assemblyai 3.1.0 → 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.
@@ -1,4 +1,4 @@
1
- type FileUploadParameters = string | FileUploadData;
1
+ type FileUploadParams = string | FileUploadData;
2
2
  type FileUploadData =
3
3
  | NodeJS.ReadableStream
4
4
  | ReadableStream
@@ -8,4 +8,4 @@ type FileUploadData =
8
8
  | ArrayBufferLike
9
9
  | Uint8Array;
10
10
 
11
- export type { FileUploadParameters, FileUploadData };
11
+ export type { FileUploadParams, FileUploadData };
@@ -4,3 +4,4 @@ export * from "./realtime";
4
4
  export * from "./services";
5
5
  export * from "./asyncapi.generated";
6
6
  export * from "./openapi.generated";
7
+ export * from "./deprecated";
@@ -102,116 +102,11 @@ export type ContentSafetyLabelsResult = {
102
102
  };
103
103
  };
104
104
 
105
- export type CreateRealtimeTemporaryTokenParameters = {
105
+ export type CreateRealtimeTemporaryTokenParams = {
106
106
  /** @description The amount of time until the token expires in seconds */
107
107
  expires_in: number;
108
108
  };
109
109
 
110
- /** @description The parameters for creating a transcript */
111
- export type CreateTranscriptOptionalParameters = {
112
- /** @description The point in time, in milliseconds, to stop transcribing in your media file */
113
- audio_end_at?: number;
114
- /** @description The point in time, in milliseconds, to begin transcribing in your media file */
115
- audio_start_from?: number;
116
- /** @description Enable [Auto Chapters](https://www.assemblyai.com/docs/Models/auto_chapters), can be true or false */
117
- auto_chapters?: boolean;
118
- /** @description Whether Key Phrases is enabled, either true or false */
119
- auto_highlights?: boolean;
120
- /** @description The word boost parameter value */
121
- boost_param?: TranscriptBoostParam;
122
- /** @description Enable [Content Moderation](https://www.assemblyai.com/docs/Models/content_moderation), can be true or false */
123
- content_safety?: boolean;
124
- /** @description Customize how words are spelled and formatted using to and from values */
125
- custom_spelling?: TranscriptCustomSpelling[];
126
- /** @description Whether custom topics is enabled, either true or false */
127
- custom_topics?: boolean;
128
- /** @description Transcribe Filler Words, like "umm", in your media file; can be true or false */
129
- disfluencies?: boolean;
130
- /** @description Enable [Dual Channel](https://assemblyai.com/docs/Models/speech_recognition#dual-channel-transcription) transcription, can be true or false */
131
- dual_channel?: boolean;
132
- /** @description Enable [Entity Detection](https://www.assemblyai.com/docs/Models/entity_detection), can be true or false */
133
- entity_detection?: boolean;
134
- /** @description Filter profanity from the transcribed text, can be true or false */
135
- filter_profanity?: boolean;
136
- /** @description Enable Text Formatting, can be true or false */
137
- format_text?: boolean;
138
- /** @description Enable [Topic Detection](https://www.assemblyai.com/docs/Models/iab_classification), can be true or false */
139
- iab_categories?: boolean;
140
- /**
141
- * @description The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/Concepts/supported_languages).
142
- * The default value is 'en_us'.
143
- */
144
- language_code?: TranscriptLanguageCode | null;
145
- /** @description Whether [Automatic language detection](https://www.assemblyai.com/docs/Models/speech_recognition#automatic-language-detection) is enabled, either true or false */
146
- language_detection?: boolean;
147
- /** @description Enable Automatic Punctuation, can be true or false */
148
- punctuate?: boolean;
149
- /** @description Redact PII from the transcribed text using the Redact PII model, can be true or false */
150
- redact_pii?: boolean;
151
- /** @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. */
152
- redact_pii_audio?: boolean;
153
- /**
154
- * @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.
155
- * @default mp3
156
- */
157
- redact_pii_audio_quality?: string;
158
- /** @description The list of PII Redaction policies to enable. See [PII redaction](https://www.assemblyai.com/docs/Models/pii_redaction) for more details. */
159
- redact_pii_policies?: PiiPolicy[];
160
- /** @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. */
161
- redact_pii_sub?: SubstitutionPolicy | null;
162
- /** @description Enable [Sentiment Analysis](https://www.assemblyai.com/docs/Models/sentiment_analysis), can be true or false */
163
- sentiment_analysis?: boolean;
164
- /** @description Enable [Speaker diarization](https://www.assemblyai.com/docs/Models/speaker_diarization), can be true or false */
165
- speaker_labels?: boolean;
166
- /**
167
- * @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.
168
- * @default null
169
- */
170
- speakers_expected?: number | null;
171
- /**
172
- * Format: float
173
- * @description Reject audio files that contain less than this fraction of speech.
174
- * Valid values are in the range [0, 1] inclusive.
175
- *
176
- * @default null
177
- */
178
- speech_threshold?: number | null;
179
- /** @description Enable [Summarization](https://www.assemblyai.com/docs/Models/summarization), can be true or false */
180
- summarization?: boolean;
181
- /**
182
- * @description The model to summarize the transcript
183
- * @default informative
184
- */
185
- summary_model?: SummaryModel;
186
- /**
187
- * @description The type of summary
188
- * @default bullets
189
- */
190
- summary_type?: SummaryType;
191
- /** @description The list of custom topics provided, if custom topics is enabled */
192
- topics?: string[];
193
- /**
194
- * @description The header name which should be sent back with webhook calls
195
- * @default null
196
- */
197
- webhook_auth_header_name?: string | null;
198
- /**
199
- * @description Specify a header name and value to send back with a webhook call for added security
200
- * @default null
201
- */
202
- webhook_auth_header_value?: string | null;
203
- /** @description The URL to which AssemblyAI send webhooks upon trancription completion */
204
- webhook_url?: string;
205
- /** @description The list of custom vocabulary to boost transcription probability for */
206
- word_boost?: string[];
207
- };
208
-
209
- /** @description The parameters for creating a transcript */
210
- export type CreateTranscriptParameters = CreateTranscriptOptionalParameters & {
211
- /** @description The URL of the audio or video file to transcribe. */
212
- audio_url: string;
213
- };
214
-
215
110
  /** @description A detected entity */
216
111
  export type Entity = {
217
112
  /** @description The ending time, in milliseconds, for the detected entity in the audio file */
@@ -266,14 +161,14 @@ export type Error = {
266
161
  status?: "error";
267
162
  };
268
163
 
269
- export type LemurActionItemsParameters = LemurBaseParameters;
164
+ export type LemurActionItemsParams = LemurBaseParams;
270
165
 
271
166
  export type LemurActionItemsResponse = LemurBaseResponse & {
272
167
  /** @description The response generated by LeMUR */
273
168
  response: string;
274
169
  };
275
170
 
276
- export type LemurBaseParameters = {
171
+ export type LemurBaseParams = {
277
172
  /** @description Context to provide the model. This can be a string or a free-form JSON value. */
278
173
  context?: OneOf<
279
174
  [
@@ -343,7 +238,7 @@ export type LemurQuestionAnswer = {
343
238
  question: string;
344
239
  };
345
240
 
346
- export type LemurQuestionAnswerParameters = LemurBaseParameters & {
241
+ export type LemurQuestionAnswerParams = LemurBaseParams & {
347
242
  /** @description A list of questions to ask */
348
243
  questions: LemurQuestion[];
349
244
  };
@@ -353,7 +248,7 @@ export type LemurQuestionAnswerResponse = LemurBaseResponse & {
353
248
  response: LemurQuestionAnswer[];
354
249
  };
355
250
 
356
- export type LemurSummaryParameters = LemurBaseParameters & {
251
+ export type LemurSummaryParams = LemurBaseParams & {
357
252
  /** @description How you want the summary to be returned. This can be any text. Examples: "TLDR", "bullet points" */
358
253
  answer_format?: string;
359
254
  };
@@ -363,7 +258,7 @@ export type LemurSummaryResponse = LemurBaseResponse & {
363
258
  response: string;
364
259
  };
365
260
 
366
- export type LemurTaskParameters = LemurBaseParameters & {
261
+ export type LemurTaskParams = LemurBaseParams & {
367
262
  /** @description Your text to prompt the model to produce a desired output, including any context you want to pass into the model. */
368
263
  prompt: string;
369
264
  };
@@ -373,6 +268,28 @@ export type LemurTaskResponse = LemurBaseResponse & {
373
268
  response: string;
374
269
  };
375
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
+
376
293
  export type PageDetails = {
377
294
  current_url: string;
378
295
  limit: number;
@@ -782,26 +699,103 @@ export type TranscriptListItem = {
782
699
  status: TranscriptStatus;
783
700
  };
784
701
 
785
- export type TranscriptListParameters = {
786
- /** @description Get transcripts that were created after this transcript ID */
787
- after_id?: string;
788
- /** @description Get transcripts that were created before this transcript ID */
789
- before_id?: string;
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;
790
732
  /**
791
- * Format: date
792
- * @description Only get transcripts created on this date
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'.
793
735
  */
794
- created_on?: string;
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;
795
745
  /**
796
- * Format: int64
797
- * @description Maximum amount of transcripts to retrieve
798
- * @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
799
748
  */
800
- limit?: number;
801
- /** @description Filter by transcript status */
802
- status?: TranscriptStatus;
803
- /** @description Only get throttled transcripts, overrides the status filter */
804
- throttled_only?: boolean;
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[];
805
799
  };
806
800
 
807
801
  export type TranscriptParagraph = {
@@ -813,6 +807,12 @@ export type TranscriptParagraph = {
813
807
  words: TranscriptWord[];
814
808
  };
815
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
+
816
816
  export type TranscriptSentence = {
817
817
  /** Format: double */
818
818
  confidence: number;
@@ -1,16 +1,16 @@
1
1
  /**
2
2
  * Interface for classes that can create resources.
3
3
  * @template T The type of the resource.
4
- * @template Parameters The type of the parameters required to create the resource.
4
+ * @template Params The type of the parameters required to create the resource.
5
5
  */
6
- interface Createable<T, Parameters, Options = Record<string, unknown>> {
6
+ interface Createable<T, Params, Options = Record<string, unknown>> {
7
7
  /**
8
8
  * Create a new resource.
9
9
  * @param params The parameters of the new resource.
10
10
  * @param options The options used for creating the new resource.
11
11
  * @return A promise that resolves to the newly created resource.
12
12
  */
13
- create(params: Parameters, options?: Options): Promise<T>;
13
+ create(params: Params, options?: Options): Promise<T>;
14
14
  }
15
15
 
16
16
  /**
@@ -1,3 +1,6 @@
1
+ import { FileUploadParams } from "../files";
2
+ import { TranscriptParams } from "../openapi.generated";
3
+
1
4
  export type PollingOptions = {
2
5
  /**
3
6
  * The amount of time to wait between polling requests.
@@ -10,6 +13,7 @@ export type PollingOptions = {
10
13
  */
11
14
  pollingTimeout?: number;
12
15
  };
16
+
13
17
  export type CreateTranscriptOptions = {
14
18
  /**
15
19
  * Whether to poll the transcript until it is ready.
@@ -17,3 +21,26 @@ export type CreateTranscriptOptions = {
17
21
  */
18
22
  poll?: boolean;
19
23
  } & PollingOptions;
24
+
25
+ /**
26
+ * The audio to transcribe. This can be a public URL, a local file path, a readable file stream, or a file buffer.
27
+ */
28
+ export type AudioToTranscribe = FileUploadParams;
29
+
30
+ /**
31
+ * The parameters to transcribe an audio file.
32
+ */
33
+ export type TranscribeParams = { audio: AudioToTranscribe } & Omit<
34
+ TranscriptParams,
35
+ "audio_url"
36
+ >;
37
+
38
+ /**
39
+ * The parameters to start the transcription of an audio file.
40
+ */
41
+ export type SubmitParams = TranscribeParams;
42
+
43
+ /**
44
+ * The options to transcribe an audio file, including polling options.
45
+ */
46
+ export type TranscribeOptions = PollingOptions;
File without changes