v1.d.ts
35.7 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
/// <reference types="node" />
import { OAuth2Client, JWT, Compute, UserRefreshClient, BaseExternalAccountClient, GaxiosPromise, GoogleConfigurable, MethodOptions, StreamMethodOptions, GlobalOptions, GoogleAuth, BodyResponseCallback, APIRequestContext } from 'googleapis-common';
import { Readable } from 'stream';
export declare namespace speech_v1 {
export interface Options extends GlobalOptions {
version: 'v1';
}
interface StandardParameters {
/**
* Auth client or API Key for the request
*/
auth?: string | OAuth2Client | JWT | Compute | UserRefreshClient | BaseExternalAccountClient | GoogleAuth;
/**
* V1 error format.
*/
'$.xgafv'?: string;
/**
* OAuth access token.
*/
access_token?: string;
/**
* Data format for response.
*/
alt?: string;
/**
* JSONP
*/
callback?: string;
/**
* Selector specifying which fields to include in a partial response.
*/
fields?: string;
/**
* API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.
*/
key?: string;
/**
* OAuth 2.0 token for the current user.
*/
oauth_token?: string;
/**
* Returns response with indentations and line breaks.
*/
prettyPrint?: boolean;
/**
* Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.
*/
quotaUser?: string;
/**
* Legacy upload protocol for media (e.g. "media", "multipart").
*/
uploadType?: string;
/**
* Upload protocol for media (e.g. "raw", "multipart").
*/
upload_protocol?: string;
}
/**
* Cloud Speech-to-Text API
*
* Converts audio to text by applying powerful neural network models.
*
* @example
* ```js
* const {google} = require('googleapis');
* const speech = google.speech('v1');
* ```
*/
export class Speech {
context: APIRequestContext;
operations: Resource$Operations;
speech: Resource$Speech;
constructor(options: GlobalOptions, google?: GoogleConfigurable);
}
/**
* The response message for Operations.ListOperations.
*/
export interface Schema$ListOperationsResponse {
/**
* The standard List next-page token.
*/
nextPageToken?: string | null;
/**
* A list of operations that matches the specified filter in the request.
*/
operations?: Schema$Operation[];
}
/**
* Describes the progress of a long-running `LongRunningRecognize` call. It is included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.
*/
export interface Schema$LongRunningRecognizeMetadata {
/**
* Time of the most recent processing update.
*/
lastUpdateTime?: string | null;
/**
* Approximate percentage of audio processed thus far. Guaranteed to be 100 when the audio is fully processed and the results are available.
*/
progressPercent?: number | null;
/**
* Time when the request was received.
*/
startTime?: string | null;
/**
* Output only. The URI of the audio file being transcribed. Empty if the audio was sent as byte content.
*/
uri?: string | null;
}
/**
* The top-level message sent by the client for the `LongRunningRecognize` method.
*/
export interface Schema$LongRunningRecognizeRequest {
/**
* Required. The audio data to be recognized.
*/
audio?: Schema$RecognitionAudio;
/**
* Required. Provides information to the recognizer that specifies how to process the request.
*/
config?: Schema$RecognitionConfig;
}
/**
* The only message returned to the client by the `LongRunningRecognize` method. It contains the result as zero or more sequential `SpeechRecognitionResult` messages. It is included in the `result.response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.
*/
export interface Schema$LongRunningRecognizeResponse {
/**
* Sequential list of transcription results corresponding to sequential portions of audio.
*/
results?: Schema$SpeechRecognitionResult[];
}
/**
* This resource represents a long-running operation that is the result of a network API call.
*/
export interface Schema$Operation {
/**
* If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
*/
done?: boolean | null;
/**
* The error result of the operation in case of failure or cancellation.
*/
error?: Schema$Status;
/**
* Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
*/
metadata?: {
[key: string]: any;
} | null;
/**
* The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id\}`.
*/
name?: string | null;
/**
* The normal response of the operation in case of success. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
*/
response?: {
[key: string]: any;
} | null;
}
/**
* Contains audio data in the encoding specified in the `RecognitionConfig`. Either `content` or `uri` must be supplied. Supplying both or neither returns google.rpc.Code.INVALID_ARGUMENT. See [content limits](https://cloud.google.com/speech-to-text/quotas#content).
*/
export interface Schema$RecognitionAudio {
/**
* The audio data bytes encoded as specified in `RecognitionConfig`. Note: as with all bytes fields, proto buffers use a pure binary representation, whereas JSON representations use base64.
*/
content?: string | null;
/**
* URI that points to a file that contains audio data bytes as specified in `RecognitionConfig`. The file must not be compressed (for example, gzip). Currently, only Google Cloud Storage URIs are supported, which must be specified in the following format: `gs://bucket_name/object_name` (other URI formats return google.rpc.Code.INVALID_ARGUMENT). For more information, see [Request URIs](https://cloud.google.com/storage/docs/reference-uris).
*/
uri?: string | null;
}
/**
* Provides information to the recognizer that specifies how to process the request.
*/
export interface Schema$RecognitionConfig {
/**
* The number of channels in the input audio data. ONLY set this for MULTI-CHANNEL recognition. Valid values for LINEAR16 and FLAC are `1`-`8`. Valid values for OGG_OPUS are '1'-'254'. Valid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only `1`. If `0` or omitted, defaults to one channel (mono). Note: We only recognize the first channel by default. To perform independent recognition on each channel set `enable_separate_recognition_per_channel` to 'true'.
*/
audioChannelCount?: number | null;
/**
* Config to enable speaker diarization and set additional parameters to make diarization better suited for your application. Note: When this is enabled, we send all the words from the beginning of the audio for the top alternative in every consecutive STREAMING responses. This is done in order to improve our speaker tags as our models learn to identify the speakers in the conversation over time. For non-streaming requests, the diarization results will be provided only in the top alternative of the FINAL SpeechRecognitionResult.
*/
diarizationConfig?: Schema$SpeakerDiarizationConfig;
/**
* If 'true', adds punctuation to recognition result hypotheses. This feature is only available in select languages. Setting this for requests in other languages has no effect at all. The default 'false' value does not add punctuation to result hypotheses.
*/
enableAutomaticPunctuation?: boolean | null;
/**
* This needs to be set to `true` explicitly and `audio_channel_count` \> 1 to get each channel recognized separately. The recognition result will contain a `channel_tag` field to state which channel that result belongs to. If this is not true, we will only recognize the first channel. The request is billed cumulatively for all channels recognized: `audio_channel_count` multiplied by the length of the audio.
*/
enableSeparateRecognitionPerChannel?: boolean | null;
/**
* If `true`, the top result includes a list of words and the start and end time offsets (timestamps) for those words. If `false`, no word-level time offset information is returned. The default is `false`.
*/
enableWordTimeOffsets?: boolean | null;
/**
* Encoding of audio data sent in all `RecognitionAudio` messages. This field is optional for `FLAC` and `WAV` audio files and required for all other audio formats. For details, see AudioEncoding.
*/
encoding?: string | null;
/**
* Required. The language of the supplied audio as a [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag. Example: "en-US". See [Language Support](https://cloud.google.com/speech-to-text/docs/languages) for a list of the currently supported language codes.
*/
languageCode?: string | null;
/**
* Maximum number of recognition hypotheses to be returned. Specifically, the maximum number of `SpeechRecognitionAlternative` messages within each `SpeechRecognitionResult`. The server may return fewer than `max_alternatives`. Valid values are `0`-`30`. A value of `0` or `1` will return a maximum of one. If omitted, will return a maximum of one.
*/
maxAlternatives?: number | null;
/**
* Metadata regarding this request.
*/
metadata?: Schema$RecognitionMetadata;
/**
* Which model to select for the given request. Select the model best suited to your domain to get best results. If a model is not explicitly specified, then we auto-select a model based on the parameters in the RecognitionConfig. *Model* *Description* command_and_search Best for short queries such as voice commands or voice search. phone_call Best for audio that originated from a phone call (typically recorded at an 8khz sampling rate). video Best for audio that originated from video or includes multiple speakers. Ideally the audio is recorded at a 16khz or greater sampling rate. This is a premium model that costs more than the standard rate. default Best for audio that is not one of the specific audio models. For example, long-form audio. Ideally the audio is high-fidelity, recorded at a 16khz or greater sampling rate.
*/
model?: string | null;
/**
* If set to `true`, the server will attempt to filter out profanities, replacing all but the initial character in each filtered word with asterisks, e.g. "f***". If set to `false` or omitted, profanities won't be filtered out.
*/
profanityFilter?: boolean | null;
/**
* Sample rate in Hertz of the audio data sent in all `RecognitionAudio` messages. Valid values are: 8000-48000. 16000 is optimal. For best results, set the sampling rate of the audio source to 16000 Hz. If that's not possible, use the native sample rate of the audio source (instead of re-sampling). This field is optional for FLAC and WAV audio files, but is required for all other audio formats. For details, see AudioEncoding.
*/
sampleRateHertz?: number | null;
/**
* Array of SpeechContext. A means to provide context to assist the speech recognition. For more information, see [speech adaptation](https://cloud.google.com/speech-to-text/docs/adaptation).
*/
speechContexts?: Schema$SpeechContext[];
/**
* Set to true to use an enhanced model for speech recognition. If `use_enhanced` is set to true and the `model` field is not set, then an appropriate enhanced model is chosen if an enhanced model exists for the audio. If `use_enhanced` is true and an enhanced version of the specified model does not exist, then the speech is recognized using the standard version of the specified model.
*/
useEnhanced?: boolean | null;
}
/**
* Description of audio data to be recognized.
*/
export interface Schema$RecognitionMetadata {
/**
* Description of the content. Eg. "Recordings of federal supreme court hearings from 2012".
*/
audioTopic?: string | null;
/**
* The industry vertical to which this speech recognition request most closely applies. This is most indicative of the topics contained in the audio. Use the 6-digit NAICS code to identify the industry vertical - see https://www.naics.com/search/.
*/
industryNaicsCodeOfAudio?: number | null;
/**
* The use case most closely describing the audio content to be recognized.
*/
interactionType?: string | null;
/**
* The audio type that most closely describes the audio being recognized.
*/
microphoneDistance?: string | null;
/**
* The original media the speech was recorded on.
*/
originalMediaType?: string | null;
/**
* Mime type of the original audio file. For example `audio/m4a`, `audio/x-alaw-basic`, `audio/mp3`, `audio/3gpp`. A list of possible audio mime types is maintained at http://www.iana.org/assignments/media-types/media-types.xhtml#audio
*/
originalMimeType?: string | null;
/**
* The device used to make the recording. Examples 'Nexus 5X' or 'Polycom SoundStation IP 6000' or 'POTS' or 'VoIP' or 'Cardioid Microphone'.
*/
recordingDeviceName?: string | null;
/**
* The type of device the speech was recorded with.
*/
recordingDeviceType?: string | null;
}
/**
* The top-level message sent by the client for the `Recognize` method.
*/
export interface Schema$RecognizeRequest {
/**
* Required. The audio data to be recognized.
*/
audio?: Schema$RecognitionAudio;
/**
* Required. Provides information to the recognizer that specifies how to process the request.
*/
config?: Schema$RecognitionConfig;
}
/**
* The only message returned to the client by the `Recognize` method. It contains the result as zero or more sequential `SpeechRecognitionResult` messages.
*/
export interface Schema$RecognizeResponse {
/**
* Sequential list of transcription results corresponding to sequential portions of audio.
*/
results?: Schema$SpeechRecognitionResult[];
}
/**
* Config to enable speaker diarization.
*/
export interface Schema$SpeakerDiarizationConfig {
/**
* If 'true', enables speaker detection for each recognized word in the top alternative of the recognition result using a speaker_tag provided in the WordInfo.
*/
enableSpeakerDiarization?: boolean | null;
/**
* Maximum number of speakers in the conversation. This range gives you more flexibility by allowing the system to automatically determine the correct number of speakers. If not set, the default value is 6.
*/
maxSpeakerCount?: number | null;
/**
* Minimum number of speakers in the conversation. This range gives you more flexibility by allowing the system to automatically determine the correct number of speakers. If not set, the default value is 2.
*/
minSpeakerCount?: number | null;
/**
* Output only. Unused.
*/
speakerTag?: number | null;
}
/**
* Provides "hints" to the speech recognizer to favor specific words and phrases in the results.
*/
export interface Schema$SpeechContext {
/**
* A list of strings containing words and phrases "hints" so that the speech recognition is more likely to recognize them. This can be used to improve the accuracy for specific words and phrases, for example, if specific commands are typically spoken by the user. This can also be used to add additional words to the vocabulary of the recognizer. See [usage limits](https://cloud.google.com/speech-to-text/quotas#content). List items can also be set to classes for groups of words that represent common concepts that occur in natural language. For example, rather than providing phrase hints for every month of the year, using the $MONTH class improves the likelihood of correctly transcribing audio that includes months.
*/
phrases?: string[] | null;
}
/**
* Alternative hypotheses (a.k.a. n-best list).
*/
export interface Schema$SpeechRecognitionAlternative {
/**
* The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative of a non-streaming result or, of a streaming result where `is_final=true`. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.
*/
confidence?: number | null;
/**
* Transcript text representing the words that the user spoke.
*/
transcript?: string | null;
/**
* A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is true, you will see all the words from the beginning of the audio.
*/
words?: Schema$WordInfo[];
}
/**
* A speech recognition result corresponding to a portion of the audio.
*/
export interface Schema$SpeechRecognitionResult {
/**
* May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer.
*/
alternatives?: Schema$SpeechRecognitionAlternative[];
/**
* For multi-channel audio, this is the channel number corresponding to the recognized result for the audio from that channel. For audio_channel_count = N, its output values can range from '1' to 'N'.
*/
channelTag?: number | null;
}
/**
* The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors).
*/
export interface Schema$Status {
/**
* The status code, which should be an enum value of google.rpc.Code.
*/
code?: number | null;
/**
* A list of messages that carry the error details. There is a common set of message types for APIs to use.
*/
details?: Array<{
[key: string]: any;
}> | null;
/**
* A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
*/
message?: string | null;
}
/**
* Word-specific information for recognized words.
*/
export interface Schema$WordInfo {
/**
* Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.
*/
endTime?: string | null;
/**
* Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from '1' to diarization_speaker_count. speaker_tag is set if enable_speaker_diarization = 'true' and only in the top alternative.
*/
speakerTag?: number | null;
/**
* Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.
*/
startTime?: string | null;
/**
* The word corresponding to this set of information.
*/
word?: string | null;
}
export class Resource$Operations {
context: APIRequestContext;
constructor(context: APIRequestContext);
/**
* Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.
* @example
* ```js
* // Before running the sample:
* // - Enable the API at:
* // https://console.developers.google.com/apis/api/speech.googleapis.com
* // - Login into gcloud by running:
* // `$ gcloud auth application-default login`
* // - Install the npm module by running:
* // `$ npm install googleapis`
*
* const {google} = require('googleapis');
* const speech = google.speech('v1');
*
* async function main() {
* const auth = new google.auth.GoogleAuth({
* // Scopes can be specified either as an array or as a single, space-delimited string.
* scopes: ['https://www.googleapis.com/auth/cloud-platform'],
* });
*
* // Acquire an auth client, and bind it to all future calls
* const authClient = await auth.getClient();
* google.options({auth: authClient});
*
* // Do the magic
* const res = await speech.operations.get({
* // The name of the operation resource.
* name: '.*',
* });
* console.log(res.data);
*
* // Example response
* // {
* // "done": false,
* // "error": {},
* // "metadata": {},
* // "name": "my_name",
* // "response": {}
* // }
* }
*
* main().catch(e => {
* console.error(e);
* throw e;
* });
*
* ```
*
* @param params - Parameters for request
* @param options - Optionally override request options, such as `url`, `method`, and `encoding`.
* @param callback - Optional callback that handles the response.
* @returns A promise if used with async/await, or void if used with a callback.
*/
get(params: Params$Resource$Operations$Get, options: StreamMethodOptions): GaxiosPromise<Readable>;
get(params?: Params$Resource$Operations$Get, options?: MethodOptions): GaxiosPromise<Schema$Operation>;
get(params: Params$Resource$Operations$Get, options: StreamMethodOptions | BodyResponseCallback<Readable>, callback: BodyResponseCallback<Readable>): void;
get(params: Params$Resource$Operations$Get, options: MethodOptions | BodyResponseCallback<Schema$Operation>, callback: BodyResponseCallback<Schema$Operation>): void;
get(params: Params$Resource$Operations$Get, callback: BodyResponseCallback<Schema$Operation>): void;
get(callback: BodyResponseCallback<Schema$Operation>): void;
/**
* Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns `UNIMPLEMENTED`. NOTE: the `name` binding allows API services to override the binding to use different resource name schemes, such as `users/x/operations`. To override the binding, API services can add a binding such as `"/v1/{name=users/x\}/operations"` to their service configuration. For backwards compatibility, the default name includes the operations collection id, however overriding users must ensure the name binding is the parent resource, without the operations collection id.
* @example
* ```js
* // Before running the sample:
* // - Enable the API at:
* // https://console.developers.google.com/apis/api/speech.googleapis.com
* // - Login into gcloud by running:
* // `$ gcloud auth application-default login`
* // - Install the npm module by running:
* // `$ npm install googleapis`
*
* const {google} = require('googleapis');
* const speech = google.speech('v1');
*
* async function main() {
* const auth = new google.auth.GoogleAuth({
* // Scopes can be specified either as an array or as a single, space-delimited string.
* scopes: ['https://www.googleapis.com/auth/cloud-platform'],
* });
*
* // Acquire an auth client, and bind it to all future calls
* const authClient = await auth.getClient();
* google.options({auth: authClient});
*
* // Do the magic
* const res = await speech.operations.list({
* // The standard list filter.
* filter: 'placeholder-value',
* // The name of the operation's parent resource.
* name: 'placeholder-value',
* // The standard list page size.
* pageSize: 'placeholder-value',
* // The standard list page token.
* pageToken: 'placeholder-value',
* });
* console.log(res.data);
*
* // Example response
* // {
* // "nextPageToken": "my_nextPageToken",
* // "operations": []
* // }
* }
*
* main().catch(e => {
* console.error(e);
* throw e;
* });
*
* ```
*
* @param params - Parameters for request
* @param options - Optionally override request options, such as `url`, `method`, and `encoding`.
* @param callback - Optional callback that handles the response.
* @returns A promise if used with async/await, or void if used with a callback.
*/
list(params: Params$Resource$Operations$List, options: StreamMethodOptions): GaxiosPromise<Readable>;
list(params?: Params$Resource$Operations$List, options?: MethodOptions): GaxiosPromise<Schema$ListOperationsResponse>;
list(params: Params$Resource$Operations$List, options: StreamMethodOptions | BodyResponseCallback<Readable>, callback: BodyResponseCallback<Readable>): void;
list(params: Params$Resource$Operations$List, options: MethodOptions | BodyResponseCallback<Schema$ListOperationsResponse>, callback: BodyResponseCallback<Schema$ListOperationsResponse>): void;
list(params: Params$Resource$Operations$List, callback: BodyResponseCallback<Schema$ListOperationsResponse>): void;
list(callback: BodyResponseCallback<Schema$ListOperationsResponse>): void;
}
export interface Params$Resource$Operations$Get extends StandardParameters {
/**
* The name of the operation resource.
*/
name?: string;
}
export interface Params$Resource$Operations$List extends StandardParameters {
/**
* The standard list filter.
*/
filter?: string;
/**
* The name of the operation's parent resource.
*/
name?: string;
/**
* The standard list page size.
*/
pageSize?: number;
/**
* The standard list page token.
*/
pageToken?: string;
}
export class Resource$Speech {
context: APIRequestContext;
constructor(context: APIRequestContext);
/**
* Performs asynchronous speech recognition: receive results via the google.longrunning.Operations interface. Returns either an `Operation.error` or an `Operation.response` which contains a `LongRunningRecognizeResponse` message. For more information on asynchronous speech recognition, see the [how-to](https://cloud.google.com/speech-to-text/docs/async-recognize).
* @example
* ```js
* // Before running the sample:
* // - Enable the API at:
* // https://console.developers.google.com/apis/api/speech.googleapis.com
* // - Login into gcloud by running:
* // `$ gcloud auth application-default login`
* // - Install the npm module by running:
* // `$ npm install googleapis`
*
* const {google} = require('googleapis');
* const speech = google.speech('v1');
*
* async function main() {
* const auth = new google.auth.GoogleAuth({
* // Scopes can be specified either as an array or as a single, space-delimited string.
* scopes: ['https://www.googleapis.com/auth/cloud-platform'],
* });
*
* // Acquire an auth client, and bind it to all future calls
* const authClient = await auth.getClient();
* google.options({auth: authClient});
*
* // Do the magic
* const res = await speech.speech.longrunningrecognize({
* // Request body metadata
* requestBody: {
* // request body parameters
* // {
* // "audio": {},
* // "config": {}
* // }
* },
* });
* console.log(res.data);
*
* // Example response
* // {
* // "done": false,
* // "error": {},
* // "metadata": {},
* // "name": "my_name",
* // "response": {}
* // }
* }
*
* main().catch(e => {
* console.error(e);
* throw e;
* });
*
* ```
*
* @param params - Parameters for request
* @param options - Optionally override request options, such as `url`, `method`, and `encoding`.
* @param callback - Optional callback that handles the response.
* @returns A promise if used with async/await, or void if used with a callback.
*/
longrunningrecognize(params: Params$Resource$Speech$Longrunningrecognize, options: StreamMethodOptions): GaxiosPromise<Readable>;
longrunningrecognize(params?: Params$Resource$Speech$Longrunningrecognize, options?: MethodOptions): GaxiosPromise<Schema$Operation>;
longrunningrecognize(params: Params$Resource$Speech$Longrunningrecognize, options: StreamMethodOptions | BodyResponseCallback<Readable>, callback: BodyResponseCallback<Readable>): void;
longrunningrecognize(params: Params$Resource$Speech$Longrunningrecognize, options: MethodOptions | BodyResponseCallback<Schema$Operation>, callback: BodyResponseCallback<Schema$Operation>): void;
longrunningrecognize(params: Params$Resource$Speech$Longrunningrecognize, callback: BodyResponseCallback<Schema$Operation>): void;
longrunningrecognize(callback: BodyResponseCallback<Schema$Operation>): void;
/**
* Performs synchronous speech recognition: receive results after all audio has been sent and processed.
* @example
* ```js
* // Before running the sample:
* // - Enable the API at:
* // https://console.developers.google.com/apis/api/speech.googleapis.com
* // - Login into gcloud by running:
* // `$ gcloud auth application-default login`
* // - Install the npm module by running:
* // `$ npm install googleapis`
*
* const {google} = require('googleapis');
* const speech = google.speech('v1');
*
* async function main() {
* const auth = new google.auth.GoogleAuth({
* // Scopes can be specified either as an array or as a single, space-delimited string.
* scopes: ['https://www.googleapis.com/auth/cloud-platform'],
* });
*
* // Acquire an auth client, and bind it to all future calls
* const authClient = await auth.getClient();
* google.options({auth: authClient});
*
* // Do the magic
* const res = await speech.speech.recognize({
* // Request body metadata
* requestBody: {
* // request body parameters
* // {
* // "audio": {},
* // "config": {}
* // }
* },
* });
* console.log(res.data);
*
* // Example response
* // {
* // "results": []
* // }
* }
*
* main().catch(e => {
* console.error(e);
* throw e;
* });
*
* ```
*
* @param params - Parameters for request
* @param options - Optionally override request options, such as `url`, `method`, and `encoding`.
* @param callback - Optional callback that handles the response.
* @returns A promise if used with async/await, or void if used with a callback.
*/
recognize(params: Params$Resource$Speech$Recognize, options: StreamMethodOptions): GaxiosPromise<Readable>;
recognize(params?: Params$Resource$Speech$Recognize, options?: MethodOptions): GaxiosPromise<Schema$RecognizeResponse>;
recognize(params: Params$Resource$Speech$Recognize, options: StreamMethodOptions | BodyResponseCallback<Readable>, callback: BodyResponseCallback<Readable>): void;
recognize(params: Params$Resource$Speech$Recognize, options: MethodOptions | BodyResponseCallback<Schema$RecognizeResponse>, callback: BodyResponseCallback<Schema$RecognizeResponse>): void;
recognize(params: Params$Resource$Speech$Recognize, callback: BodyResponseCallback<Schema$RecognizeResponse>): void;
recognize(callback: BodyResponseCallback<Schema$RecognizeResponse>): void;
}
export interface Params$Resource$Speech$Longrunningrecognize extends StandardParameters {
/**
* Request body metadata
*/
requestBody?: Schema$LongRunningRecognizeRequest;
}
export interface Params$Resource$Speech$Recognize extends StandardParameters {
/**
* Request body metadata
*/
requestBody?: Schema$RecognizeRequest;
}
export {};
}