Blame - docs/dyn/speech_v1beta1.speech.html - platform/external/python/google-api-python-client

"config": { # The `RecognitionConfig` message provides information to the recognizer # [Required] The `config` message provides information to the recognizer

112

# that specifies how to process the request.

113

# that specifies how to process the request.

114

"languageCode": "A String", # [Optional] The language of the supplied audio as a BCP-47 language tag.

115

# Example: "en-GB" https://www.rfc-editor.org/rfc/bcp/bcp47.txt

116

# If omitted, defaults to "en-US". See

117

# [Language Support](https://cloud.google.com/speech/docs/best-practices#language_support)

118

# for a list of the currently supported language codes.

119

"speechContext": { # Provides "hints" to the speech recognizer to favor specific words and phrases # [Optional] A means to provide context to assist the speech recognition.

120

# in the results.

121

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

122

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

123

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

124

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

125

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

126

# [usage limits](https://cloud.google.com/speech/limits#content).

"A String",

],

},

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

131

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

132

# Specifically, the maximum number of `SpeechRecognitionAlternative` messages

133

# within each `SpeechRecognitionResult`.

134

# The server may return fewer than `max_alternatives`.

135

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

136

# `1`. If omitted, defaults to `1`.

137

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

138

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

139

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

140

# won't be filtered out.

141

"sampleRate": 42, # [Required] Sample rate in Hertz of the audio data sent in all

142

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

143

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

144

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

145

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

},

}

x__xgafv: string, V1 error format.

Allowed values

1 - v1 error format

2 - v2 error format

Returns:

An object of the form:

156

157

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

158

# network API call.

159

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

160

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

161

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

162

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

163

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

164

},

165

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

166

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

167

# available.

168

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

169

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

170

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

171

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

172

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

173

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

174

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

175

# `TakeSnapshotResponse`.

176

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

177

},

178

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

179

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

180

# `name` should have the format of `operations/some/unique/name`.

181

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

182

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

183

# [gRPC](https://github.com/grpc). The error model is designed to be:

184

#

185

# - Simple to use and understand for most users

186

# - Flexible enough to meet unexpected needs

#

# # Overview

#

# The `Status` message contains three pieces of data: error code, error message,

191

# and error details. The error code should be an enum value of

192

# google.rpc.Code, but it may accept additional error codes if needed. The

193

# error message should be a developer-facing English message that helps

194

# developers *understand* and *resolve* the error. If a localized user-facing

195

# error message is needed, put the localized message in the error details or

196

# localize it in the client. The optional error details may contain arbitrary

197

# information about the error. There is a predefined set of error detail types

198

# in the package `google.rpc` which can be used for common error conditions.

#

# # Language mapping

#

# The `Status` message is the logical representation of the error model, but it

203

# is not necessarily the actual wire format. When the `Status` message is

204

# exposed in different client libraries and different wire protocols, it can be

205

# mapped differently. For example, it will likely be mapped to some exceptions

206

# in Java, but more likely mapped to some error codes in C.

#

# # Other uses

#

# The error model and the `Status` message can be used in a variety of

211

# environments, either with or without APIs, to provide a

212

# consistent developer experience across different environments.

213

#

214

# Example uses of this error model include:

215

#

216

# - Partial errors. If a service needs to return partial errors to the client,

217

# it may embed the `Status` in the normal response to indicate the partial

218

# errors.

219

#

220

# - Workflow errors. A typical workflow has multiple steps. Each step may

221

# have a `Status` message for error reporting purpose.

222

#

223

# - Batch operations. If a client uses batch request and batch response, the

224

# `Status` message should be used directly inside batch response, one for

225

# each error sub-response.

226

#

227

# - Asynchronous operations. If an API call embeds asynchronous operation

228

# results in its response, the status of those operations should be

229

# represented directly using the `Status` message.

230

#

231

# - Logging. If some API errors are stored in logs, the message `Status` could

232

# be used directly after any stripping needed for security/privacy reasons.

233

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

234

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

235

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

236

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

237

"details": [ # A list of messages that carry the error details. There will be a

238

# common set of message types for APIs to use.

239

{

240

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

},

],

},

}</pre>

</div>

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

249

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

250

has been sent and processed.

251

252

Args:

253

body: object, The request body. (required)

254

The object takes the form of:

255

256

{ # `SyncRecognizeRequest` is the top-level message sent by the client for

257

# the `SyncRecognize` method.

258

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

259

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

260

# returns google.rpc.Code.INVALID_ARGUMENT. See

261

# [audio limits](https://cloud.google.com/speech/limits#content).

262

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

263

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

264

# pure binary representation, whereas JSON representations use base64.

265

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

266

# `RecognitionConfig`. Currently, only Google Cloud Storage URIs are

267

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

268

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

269

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

270

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

271

},

272

"config": { # The `RecognitionConfig` message provides information to the recognizer # [Required] The `config` message provides information to the recognizer

273

# that specifies how to process the request.

274

# that specifies how to process the request.

275

"languageCode": "A String", # [Optional] The language of the supplied audio as a BCP-47 language tag.

276

# Example: "en-GB" https://www.rfc-editor.org/rfc/bcp/bcp47.txt

277

# If omitted, defaults to "en-US". See

278

# [Language Support](https://cloud.google.com/speech/docs/best-practices#language_support)

279

# for a list of the currently supported language codes.

280

"speechContext": { # Provides "hints" to the speech recognizer to favor specific words and phrases # [Optional] A means to provide context to assist the speech recognition.

281

# in the results.

282

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

283

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

284

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

285

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

286

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

287

# [usage limits](https://cloud.google.com/speech/limits#content).

"A String",

],

},

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

292

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

293

# Specifically, the maximum number of `SpeechRecognitionAlternative` messages

294

# within each `SpeechRecognitionResult`.

295

# The server may return fewer than `max_alternatives`.

296

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

297

# `1`. If omitted, defaults to `1`.

298

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

299

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

300

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

301

# won't be filtered out.

302

"sampleRate": 42, # [Required] Sample rate in Hertz of the audio data sent in all

303

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

304

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

305

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

306

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

},

}

x__xgafv: string, V1 error format.

Allowed values

1 - v1 error format

2 - v2 error format

Returns:

An object of the form:

317

318

{ # `SyncRecognizeResponse` is the only message returned to the client by

319

# `SyncRecognize`. It contains the result as zero or more sequential

320

# `SpeechRecognitionResult` messages.

321

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

322

# sequential portions of audio.

323

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

324

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

325

# maximum specified in `max_alternatives`).

326

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

327

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

328

# means the system is more confident that the recognition is correct.

329

# This field is typically provided only for the top hypothesis, and only for

330

# `is_final=true` results.

331

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

332

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

},

],

},

],

}</pre>

</div>

</body></html>