
|
173
|
-
*/
|
|
174
|
-
speech_threshold?: number | null;
|
|
175
|
-
/** @description Enable [Summarization](https://www.assemblyai.com/docs/Models/summarization), can be true or false */
|
|
176
|
-
summarization?: boolean;
|
|
177
|
-
/**
|
|
178
|
-
* @description The model to summarize the transcript
|
|
179
|
-
* @default informative
|
|
180
|
-
*/
|
|
181
|
-
summary_model?: SummaryModel;
|
|
182
|
-
/**
|
|
183
|
-
* @description The type of summary
|
|
184
|
-
* @default bullets
|
|
185
|
-
*/
|
|
186
|
-
summary_type?: SummaryType;
|
|
187
|
-
/** @description The list of custom topics provided if custom topics was enabled in the transcription request */
|
|
188
|
-
topics?: string[];
|
|
189
|
-
/**
|
|
190
|
-
* @description The header name which should be sent back with webhook calls, if provided in the transcription request.
|
|
191
|
-
* @default null
|
|
192
|
-
*/
|
|
193
|
-
webhook_auth_header_name?: string | null;
|
|
194
|
-
/**
|
|
195
|
-
* @description Defaults to null. Optionally allows a user to specify a header name and value to send back with a webhook call for added security.
|
|
196
|
-
* @default null
|
|
197
|
-
*/
|
|
198
|
-
webhook_auth_header_value?: string | null;
|
|
199
|
-
/** @description The URL to which we send webhooks upon trancription completion, if provided in the transcription request. */
|
|
200
|
-
webhook_url?: string;
|
|
201
|
-
/** @description The list of custom vocabulary to boost transcription probability for, if provided in the transcription request. */
|
|
202
|
-
word_boost?: string[];
|
|
203
|
-
};
|
|
204
|
-
|
|
205
|
-
/** @description The parameters for creating a transcript */
|
|
206
|
-
export type CreateTranscriptParameters = CreateTranscriptOptionalParameters & {
|
|
207
|
-
/** @description The URL of the audio or video file to transcribe. */
|
|
208
|
-
audio_url: string;
|
|
105
|
+
export type CreateRealtimeTemporaryTokenParams = {
|
|
106
|
+
/** @description The amount of time until the token expires in seconds */
|
|
107
|
+
expires_in: number;
|
|
209
108
|
};
|
|
210
109
|
|
|
211
110
|
/** @description A detected entity */
|
|
@@ -262,14 +161,14 @@ export type Error = {
|
|
|
262
161
|
status?: "error";
|
|
263
162
|
};
|
|
264
163
|
|
|
265
|
-
export type
|
|
164
|
+
export type LemurActionItemsParams = LemurBaseParams;
|
|
266
165
|
|
|
267
166
|
export type LemurActionItemsResponse = LemurBaseResponse & {
|
|
268
|
-
/** @description The response generated by LeMUR
|
|
167
|
+
/** @description The response generated by LeMUR */
|
|
269
168
|
response: string;
|
|
270
169
|
};
|
|
271
170
|
|
|
272
|
-
export type
|
|
171
|
+
export type LemurBaseParams = {
|
|
273
172
|
/** @description Context to provide the model. This can be a string or a free-form JSON value. */
|
|
274
173
|
context?: OneOf<
|
|
275
174
|
[
|
|
@@ -280,7 +179,12 @@ export type LemurBaseParameters = {
|
|
|
280
179
|
]
|
|
281
180
|
>;
|
|
282
181
|
final_model?: LemurModel;
|
|
283
|
-
/**
|
|
182
|
+
/**
|
|
183
|
+
* @description Custom formatted transcript data. Maximum size is the context limit of the selected model, which defaults to 100000.
|
|
184
|
+
* Use either transcript_ids or input_text as input into LeMUR.
|
|
185
|
+
*/
|
|
186
|
+
input_text?: string;
|
|
187
|
+
/** @description Max output size in tokens, up to 4000 */
|
|
284
188
|
max_output_size?: number;
|
|
285
189
|
/**
|
|
286
190
|
* Format: float
|
|
@@ -289,8 +193,11 @@ export type LemurBaseParameters = {
|
|
|
289
193
|
* Can be any value between 0.0 and 1.0 inclusive.
|
|
290
194
|
*/
|
|
291
195
|
temperature?: number;
|
|
292
|
-
/**
|
|
293
|
-
|
|
196
|
+
/**
|
|
197
|
+
* @description A list of completed transcripts with text. Up to a maximum of 100 files or 100 hours, whichever is lower.
|
|
198
|
+
* Use either transcript_ids or input_text as input into LeMUR.
|
|
199
|
+
*/
|
|
200
|
+
transcript_ids?: string[];
|
|
294
201
|
};
|
|
295
202
|
|
|
296
203
|
export type LemurBaseResponse = {
|
|
@@ -310,7 +217,7 @@ export type LemurQuestion = {
|
|
|
310
217
|
answer_format?: string;
|
|
311
218
|
/** @description What discrete options to return. Useful for precise responses. Can't be used with answer_format. Example: ["Yes", "No"] */
|
|
312
219
|
answer_options?: string[];
|
|
313
|
-
/** @description Any context about the transcripts you wish to provide. This can be a string
|
|
220
|
+
/** @description Any context about the transcripts you wish to provide. This can be a string or any object. */
|
|
314
221
|
context?: OneOf<
|
|
315
222
|
[
|
|
316
223
|
string,
|
|
@@ -323,44 +230,66 @@ export type LemurQuestion = {
|
|
|
323
230
|
question: string;
|
|
324
231
|
};
|
|
325
232
|
|
|
326
|
-
/** @description An answer generated by LeMUR and its question
|
|
233
|
+
/** @description An answer generated by LeMUR and its question */
|
|
327
234
|
export type LemurQuestionAnswer = {
|
|
328
|
-
/** @description The answer generated by LeMUR
|
|
235
|
+
/** @description The answer generated by LeMUR */
|
|
329
236
|
answer: string;
|
|
330
|
-
/** @description The question for LeMUR to answer
|
|
237
|
+
/** @description The question for LeMUR to answer */
|
|
331
238
|
question: string;
|
|
332
239
|
};
|
|
333
240
|
|
|
334
|
-
export type
|
|
335
|
-
/** @description A list of questions to ask
|
|
241
|
+
export type LemurQuestionAnswerParams = LemurBaseParams & {
|
|
242
|
+
/** @description A list of questions to ask */
|
|
336
243
|
questions: LemurQuestion[];
|
|
337
244
|
};
|
|
338
245
|
|
|
339
246
|
export type LemurQuestionAnswerResponse = LemurBaseResponse & {
|
|
340
|
-
/** @description The answers generated by LeMUR and their questions
|
|
247
|
+
/** @description The answers generated by LeMUR and their questions */
|
|
341
248
|
response: LemurQuestionAnswer[];
|
|
342
249
|
};
|
|
343
250
|
|
|
344
|
-
export type
|
|
251
|
+
export type LemurSummaryParams = LemurBaseParams & {
|
|
345
252
|
/** @description How you want the summary to be returned. This can be any text. Examples: "TLDR", "bullet points" */
|
|
346
253
|
answer_format?: string;
|
|
347
254
|
};
|
|
348
255
|
|
|
349
256
|
export type LemurSummaryResponse = LemurBaseResponse & {
|
|
350
|
-
/** @description The response generated by LeMUR
|
|
257
|
+
/** @description The response generated by LeMUR */
|
|
351
258
|
response: string;
|
|
352
259
|
};
|
|
353
260
|
|
|
354
|
-
export type
|
|
261
|
+
export type LemurTaskParams = LemurBaseParams & {
|
|
355
262
|
/** @description Your text to prompt the model to produce a desired output, including any context you want to pass into the model. */
|
|
356
263
|
prompt: string;
|
|
357
264
|
};
|
|
358
265
|
|
|
359
266
|
export type LemurTaskResponse = LemurBaseResponse & {
|
|
360
|
-
/** @description The response generated by LeMUR
|
|
267
|
+
/** @description The response generated by LeMUR */
|
|
361
268
|
response: string;
|
|
362
269
|
};
|
|
363
270
|
|
|
271
|
+
export type ListTranscriptParams = {
|
|
272
|
+
/** @description Get transcripts that were created after this transcript ID */
|
|
273
|
+
after_id?: string;
|
|
274
|
+
/** @description Get transcripts that were created before this transcript ID */
|
|
275
|
+
before_id?: string;
|
|
276
|
+
/**
|
|
277
|
+
* Format: date
|
|
278
|
+
* @description Only get transcripts created on this date
|
|
279
|
+
*/
|
|
280
|
+
created_on?: string;
|
|
281
|
+
/**
|
|
282
|
+
* Format: int64
|
|
283
|
+
* @description Maximum amount of transcripts to retrieve
|
|
284
|
+
* @default 10
|
|
285
|
+
*/
|
|
286
|
+
limit?: number;
|
|
287
|
+
/** @description Filter by transcript status */
|
|
288
|
+
status?: TranscriptStatus;
|
|
289
|
+
/** @description Only get throttled transcripts, overrides the status filter */
|
|
290
|
+
throttled_only?: boolean;
|
|
291
|
+
};
|
|
292
|
+
|
|
364
293
|
export type PageDetails = {
|
|
365
294
|
current_url: string;
|
|
366
295
|
limit: number;
|
|
@@ -408,11 +337,11 @@ export type PiiPolicy =
|
|
|
408
337
|
| "banking_information";
|
|
409
338
|
|
|
410
339
|
export type PurgeLemurRequestDataResponse = {
|
|
411
|
-
/** @description Whether the request data was deleted
|
|
340
|
+
/** @description Whether the request data was deleted */
|
|
412
341
|
deleted: boolean;
|
|
413
|
-
/** @description The ID of the LeMUR request */
|
|
414
|
-
request_id: string;
|
|
415
342
|
/** @description The ID of the deletion request of the LeMUR request */
|
|
343
|
+
request_id: string;
|
|
344
|
+
/** @description The ID of the LeMUR request to purge the data for */
|
|
416
345
|
request_id_to_purge: string;
|
|
417
346
|
};
|
|
418
347
|
|
|
@@ -445,7 +374,7 @@ export type SentencesResponse = {
|
|
|
445
374
|
/** @enum {unknown} */
|
|
446
375
|
export type Sentiment = "POSITIVE" | "NEUTRAL" | "NEGATIVE";
|
|
447
376
|
|
|
448
|
-
/** @description The result of the sentiment analysis model
|
|
377
|
+
/** @description The result of the sentiment analysis model */
|
|
449
378
|
export type SentimentAnalysisResult = {
|
|
450
379
|
/**
|
|
451
380
|
* Format: double
|
|
@@ -475,7 +404,7 @@ export type SeverityScoreSummary = {
|
|
|
475
404
|
|
|
476
405
|
/**
|
|
477
406
|
* @description The replacement logic for detected PII, can be "entity_type" or "hash". See [PII redaction](https://www.assemblyai.com/docs/Models/pii_redaction) for more details.
|
|
478
|
-
* @enum {string
|
|
407
|
+
* @enum {string}
|
|
479
408
|
*/
|
|
480
409
|
export type SubstitutionPolicy = "entity_type" | "hash";
|
|
481
410
|
|
|
@@ -504,7 +433,7 @@ export type SummaryType =
|
|
|
504
433
|
| "headline"
|
|
505
434
|
| "paragraph";
|
|
506
435
|
|
|
507
|
-
/** @description Timestamp containing a start and end property in milliseconds
|
|
436
|
+
/** @description Timestamp containing a start and end property in milliseconds */
|
|
508
437
|
export type Timestamp = {
|
|
509
438
|
/** @description The end time in milliseconds */
|
|
510
439
|
end: number;
|
|
@@ -512,7 +441,22 @@ export type Timestamp = {
|
|
|
512
441
|
start: number;
|
|
513
442
|
};
|
|
514
443
|
|
|
515
|
-
/**
|
|
444
|
+
/**
|
|
445
|
+
* @description The result of the Topic Detection model, if it is enabled.
|
|
446
|
+
* See [Topic Detection](https://www.assemblyai.com/docs/Models/iab_classification) for more information.
|
|
447
|
+
*/
|
|
448
|
+
export type TopicDetectionModelResult = {
|
|
449
|
+
/** @description An array of results for the Topic Detection model */
|
|
450
|
+
results: TopicDetectionResult[];
|
|
451
|
+
/** @description The status of the Topic Detection model. Either success, or unavailable in the rare case that the model failed. */
|
|
452
|
+
status: AudioIntelligenceModelStatus;
|
|
453
|
+
/** @description The overall relevance of topic to the entire audio file */
|
|
454
|
+
summary: {
|
|
455
|
+
[key: string]: number;
|
|
456
|
+
};
|
|
457
|
+
};
|
|
458
|
+
|
|
459
|
+
/** @description The result of the topic detection model */
|
|
516
460
|
export type TopicDetectionResult = {
|
|
517
461
|
labels?: {
|
|
518
462
|
/** @description The IAB taxonomical label for the label of the detected topic, where > denotes supertopic/subtopic relationship */
|
|
@@ -532,7 +476,7 @@ export type TopicDetectionResult = {
|
|
|
532
476
|
export type Transcript = {
|
|
533
477
|
/**
|
|
534
478
|
* @deprecated
|
|
535
|
-
* @description The acoustic model that was used for the
|
|
479
|
+
* @description The acoustic model that was used for the transcript
|
|
536
480
|
*/
|
|
537
481
|
acoustic_model: string;
|
|
538
482
|
/**
|
|
@@ -540,22 +484,22 @@ export type Transcript = {
|
|
|
540
484
|
* @description The duration of this transcript object's media file, in seconds
|
|
541
485
|
*/
|
|
542
486
|
audio_duration?: number | null;
|
|
543
|
-
/** @description The point in time, in milliseconds, in the file at which the transcription was terminated
|
|
487
|
+
/** @description The point in time, in milliseconds, in the file at which the transcription was terminated */
|
|
544
488
|
audio_end_at?: number | null;
|
|
545
|
-
/** @description The point in time, in milliseconds, in the file at which the transcription was started
|
|
489
|
+
/** @description The point in time, in milliseconds, in the file at which the transcription was started */
|
|
546
490
|
audio_start_from?: number | null;
|
|
547
491
|
/** @description The URL of the media that was transcribed */
|
|
548
492
|
audio_url: string;
|
|
549
|
-
/** @description
|
|
493
|
+
/** @description Whether [Auto Chapters](https://www.assemblyai.com/docs/Models/auto_chapters) is enabled, can be true or false */
|
|
550
494
|
auto_chapters?: boolean | null;
|
|
551
|
-
/** @description Whether Key Phrases
|
|
495
|
+
/** @description Whether Key Phrases is enabled, either true or false */
|
|
552
496
|
auto_highlights: boolean;
|
|
553
497
|
/**
|
|
554
|
-
* @description An array of results for the Key Phrases model, if it
|
|
498
|
+
* @description An array of results for the Key Phrases model, if it is enabled.
|
|
555
499
|
* See [Key phrases](https://www.assemblyai.com/docs/Models/key_phrases) for more information.
|
|
556
500
|
*/
|
|
557
|
-
auto_highlights_result?: AutoHighlightsResult;
|
|
558
|
-
/** @description The word boost parameter value
|
|
501
|
+
auto_highlights_result?: AutoHighlightsResult | null;
|
|
502
|
+
/** @description The word boost parameter value */
|
|
559
503
|
boost_param?: string | null;
|
|
560
504
|
/** @description An array of temporally sequential chapters for the audio file */
|
|
561
505
|
chapters?: Chapter[] | null;
|
|
@@ -564,51 +508,42 @@ export type Transcript = {
|
|
|
564
508
|
* @description The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence)
|
|
565
509
|
*/
|
|
566
510
|
confidence?: number | null;
|
|
567
|
-
/** @description
|
|
511
|
+
/** @description Whether [Content Moderation](https://www.assemblyai.com/docs/Models/content_moderation) is enabled, can be true or false */
|
|
568
512
|
content_safety?: boolean | null;
|
|
569
513
|
/**
|
|
570
|
-
* @description An array of results for the Content Moderation model, if it
|
|
514
|
+
* @description An array of results for the Content Moderation model, if it is enabled.
|
|
571
515
|
* See [Content moderation](https://www.assemblyai.com/docs/Models/content_moderation) for more information.
|
|
572
516
|
*/
|
|
573
|
-
content_safety_labels?: ContentSafetyLabelsResult;
|
|
517
|
+
content_safety_labels?: ContentSafetyLabelsResult | null;
|
|
574
518
|
/** @description Customize how words are spelled and formatted using to and from values */
|
|
575
519
|
custom_spelling?: TranscriptCustomSpelling[] | null;
|
|
576
|
-
/** @description Whether custom topics
|
|
520
|
+
/** @description Whether custom topics is enabled, either true or false */
|
|
577
521
|
custom_topics?: boolean | null;
|
|
578
522
|
/** @description Transcribe Filler Words, like "umm", in your media file; can be true or false */
|
|
579
523
|
disfluencies?: boolean | null;
|
|
580
|
-
/** @description Whether [Dual channel transcription](https://www.assemblyai.com/docs/Models/speech_recognition#dual-channel-transcription)
|
|
524
|
+
/** @description Whether [Dual channel transcription](https://www.assemblyai.com/docs/Models/speech_recognition#dual-channel-transcription) is enabled, either true or false */
|
|
581
525
|
dual_channel?: boolean | null;
|
|
582
526
|
/**
|
|
583
|
-
* @description An array of results for the Entity Detection model, if it
|
|
527
|
+
* @description An array of results for the Entity Detection model, if it is enabled.
|
|
584
528
|
* See [Entity detection](https://www.assemblyai.com/docs/Models/entity_detection) for more information.
|
|
585
529
|
*/
|
|
586
530
|
entities?: Entity[] | null;
|
|
587
|
-
/** @description
|
|
531
|
+
/** @description Whether [Entity Detection](https://www.assemblyai.com/docs/Models/entity_detection) is enabled, can be true or false */
|
|
588
532
|
entity_detection?: boolean | null;
|
|
589
533
|
/** @description Error message of why the transcript failed */
|
|
590
534
|
error?: string;
|
|
591
|
-
/** @description Whether [Profanity Filtering](https://www.assemblyai.com/docs/Models/speech_recognition#profanity-filtering)
|
|
535
|
+
/** @description Whether [Profanity Filtering](https://www.assemblyai.com/docs/Models/speech_recognition#profanity-filtering) is enabled, either true or false */
|
|
592
536
|
filter_profanity?: boolean | null;
|
|
593
|
-
/** @description Whether Text Formatting
|
|
537
|
+
/** @description Whether Text Formatting is enabled, either true or false */
|
|
594
538
|
format_text?: boolean | null;
|
|
595
|
-
/** @description
|
|
539
|
+
/** @description Whether [Topic Detection](https://www.assemblyai.com/docs/Models/iab_classification) is enabled, can be true or false */
|
|
596
540
|
iab_categories?: boolean | null;
|
|
597
541
|
/**
|
|
598
|
-
* @description The result of the Topic Detection model, if it
|
|
542
|
+
* @description The result of the Topic Detection model, if it is enabled.
|
|
599
543
|
* See [Topic Detection](https://www.assemblyai.com/docs/Models/iab_classification) for more information.
|
|
600
544
|
*/
|
|
601
|
-
iab_categories_result?:
|
|
602
|
-
|
|
603
|
-
results: TopicDetectionResult[];
|
|
604
|
-
/** @description Will be either success, or unavailable in the rare case that the Content Moderation model failed. */
|
|
605
|
-
status: AudioIntelligenceModelStatus;
|
|
606
|
-
/** @description The overall relevance of topic to the entire audio file */
|
|
607
|
-
summary: {
|
|
608
|
-
[key: string]: number;
|
|
609
|
-
};
|
|
610
|
-
} | null;
|
|
611
|
-
/** @description The unique identifier of your transcription */
|
|
545
|
+
iab_categories_result?: TopicDetectionModelResult | null;
|
|
546
|
+
/** @description The unique identifier of your transcript */
|
|
612
547
|
id: string;
|
|
613
548
|
/**
|
|
614
549
|
* @description The language of your audio file.
|
|
@@ -616,24 +551,24 @@ export type Transcript = {
|
|
|
616
551
|
* The default value is 'en_us'.
|
|
617
552
|
*/
|
|
618
553
|
language_code?: TranscriptLanguageCode;
|
|
619
|
-
/** @description Whether [Automatic language detection](https://www.assemblyai.com/docs/Models/speech_recognition#automatic-language-detection)
|
|
554
|
+
/** @description Whether [Automatic language detection](https://www.assemblyai.com/docs/Models/speech_recognition#automatic-language-detection) is enabled, either true or false */
|
|
620
555
|
language_detection?: boolean | null;
|
|
621
556
|
/**
|
|
622
557
|
* @deprecated
|
|
623
|
-
* @description The language model that was used for the
|
|
558
|
+
* @description The language model that was used for the transcript
|
|
624
559
|
*/
|
|
625
560
|
language_model: string;
|
|
626
|
-
/** @description Whether Automatic Punctuation
|
|
561
|
+
/** @description Whether Automatic Punctuation is enabled, either true or false */
|
|
627
562
|
punctuate?: boolean | null;
|
|
628
|
-
/** @description Whether [PII Redaction](https://www.assemblyai.com/docs/Models/pii_redaction)
|
|
563
|
+
/** @description Whether [PII Redaction](https://www.assemblyai.com/docs/Models/pii_redaction) is enabled, either true or false */
|
|
629
564
|
redact_pii: boolean;
|
|
630
565
|
/**
|
|
631
|
-
* @description Whether a redacted version of the audio file was generated
|
|
566
|
+
* @description Whether a redacted version of the audio file was generated,
|
|
632
567
|
* either true or false. See [PII redaction](https://www.assemblyai.com/docs/Models/pii_redaction) for more information.
|
|
633
568
|
*/
|
|
634
569
|
redact_pii_audio?: boolean | null;
|
|
635
570
|
/**
|
|
636
|
-
* @description The audio quality of the PII-redacted audio file, if
|
|
571
|
+
* @description The audio quality of the PII-redacted audio file, if redact_pii_audio is enabled.
|
|
637
572
|
* See [PII redaction](https://www.assemblyai.com/docs/Models/pii_redaction) for more information.
|
|
638
573
|
*/
|
|
639
574
|
redact_pii_audio_quality?: string | null;
|
|
@@ -644,16 +579,16 @@ export type Transcript = {
|
|
|
644
579
|
redact_pii_policies?: PiiPolicy[] | null;
|
|
645
580
|
/** @description The replacement logic for detected PII, can be "entity_type" or "hash". See [PII redaction](https://www.assemblyai.com/docs/Models/pii_redaction) for more details. */
|
|
646
581
|
redact_pii_sub?: SubstitutionPolicy;
|
|
647
|
-
/** @description
|
|
582
|
+
/** @description Whether [Sentiment Analysis](https://www.assemblyai.com/docs/Models/sentiment_analysis) is enabled, can be true or false */
|
|
648
583
|
sentiment_analysis?: boolean | null;
|
|
649
584
|
/**
|
|
650
|
-
* @description An array of results for the Sentiment Analysis model, if it
|
|
585
|
+
* @description An array of results for the Sentiment Analysis model, if it is enabled.
|
|
651
586
|
* See [Sentiment analysis](https://www.assemblyai.com/docs/Models/sentiment_analysis) for more information.
|
|
652
587
|
*/
|
|
653
588
|
sentiment_analysis_results?: SentimentAnalysisResult[] | null;
|
|
654
|
-
/** @description
|
|
589
|
+
/** @description Whether [Speaker diarization](https://www.assemblyai.com/docs/Models/speaker_diarization) is enabled, can be true or false */
|
|
655
590
|
speaker_labels?: boolean | null;
|
|
656
|
-
/** @description
|
|
591
|
+
/** @description Tell the speaker label model how many speakers it should attempt to identify, up to 10. See [Speaker diarization](https://www.assemblyai.com/docs/Models/speaker_diarization) for more details. */
|
|
657
592
|
speakers_expected?: number | null;
|
|
658
593
|
/**
|
|
659
594
|
* Format: float
|
|
@@ -663,42 +598,42 @@ export type Transcript = {
|
|
|
663
598
|
speech_threshold?: number | null;
|
|
664
599
|
/**
|
|
665
600
|
* @deprecated
|
|
666
|
-
* @description Whether speed boost
|
|
601
|
+
* @description Whether speed boost is enabled
|
|
667
602
|
*/
|
|
668
603
|
speed_boost?: boolean | null;
|
|
669
|
-
/** @description The status of your
|
|
604
|
+
/** @description The status of your transcript. Possible values are queued, processing, completed, or error. */
|
|
670
605
|
status: TranscriptStatus;
|
|
671
|
-
/** @description Whether [Summarization](https://www.assemblyai.com/docs/Models/summarization)
|
|
606
|
+
/** @description Whether [Summarization](https://www.assemblyai.com/docs/Models/summarization) is enabled, either true or false */
|
|
672
607
|
summarization: boolean;
|
|
673
|
-
/** @description The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/Models/summarization)
|
|
608
|
+
/** @description The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/Models/summarization) is enabled */
|
|
674
609
|
summary?: string | null;
|
|
675
610
|
/**
|
|
676
611
|
* @description The Summarization model used to generate the summary,
|
|
677
|
-
* if [Summarization](https://www.assemblyai.com/docs/Models/summarization)
|
|
612
|
+
* if [Summarization](https://www.assemblyai.com/docs/Models/summarization) is enabled
|
|
678
613
|
*/
|
|
679
614
|
summary_model?: string | null;
|
|
680
|
-
/** @description The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/Models/summarization)
|
|
615
|
+
/** @description The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/Models/summarization) is enabled */
|
|
681
616
|
summary_type?: string | null;
|
|
682
617
|
/** @description The textual transcript of your media file */
|
|
683
618
|
text?: string | null;
|
|
684
619
|
/** @description True while a request is throttled and false when a request is no longer throttled */
|
|
685
620
|
throttled?: boolean | null;
|
|
686
|
-
/** @description The list of custom topics provided if custom topics
|
|
621
|
+
/** @description The list of custom topics provided if custom topics is enabled */
|
|
687
622
|
topics?: string[];
|
|
688
623
|
/**
|
|
689
624
|
* @description When dual_channel or speaker_labels is enabled, a list of turn-by-turn utterance objects.
|
|
690
625
|
* See [Speaker diarization](https://www.assemblyai.com/docs/Models/speaker_diarization) for more information.
|
|
691
626
|
*/
|
|
692
627
|
utterances?: TranscriptUtterance[] | null;
|
|
693
|
-
/** @description Whether webhook authentication details were provided
|
|
628
|
+
/** @description Whether webhook authentication details were provided */
|
|
694
629
|
webhook_auth: boolean;
|
|
695
|
-
/** @description The header name which should be sent back with webhook calls
|
|
630
|
+
/** @description The header name which should be sent back with webhook calls */
|
|
696
631
|
webhook_auth_header_name?: string | null;
|
|
697
|
-
/** @description The status code we received from your server when delivering your webhook, if a webhook URL was provided
|
|
632
|
+
/** @description The status code we received from your server when delivering your webhook, if a webhook URL was provided */
|
|
698
633
|
webhook_status_code?: number | null;
|
|
699
|
-
/** @description The URL to which we send webhooks upon trancription completion
|
|
634
|
+
/** @description The URL to which we send webhooks upon trancription completion */
|
|
700
635
|
webhook_url?: string | null;
|
|
701
|
-
/** @description The list of custom vocabulary to boost transcription probability for
|
|
636
|
+
/** @description The list of custom vocabulary to boost transcription probability for */
|
|
702
637
|
word_boost?: string[];
|
|
703
638
|
/**
|
|
704
639
|
* @description An array of temporally-sequential word objects, one for each word in the transcript.
|
|
@@ -708,7 +643,7 @@ export type Transcript = {
|
|
|
708
643
|
};
|
|
709
644
|
|
|
710
645
|
/**
|
|
711
|
-
* @description The word boost parameter value
|
|
646
|
+
* @description The word boost parameter value
|
|
712
647
|
* @enum {string}
|
|
713
648
|
*/
|
|
714
649
|
export type TranscriptBoostParam = "low" | "default" | "high";
|
|
@@ -726,7 +661,7 @@ export type TranscriptCustomSpelling = {
|
|
|
726
661
|
* The default value is 'en_us'.
|
|
727
662
|
*
|
|
728
663
|
* @default en_us
|
|
729
|
-
* @enum {string
|
|
664
|
+
* @enum {string}
|
|
730
665
|
*/
|
|
731
666
|
export type TranscriptLanguageCode =
|
|
732
667
|
| "en"
|
|
@@ -764,26 +699,103 @@ export type TranscriptListItem = {
|
|
|
764
699
|
status: TranscriptStatus;
|
|
765
700
|
};
|
|
766
701
|
|
|
767
|
-
|
|
768
|
-
|
|
769
|
-
|
|
770
|
-
|
|
771
|
-
|
|
702
|
+
/** @description The parameters for creating a transcript */
|
|
703
|
+
export type TranscriptOptionalParams = {
|
|
704
|
+
/** @description The point in time, in milliseconds, to stop transcribing in your media file */
|
|
705
|
+
audio_end_at?: number;
|
|
706
|
+
/** @description The point in time, in milliseconds, to begin transcribing in your media file */
|
|
707
|
+
audio_start_from?: number;
|
|
708
|
+
/** @description Enable [Auto Chapters](https://www.assemblyai.com/docs/Models/auto_chapters), can be true or false */
|
|
709
|
+
auto_chapters?: boolean;
|
|
710
|
+
/** @description Whether Key Phrases is enabled, either true or false */
|
|
711
|
+
auto_highlights?: boolean;
|
|
712
|
+
/** @description The word boost parameter value */
|
|
713
|
+
boost_param?: TranscriptBoostParam;
|
|
714
|
+
/** @description Enable [Content Moderation](https://www.assemblyai.com/docs/Models/content_moderation), can be true or false */
|
|
715
|
+
content_safety?: boolean;
|
|
716
|
+
/** @description Customize how words are spelled and formatted using to and from values */
|
|
717
|
+
custom_spelling?: TranscriptCustomSpelling[];
|
|
718
|
+
/** @description Whether custom topics is enabled, either true or false */
|
|
719
|
+
custom_topics?: boolean;
|
|
720
|
+
/** @description Transcribe Filler Words, like "umm", in your media file; can be true or false */
|
|
721
|
+
disfluencies?: boolean;
|
|
722
|
+
/** @description Enable [Dual Channel](https://assemblyai.com/docs/Models/speech_recognition#dual-channel-transcription) transcription, can be true or false */
|
|
723
|
+
dual_channel?: boolean;
|
|
724
|
+
/** @description Enable [Entity Detection](https://www.assemblyai.com/docs/Models/entity_detection), can be true or false */
|
|
725
|
+
entity_detection?: boolean;
|
|
726
|
+
/** @description Filter profanity from the transcribed text, can be true or false */
|
|
727
|
+
filter_profanity?: boolean;
|
|
728
|
+
/** @description Enable Text Formatting, can be true or false */
|
|
729
|
+
format_text?: boolean;
|
|
730
|
+
/** @description Enable [Topic Detection](https://www.assemblyai.com/docs/Models/iab_classification), can be true or false */
|
|
731
|
+
iab_categories?: boolean;
|
|
772
732
|
/**
|
|
773
|
-
*
|
|
774
|
-
*
|
|
733
|
+
* @description The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/Concepts/supported_languages).
|
|
734
|
+
* The default value is 'en_us'.
|
|
775
735
|
*/
|
|
776
|
-
|
|
736
|
+
language_code?: TranscriptLanguageCode | null;
|
|
737
|
+
/** @description Whether [Automatic language detection](https://www.assemblyai.com/docs/Models/speech_recognition#automatic-language-detection) is enabled, either true or false */
|
|
738
|
+
language_detection?: boolean;
|
|
739
|
+
/** @description Enable Automatic Punctuation, can be true or false */
|
|
740
|
+
punctuate?: boolean;
|
|
741
|
+
/** @description Redact PII from the transcribed text using the Redact PII model, can be true or false */
|
|
742
|
+
redact_pii?: boolean;
|
|
743
|
+
/** @description Generate a copy of the original media file with spoken PII "beeped" out, can be true or false. See [PII redaction](https://www.assemblyai.com/docs/Models/pii_redaction) for more details. */
|
|
744
|
+
redact_pii_audio?: boolean;
|
|
777
745
|
/**
|
|
778
|
-
*
|
|
779
|
-
* @
|
|
780
|
-
* @default 10
|
|
746
|
+
* @description Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See [PII redaction](https://www.assemblyai.com/docs/Models/pii_redaction) for more details.
|
|
747
|
+
* @default mp3
|
|
781
748
|
*/
|
|
782
|
-
|
|
783
|
-
/** @description
|
|
784
|
-
|
|
785
|
-
/** @description
|
|
786
|
-
|
|
749
|
+
redact_pii_audio_quality?: string;
|
|
750
|
+
/** @description The list of PII Redaction policies to enable. See [PII redaction](https://www.assemblyai.com/docs/Models/pii_redaction) for more details. */
|
|
751
|
+
redact_pii_policies?: PiiPolicy[];
|
|
752
|
+
/** @description The replacement logic for detected PII, can be "entity_type" or "hash". See [PII redaction](https://www.assemblyai.com/docs/Models/pii_redaction) for more details. */
|
|
753
|
+
redact_pii_sub?: SubstitutionPolicy | null;
|
|
754
|
+
/** @description Enable [Sentiment Analysis](https://www.assemblyai.com/docs/Models/sentiment_analysis), can be true or false */
|
|
755
|
+
sentiment_analysis?: boolean;
|
|
756
|
+
/** @description Enable [Speaker diarization](https://www.assemblyai.com/docs/Models/speaker_diarization), can be true or false */
|
|
757
|
+
speaker_labels?: boolean;
|
|
758
|
+
/**
|
|
759
|
+
* @description Tell the speaker label model how many speakers it should attempt to identify, up to 10. See [Speaker diarization](https://www.assemblyai.com/docs/Models/speaker_diarization) for more details.
|
|
760
|
+
* @default null
|
|
761
|
+
*/
|
|
762
|
+
speakers_expected?: number | null;
|
|
763
|
+
/**
|
|
764
|
+
* Format: float
|
|
765
|
+
* @description Reject audio files that contain less than this fraction of speech.
|
|
766
|
+
* Valid values are in the range [0, 1] inclusive.
|
|
767
|
+
*
|
|
768
|
+
* @default null
|
|
769
|
+
*/
|
|
770
|
+
speech_threshold?: number | null;
|
|
771
|
+
/** @description Enable [Summarization](https://www.assemblyai.com/docs/Models/summarization), can be true or false */
|
|
772
|
+
summarization?: boolean;
|
|
773
|
+
/**
|
|
774
|
+
* @description The model to summarize the transcript
|
|
775
|
+
* @default informative
|
|
776
|
+
*/
|
|
777
|
+
summary_model?: SummaryModel;
|
|
778
|
+
/**
|
|
779
|
+
* @description The type of summary
|
|
780
|
+
* @default bullets
|
|
781
|
+
*/
|
|
782
|
+
summary_type?: SummaryType;
|
|
783
|
+
/** @description The list of custom topics provided, if custom topics is enabled */
|
|
784
|
+
topics?: string[];
|
|
785
|
+
/**
|
|
786
|
+
* @description The header name which should be sent back with webhook calls
|
|
787
|
+
* @default null
|
|
788
|
+
*/
|
|
789
|
+
webhook_auth_header_name?: string | null;
|
|
790
|
+
/**
|
|
791
|
+
* @description Specify a header name and value to send back with a webhook call for added security
|
|
792
|
+
* @default null
|
|
793
|
+
*/
|
|
794
|
+
webhook_auth_header_value?: string | null;
|
|
795
|
+
/** @description The URL to which AssemblyAI send webhooks upon trancription completion */
|
|
796
|
+
webhook_url?: string;
|
|
797
|
+
/** @description The list of custom vocabulary to boost transcription probability for */
|
|
798
|
+
word_boost?: string[];
|
|
787
799
|
};
|
|
788
800
|
|
|
789
801
|
export type TranscriptParagraph = {
|
|
@@ -795,6 +807,12 @@ export type TranscriptParagraph = {
|
|
|
795
807
|
words: TranscriptWord[];
|
|
796
808
|
};
|
|
797
809
|
|
|
810
|
+
/** @description The parameters for creating a transcript */
|
|
811
|
+
export type TranscriptParams = TranscriptOptionalParams & {
|
|
812
|
+
/** @description The URL of the audio or video file to transcribe. */
|
|
813
|
+
audio_url: string;
|
|
814
|
+
};
|
|
815
|
+
|
|
798
816
|
export type TranscriptSentence = {
|
|
799
817
|
/** Format: double */
|
|
800
818
|
confidence: number;
|
|
@@ -805,7 +823,7 @@ export type TranscriptSentence = {
|
|
|
805
823
|
};
|
|
806
824
|
|
|
807
825
|
/**
|
|
808
|
-
* @description The status of your
|
|
826
|
+
* @description The status of your transcript. Possible values are queued, processing, completed, or error.
|
|
809
827
|
* @enum {string}
|
|
810
828
|
*/
|
|
811
829
|
export type TranscriptStatus = "queued" | "processing" | "completed" | "error";
|