Blame - docs/dyn/speech_v1p1beta1.speech.html - platform/external/python/google-api-python-client

"config": { # Provides information to the recognizer that specifies how to process the # *Required* Provides information to the recognizer that specifies how to

115

# process the request.

116

# request.

117

"languageCode": "A String", # *Required* The language of the supplied audio as a

118

# [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.

119

# Example: "en-US".

120

# See [Language Support](/speech-to-text/docs/languages)

121

# for a list of the currently supported language codes.

122

"audioChannelCount": 42, # *Optional* The number of channels in the input audio data.

123

# ONLY set this for MULTI-CHANNEL recognition.

124

# Valid values for LINEAR16 and FLAC are `1`-`8`.

125

# Valid values for OGG_OPUS are '1'-'254'.

126

# Valid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only `1`.

127

# If `0` or omitted, defaults to one channel (mono).

128

# Note: We only recognize the first channel by default.

129

# To perform independent recognition on each channel set

130

# `enable_separate_recognition_per_channel` to 'true'.

131

"encoding": "A String", # Encoding of audio data sent in all `RecognitionAudio` messages.

132

# This field is optional for `FLAC` and `WAV` audio files and required

133

# for all other audio formats. For details, see AudioEncoding.

134

"enableAutomaticPunctuation": True or False, # *Optional* If 'true', adds punctuation to recognition result hypotheses.

135

# This feature is only available in select languages. Setting this for

136

# requests in other languages has no effect at all.

137

# The default 'false' value does not add punctuation to result hypotheses.

138

# Note: This is currently offered as an experimental service, complimentary

139

# to all users. In the future this may be exclusively available as a

140

# premium feature.

141

"alternativeLanguageCodes": [ # *Optional* A list of up to 3 additional

142

# [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,

143

# listing possible alternative languages of the supplied audio.

144

# See [Language Support](/speech-to-text/docs/languages)

145

# for a list of the currently supported language codes.

146

# If alternative languages are listed, recognition result will contain

147

# recognition in the most likely language detected including the main

148

# language_code. The recognition result will include the language tag

149

# of the language detected in the audio.

150

# Note: This feature is only supported for Voice Command and Voice Search

151

# use cases and performance may vary for other use cases (e.g., phone call

# transcription).

"A String",

],

"enableSeparateRecognitionPerChannel": True or False, # This needs to be set to `true` explicitly and `audio_channel_count` > 1

156

# to get each channel recognized separately. The recognition result will

157

# contain a `channel_tag` field to state which channel that result belongs

158

# to. If this is not true, we will only recognize the first channel. The

159

# request is billed cumulatively for all channels recognized:

160

# `audio_channel_count` multiplied by the length of the audio.

161

"enableWordTimeOffsets": True or False, # *Optional* If `true`, the top result includes a list of words and

162

# the start and end time offsets (timestamps) for those words. If

163

# `false`, no word-level time offset information is returned. The default is

164

# `false`.

165

"enableSpeakerDiarization": True or False, # *Optional* If 'true', enables speaker detection for each recognized word in

166

# the top alternative of the recognition result using a speaker_tag provided

167

# in the WordInfo.

168

# Note: Use diarization_config instead. This field will be DEPRECATED soon.

169

"maxAlternatives": 42, # *Optional* Maximum number of recognition hypotheses to be returned.

170

# Specifically, the maximum number of `SpeechRecognitionAlternative` messages

171

# within each `SpeechRecognitionResult`.

172

# The server may return fewer than `max_alternatives`.

173

# Valid values are `0`-`30`. A value of `0` or `1` will return a maximum of

174

# one. If omitted, will return a maximum of one.

175

"profanityFilter": True or False, # *Optional* If set to `true`, the server will attempt to filter out

176

# profanities, replacing all but the initial character in each filtered word

177

# with asterisks, e.g. "f***". If set to `false` or omitted, profanities

178

# won't be filtered out.

179

"useEnhanced": True or False, # *Optional* Set to true to use an enhanced model for speech recognition.

180

# If `use_enhanced` is set to true and the `model` field is not set, then

181

# an appropriate enhanced model is chosen if:

182

# 1. project is eligible for requesting enhanced models

183

# 2. an enhanced model exists for the audio

184

#

185

# If `use_enhanced` is true and an enhanced version of the specified model

186

# does not exist, then the speech is recognized using the standard version

187

# of the specified model.

188

#

189

# Enhanced speech models require that you opt-in to data logging using

190

# instructions in the

191

# [documentation](/speech-to-text/docs/enable-data-logging). If you set

192

# `use_enhanced` to true and you have not enabled audio logging, then you

193

# will receive an error.

194

"sampleRateHertz": 42, # Sample rate in Hertz of the audio data sent in all

195

# `RecognitionAudio` messages. Valid values are: 8000-48000.

196

# 16000 is optimal. For best results, set the sampling rate of the audio

197

# source to 16000 Hz. If that's not possible, use the native sample rate of

198

# the audio source (instead of re-sampling).

199

# This field is optional for FLAC and WAV audio files, but is

200

# required for all other audio formats. For details, see AudioEncoding.

201

"diarizationSpeakerCount": 42, # *Optional*

202

# If set, specifies the estimated number of speakers in the conversation.

203

# If not set, defaults to '2'.

204

# Ignored unless enable_speaker_diarization is set to true."

205

# Note: Use diarization_config instead. This field will be DEPRECATED soon.

206

"enableWordConfidence": True or False, # *Optional* If `true`, the top result includes a list of words and the

207

# confidence for those words. If `false`, no word-level confidence

208

# information is returned. The default is `false`.

209

"model": "A String", # *Optional* Which model to select for the given request. Select the model

210

# best suited to your domain to get best results. If a model is not

211

# explicitly specified, then we auto-select a model based on the parameters

212

# in the RecognitionConfig.

213

# <table>

214

# <tr>

215

# <td><b>Model</b></td>

216

# <td><b>Description</b></td>

217

# </tr>

218

# <tr>

219

# <td><code>command_and_search</code></td>

220

# <td>Best for short queries such as voice commands or voice search.</td>

221

# </tr>

222

# <tr>

223

# <td><code>phone_call</code></td>

224

# <td>Best for audio that originated from a phone call (typically

225

# recorded at an 8khz sampling rate).</td>

226

# </tr>

227

# <tr>

228

# <td><code>video</code></td>

229

# <td>Best for audio that originated from from video or includes multiple

230

# speakers. Ideally the audio is recorded at a 16khz or greater

231

# sampling rate. This is a premium model that costs more than the

232

# standard rate.</td>

233

# </tr>

234

# <tr>

235

# <td><code>default</code></td>

236

# <td>Best for audio that is not one of the specific audio models.

237

# For example, long-form audio. Ideally the audio is high-fidelity,

238

# recorded at a 16khz or greater sampling rate.</td>

239

# </tr>

240

# </table>

241

"diarizationConfig": { # *Optional* Config to enable speaker diarization and set additional

242

# parameters to make diarization better suited for your application.

243

# Note: When this is enabled, we send all the words from the beginning of the

244

# audio for the top alternative in every consecutive STREAMING responses.

245

# This is done in order to improve our speaker tags as our models learn to

246

# identify the speakers in the conversation over time.

247

# For non-streaming requests, the diarization results will be provided only

248

# in the top alternative of the FINAL SpeechRecognitionResult.

249

"minSpeakerCount": 42, # *Optional* Only used if diarization_speaker_count is not set.

250

# Minimum number of speakers in the conversation. This range gives you more

251

# flexibility by allowing the system to automatically determine the correct

252

# number of speakers. If not set, the default value is 2.

253

"enableSpeakerDiarization": True or False, # *Optional* If 'true', enables speaker detection for each recognized word in

254

# the top alternative of the recognition result using a speaker_tag provided

255

# in the WordInfo.

256

"maxSpeakerCount": 42, # *Optional* Only used if diarization_speaker_count is not set.

257

# Maximum number of speakers in the conversation. This range gives you more

258

# flexibility by allowing the system to automatically determine the correct

259

# number of speakers. If not set, the default value is 6.

260

},

261

"speechContexts": [ # *Optional* array of SpeechContext.

262

# A means to provide context to assist the speech recognition. For more

263

# information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).

264

{ # Provides "hints" to the speech recognizer to favor specific words and phrases

265

# in the results.

266

"phrases": [ # *Optional* A list of strings containing words and phrases "hints" so that

267

# the speech recognition is more likely to recognize them. This can be used

268

# to improve the accuracy for specific words and phrases, for example, if

269

# specific commands are typically spoken by the user. This can also be used

270

# to add additional words to the vocabulary of the recognizer. See

271

# [usage limits](/speech-to-text/quotas#content).

272

#

273

# List items can also be set to classes for groups of words that represent

274

# common concepts that occur in natural language. For example, rather than

275

# providing phrase hints for every month of the year, using the $MONTH class

276

# improves the likelihood of correctly transcribing audio that includes

# months.

"A String",

],

"boost": 3.14, # Hint Boost. Positive value will increase the probability that a specific

281

# phrase will be recognized over other similar sounding phrases. The higher

282

# the boost, the higher the chance of false positive recognition as well.

283

# Negative boost values would correspond to anti-biasing. Anti-biasing is not

284

# enabled, so negative boost will simply be ignored. Though `boost` can

285

# accept a wide range of positive values, most use cases are best served with

286

# values between 0 and 20. We recommend using a binary search approach to

287

# finding the optimal value for your use case.

288

},

289

],

290

"metadata": { # Description of audio data to be recognized. # *Optional* Metadata regarding this request.

291

"recordingDeviceType": "A String", # The type of device the speech was recorded with.

292

"originalMediaType": "A String", # The original media the speech was recorded on.

293

"microphoneDistance": "A String", # The audio type that most closely describes the audio being recognized.

294

"obfuscatedId": "A String", # Obfuscated (privacy-protected) ID of the user, to identify number of

295

# unique users using the service.

296

"recordingDeviceName": "A String", # The device used to make the recording. Examples 'Nexus 5X' or

297

# 'Polycom SoundStation IP 6000' or 'POTS' or 'VoIP' or

298

# 'Cardioid Microphone'.

299

"industryNaicsCodeOfAudio": 42, # The industry vertical to which this speech recognition request most

300

# closely applies. This is most indicative of the topics contained

301

# in the audio. Use the 6-digit NAICS code to identify the industry

302

# vertical - see https://www.naics.com/search/.

303

"audioTopic": "A String", # Description of the content. Eg. "Recordings of federal supreme court

304

# hearings from 2012".

305

"originalMimeType": "A String", # Mime type of the original audio file. For example `audio/m4a`,

306

# `audio/x-alaw-basic`, `audio/mp3`, `audio/3gpp`.

307

# A list of possible audio mime types is maintained at

308

# http://www.iana.org/assignments/media-types/media-types.xhtml#audio

309

"interactionType": "A String", # The use case most closely describing the audio content to be recognized.

},

},

}

x__xgafv: string, V1 error format.

Allowed values

1 - v1 error format

2 - v2 error format

Returns:

An object of the form:

321

322

{ # This resource represents a long-running operation that is the result of a

323

# network API call.

324

"metadata": { # Service-specific metadata associated with the operation. It typically

325

# contains progress information and common metadata such as create time.

326

# Some services might not provide such metadata. Any method that returns a

327

# long-running operation should document the metadata type, if any.

328

"a_key": "", # Properties of the object. Contains field @type with type URL.

329

},

330

"error": { # The `Status` type defines a logical error model that is suitable for # The error result of the operation in case of failure or cancellation.

331

# different programming environments, including REST APIs and RPC APIs. It is

332

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

333

# three pieces of data: error code, error message, and error details.

334

#

335

# You can find out more about this error model and how to work with it in the

336

# [API Design Guide](https://cloud.google.com/apis/design/errors).

337

"message": "A String", # A developer-facing error message, which should be in English. Any

338

# user-facing error message should be localized and sent in the

339

# google.rpc.Status.details field, or localized by the client.

340

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

341

"details": [ # A list of messages that carry the error details. There is a common set of

342

# message types for APIs to use.

343

{

344

"a_key": "", # Properties of the object. Contains field @type with type URL.

},

],

},

"done": True or False, # If the value is `false`, it means the operation is still in progress.

349

# If `true`, the operation is completed, and either `error` or `response` is

350

# available.

351

"response": { # The normal response of the operation in case of success. If the original

352

# method returns no data on success, such as `Delete`, the response is

353

# `google.protobuf.Empty`. If the original method is standard

354

# `Get`/`Create`/`Update`, the response should be the resource. For other

355

# methods, the response should have the type `XxxResponse`, where `Xxx`

356

# is the original method name. For example, if the original method name

357

# is `TakeSnapshot()`, the inferred response type is

358

# `TakeSnapshotResponse`.

359

"a_key": "", # Properties of the object. Contains field @type with type URL.

360

},

361

"name": "A String", # The server-assigned name, which is only unique within the same service that

362

# originally returns it. If you use the default HTTP mapping, the

363

# `name` should be a resource name ending with `operations/{unique_id}`.

}</pre>

</div>

<code class="details" id="recognize">recognize(body, x__xgafv=None)</code>

369

<pre>Performs synchronous speech recognition: receive results after all audio

370

has been sent and processed.

371

372

Args:

373

body: object, The request body. (required)

374

The object takes the form of:

375

376

{ # The top-level message sent by the client for the `Recognize` method.

377

"audio": { # Contains audio data in the encoding specified in the `RecognitionConfig`. # *Required* The audio data to be recognized.

378

# Either `content` or `uri` must be supplied. Supplying both or neither

379

# returns google.rpc.Code.INVALID_ARGUMENT. See

380

# [content limits](/speech-to-text/quotas#content).

381

"content": "A String", # The audio data bytes encoded as specified in

382

# `RecognitionConfig`. Note: as with all bytes fields, proto buffers use a

383

# pure binary representation, whereas JSON representations use base64.

384

"uri": "A String", # URI that points to a file that contains audio data bytes as specified in

385

# `RecognitionConfig`. The file must not be compressed (for example, gzip).

386

# Currently, only Google Cloud Storage URIs are

387

# supported, which must be specified in the following format:

388

# `gs://bucket_name/object_name` (other URI formats return

389

# google.rpc.Code.INVALID_ARGUMENT). For more information, see

390

# [Request URIs](https://cloud.google.com/storage/docs/reference-uris).

391

},

392

"config": { # Provides information to the recognizer that specifies how to process the # *Required* Provides information to the recognizer that specifies how to

393

# process the request.

394

# request.

395

"languageCode": "A String", # *Required* The language of the supplied audio as a

396

# [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.

397

# Example: "en-US".

398

# See [Language Support](/speech-to-text/docs/languages)

399

# for a list of the currently supported language codes.

400

"audioChannelCount": 42, # *Optional* The number of channels in the input audio data.

401

# ONLY set this for MULTI-CHANNEL recognition.

402

# Valid values for LINEAR16 and FLAC are `1`-`8`.

403

# Valid values for OGG_OPUS are '1'-'254'.

404

# Valid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only `1`.

405

# If `0` or omitted, defaults to one channel (mono).

406

# Note: We only recognize the first channel by default.

407

# To perform independent recognition on each channel set

408

# `enable_separate_recognition_per_channel` to 'true'.

409

"encoding": "A String", # Encoding of audio data sent in all `RecognitionAudio` messages.

410

# This field is optional for `FLAC` and `WAV` audio files and required

411

# for all other audio formats. For details, see AudioEncoding.

412

"enableAutomaticPunctuation": True or False, # *Optional* If 'true', adds punctuation to recognition result hypotheses.

413

# This feature is only available in select languages. Setting this for

414

# requests in other languages has no effect at all.

415

# The default 'false' value does not add punctuation to result hypotheses.

416

# Note: This is currently offered as an experimental service, complimentary

417

# to all users. In the future this may be exclusively available as a

418

# premium feature.

419

"alternativeLanguageCodes": [ # *Optional* A list of up to 3 additional

420

# [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,

421

# listing possible alternative languages of the supplied audio.

422

# See [Language Support](/speech-to-text/docs/languages)

423

# for a list of the currently supported language codes.

424

# If alternative languages are listed, recognition result will contain

425

# recognition in the most likely language detected including the main

426

# language_code. The recognition result will include the language tag

427

# of the language detected in the audio.

428

# Note: This feature is only supported for Voice Command and Voice Search

429

# use cases and performance may vary for other use cases (e.g., phone call

# transcription).

"A String",

],

"enableSeparateRecognitionPerChannel": True or False, # This needs to be set to `true` explicitly and `audio_channel_count` > 1

434

# to get each channel recognized separately. The recognition result will

435

# contain a `channel_tag` field to state which channel that result belongs

436

# to. If this is not true, we will only recognize the first channel. The

437

# request is billed cumulatively for all channels recognized:

438

# `audio_channel_count` multiplied by the length of the audio.

439

"enableWordTimeOffsets": True or False, # *Optional* If `true`, the top result includes a list of words and

440

# the start and end time offsets (timestamps) for those words. If

441

# `false`, no word-level time offset information is returned. The default is

442

# `false`.

443

"enableSpeakerDiarization": True or False, # *Optional* If 'true', enables speaker detection for each recognized word in

444

# the top alternative of the recognition result using a speaker_tag provided

445

# in the WordInfo.

446

# Note: Use diarization_config instead. This field will be DEPRECATED soon.

447

"maxAlternatives": 42, # *Optional* Maximum number of recognition hypotheses to be returned.

448

# Specifically, the maximum number of `SpeechRecognitionAlternative` messages

449

# within each `SpeechRecognitionResult`.

450

# The server may return fewer than `max_alternatives`.

451

# Valid values are `0`-`30`. A value of `0` or `1` will return a maximum of

452

# one. If omitted, will return a maximum of one.

453

"profanityFilter": True or False, # *Optional* If set to `true`, the server will attempt to filter out

454

# profanities, replacing all but the initial character in each filtered word

455

# with asterisks, e.g. "f***". If set to `false` or omitted, profanities

456

# won't be filtered out.

457

"useEnhanced": True or False, # *Optional* Set to true to use an enhanced model for speech recognition.

458

# If `use_enhanced` is set to true and the `model` field is not set, then

459

# an appropriate enhanced model is chosen if:

460

# 1. project is eligible for requesting enhanced models

461

# 2. an enhanced model exists for the audio

462

#

463

# If `use_enhanced` is true and an enhanced version of the specified model

464

# does not exist, then the speech is recognized using the standard version

465

# of the specified model.

466

#

467

# Enhanced speech models require that you opt-in to data logging using

468

# instructions in the

469

# [documentation](/speech-to-text/docs/enable-data-logging). If you set

470

# `use_enhanced` to true and you have not enabled audio logging, then you

471

# will receive an error.

472

"sampleRateHertz": 42, # Sample rate in Hertz of the audio data sent in all

473

# `RecognitionAudio` messages. Valid values are: 8000-48000.

474

# 16000 is optimal. For best results, set the sampling rate of the audio

475

# source to 16000 Hz. If that's not possible, use the native sample rate of

476

# the audio source (instead of re-sampling).

477

# This field is optional for FLAC and WAV audio files, but is

478

# required for all other audio formats. For details, see AudioEncoding.

479

"diarizationSpeakerCount": 42, # *Optional*

480

# If set, specifies the estimated number of speakers in the conversation.

481

# If not set, defaults to '2'.

482

# Ignored unless enable_speaker_diarization is set to true."

483

# Note: Use diarization_config instead. This field will be DEPRECATED soon.

484

"enableWordConfidence": True or False, # *Optional* If `true`, the top result includes a list of words and the

485

# confidence for those words. If `false`, no word-level confidence

486

# information is returned. The default is `false`.

487

"model": "A String", # *Optional* Which model to select for the given request. Select the model

488

# best suited to your domain to get best results. If a model is not

489

# explicitly specified, then we auto-select a model based on the parameters

490

# in the RecognitionConfig.

491

# <table>

492

# <tr>

493

# <td><b>Model</b></td>

494

# <td><b>Description</b></td>

495

# </tr>

496

# <tr>

497

# <td><code>command_and_search</code></td>

498

# <td>Best for short queries such as voice commands or voice search.</td>

499

# </tr>

500

# <tr>

501

# <td><code>phone_call</code></td>

502

# <td>Best for audio that originated from a phone call (typically

503

# recorded at an 8khz sampling rate).</td>

504

# </tr>

505

# <tr>

506

# <td><code>video</code></td>

507

# <td>Best for audio that originated from from video or includes multiple

508

# speakers. Ideally the audio is recorded at a 16khz or greater

509

# sampling rate. This is a premium model that costs more than the

510

# standard rate.</td>

511

# </tr>

512

# <tr>

513

# <td><code>default</code></td>

514

# <td>Best for audio that is not one of the specific audio models.

515

# For example, long-form audio. Ideally the audio is high-fidelity,

516

# recorded at a 16khz or greater sampling rate.</td>

517

# </tr>

518

# </table>

519

"diarizationConfig": { # *Optional* Config to enable speaker diarization and set additional

520

# parameters to make diarization better suited for your application.

521

# Note: When this is enabled, we send all the words from the beginning of the

522

# audio for the top alternative in every consecutive STREAMING responses.

523

# This is done in order to improve our speaker tags as our models learn to

524

# identify the speakers in the conversation over time.

525

# For non-streaming requests, the diarization results will be provided only

526

# in the top alternative of the FINAL SpeechRecognitionResult.

527

"minSpeakerCount": 42, # *Optional* Only used if diarization_speaker_count is not set.

528

# Minimum number of speakers in the conversation. This range gives you more

529

# flexibility by allowing the system to automatically determine the correct

530

# number of speakers. If not set, the default value is 2.

531

"enableSpeakerDiarization": True or False, # *Optional* If 'true', enables speaker detection for each recognized word in

532

# the top alternative of the recognition result using a speaker_tag provided

533

# in the WordInfo.

534

"maxSpeakerCount": 42, # *Optional* Only used if diarization_speaker_count is not set.

535

# Maximum number of speakers in the conversation. This range gives you more

536

# flexibility by allowing the system to automatically determine the correct

537

# number of speakers. If not set, the default value is 6.

538

},

539

"speechContexts": [ # *Optional* array of SpeechContext.

540

# A means to provide context to assist the speech recognition. For more

541

# information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).

542

{ # Provides "hints" to the speech recognizer to favor specific words and phrases

543

# in the results.

544

"phrases": [ # *Optional* A list of strings containing words and phrases "hints" so that

545

# the speech recognition is more likely to recognize them. This can be used

546

# to improve the accuracy for specific words and phrases, for example, if

547

# specific commands are typically spoken by the user. This can also be used

548

# to add additional words to the vocabulary of the recognizer. See

549

# [usage limits](/speech-to-text/quotas#content).

550

#

551

# List items can also be set to classes for groups of words that represent

552

# common concepts that occur in natural language. For example, rather than

553

# providing phrase hints for every month of the year, using the $MONTH class

554

# improves the likelihood of correctly transcribing audio that includes

# months.

"A String",

],

"boost": 3.14, # Hint Boost. Positive value will increase the probability that a specific

559

# phrase will be recognized over other similar sounding phrases. The higher

560

# the boost, the higher the chance of false positive recognition as well.

561

# Negative boost values would correspond to anti-biasing. Anti-biasing is not

562

# enabled, so negative boost will simply be ignored. Though `boost` can

563

# accept a wide range of positive values, most use cases are best served with

564

# values between 0 and 20. We recommend using a binary search approach to

565

# finding the optimal value for your use case.

566

},

567

],

568

"metadata": { # Description of audio data to be recognized. # *Optional* Metadata regarding this request.

569

"recordingDeviceType": "A String", # The type of device the speech was recorded with.

570

"originalMediaType": "A String", # The original media the speech was recorded on.

571

"microphoneDistance": "A String", # The audio type that most closely describes the audio being recognized.

572

"obfuscatedId": "A String", # Obfuscated (privacy-protected) ID of the user, to identify number of

573

# unique users using the service.

574

"recordingDeviceName": "A String", # The device used to make the recording. Examples 'Nexus 5X' or

575

# 'Polycom SoundStation IP 6000' or 'POTS' or 'VoIP' or

576

# 'Cardioid Microphone'.

577

"industryNaicsCodeOfAudio": 42, # The industry vertical to which this speech recognition request most

578

# closely applies. This is most indicative of the topics contained

579

# in the audio. Use the 6-digit NAICS code to identify the industry

580

# vertical - see https://www.naics.com/search/.

581

"audioTopic": "A String", # Description of the content. Eg. "Recordings of federal supreme court

582

# hearings from 2012".

583

"originalMimeType": "A String", # Mime type of the original audio file. For example `audio/m4a`,

584

# `audio/x-alaw-basic`, `audio/mp3`, `audio/3gpp`.

585

# A list of possible audio mime types is maintained at

586

# http://www.iana.org/assignments/media-types/media-types.xhtml#audio

587

"interactionType": "A String", # The use case most closely describing the audio content to be recognized.

588

},

589

},

590

"name": "A String", # *Optional* The name of the model to use for recognition.

591

}

592

593

x__xgafv: string, V1 error format.

Allowed values

1 - v1 error format

2 - v2 error format

Returns:

An object of the form:

600

601

{ # The only message returned to the client by the `Recognize` method. It

602

# contains the result as zero or more sequential `SpeechRecognitionResult`

603

# messages.

604

"results": [ # Output only. Sequential list of transcription results corresponding to

605

# sequential portions of audio.

606

{ # A speech recognition result corresponding to a portion of the audio.

607

"languageCode": "A String", # Output only. The

608

# [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the

609

# language in this result. This language code was detected to have the most

610

# likelihood of being spoken in the audio.

611

"alternatives": [ # Output only. May contain one or more recognition hypotheses (up to the

612

# maximum specified in `max_alternatives`).

613

# These alternatives are ordered in terms of accuracy, with the top (first)

614

# alternative being the most probable, as ranked by the recognizer.

615

{ # Alternative hypotheses (a.k.a. n-best list).

616

"confidence": 3.14, # Output only. The confidence estimate between 0.0 and 1.0. A higher number

617

# indicates an estimated greater likelihood that the recognized words are

618

# correct. This field is set only for the top alternative of a non-streaming

619

# result or, of a streaming result where `is_final=true`.

620

# This field is not guaranteed to be accurate and users should not rely on it

621

# to be always provided.

622

# The default of 0.0 is a sentinel value indicating `confidence` was not set.

623

"transcript": "A String", # Output only. Transcript text representing the words that the user spoke.

624

"words": [ # Output only. A list of word-specific information for each recognized word.

625

# Note: When `enable_speaker_diarization` is true, you will see all the words

626

# from the beginning of the audio.

627

{ # Word-specific information for recognized words.

628

"confidence": 3.14, # Output only. The confidence estimate between 0.0 and 1.0. A higher number

629

# indicates an estimated greater likelihood that the recognized words are

630

# correct. This field is set only for the top alternative of a non-streaming

631

# result or, of a streaming result where `is_final=true`.

632

# This field is not guaranteed to be accurate and users should not rely on it

633

# to be always provided.

634

# The default of 0.0 is a sentinel value indicating `confidence` was not set.

635

"endTime": "A String", # Output only. Time offset relative to the beginning of the audio,

636

# and corresponding to the end of the spoken word.

637

# This field is only set if `enable_word_time_offsets=true` and only

638

# in the top hypothesis.

639

# This is an experimental feature and the accuracy of the time offset can

640

# vary.

641

"word": "A String", # Output only. The word corresponding to this set of information.

642

"startTime": "A String", # Output only. Time offset relative to the beginning of the audio,

643

# and corresponding to the start of the spoken word.

644

# This field is only set if `enable_word_time_offsets=true` and only

645

# in the top hypothesis.

646

# This is an experimental feature and the accuracy of the time offset can

647

# vary.

648

"speakerTag": 42, # Output only. A distinct integer value is assigned for every speaker within

649

# the audio. This field specifies which one of those speakers was detected to

650

# have spoken this word. Value ranges from '1' to diarization_speaker_count.

651

# speaker_tag is set if enable_speaker_diarization = 'true' and only in the

# top alternative.

},

],

},

],

"channelTag": 42, # For multi-channel audio, this is the channel number corresponding to the

658

# recognized result for the audio from that channel.

659

# For audio_channel_count = N, its output values can range from '1' to 'N'.

},

],

}</pre>

</div>

</body></html>