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
|
{
"auth": {
"oauth2": {
"scopes": {
"https://www.googleapis.com/auth/cloud-platform": {
"description": "View and manage your data across Google Cloud Platform services"
}
}
}
},
"basePath": "",
"baseUrl": "https://speech.googleapis.com/",
"batchPath": "batch",
"canonicalName": "Speech",
"description": "Converts audio to text by applying powerful neural network models.",
"discoveryVersion": "v1",
"documentationLink": "https://cloud.google.com/speech-to-text/docs/quickstart-protocol",
"fullyEncodeReservedExpansion": true,
"icons": {
"x16": "http://www.google.com/images/icons/product/search-16.gif",
"x32": "http://www.google.com/images/icons/product/search-32.gif"
},
"id": "speech:v2beta",
"kind": "discovery#restDescription",
"name": "speech",
"ownerDomain": "google.com",
"ownerName": "Google",
"parameters": {
"$.xgafv": {
"description": "V1 error format.",
"enum": [
"1",
"2"
],
"enumDescriptions": [
"v1 error format",
"v2 error format"
],
"location": "query",
"type": "string"
},
"access_token": {
"description": "OAuth access token.",
"location": "query",
"type": "string"
},
"alt": {
"default": "json",
"description": "Data format for response.",
"enum": [
"json",
"media",
"proto"
],
"enumDescriptions": [
"Responses with Content-Type of application/json",
"Media download with context-dependent Content-Type",
"Responses with Content-Type of application/x-protobuf"
],
"location": "query",
"type": "string"
},
"callback": {
"description": "JSONP",
"location": "query",
"type": "string"
},
"fields": {
"description": "Selector specifying which fields to include in a partial response.",
"location": "query",
"type": "string"
},
"key": {
"description": "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.",
"location": "query",
"type": "string"
},
"oauth_token": {
"description": "OAuth 2.0 token for the current user.",
"location": "query",
"type": "string"
},
"prettyPrint": {
"default": "true",
"description": "Returns response with indentations and line breaks.",
"location": "query",
"type": "boolean"
},
"quotaUser": {
"description": "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.",
"location": "query",
"type": "string"
},
"uploadType": {
"description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").",
"location": "query",
"type": "string"
},
"upload_protocol": {
"description": "Upload protocol for media (e.g. \"raw\", \"multipart\").",
"location": "query",
"type": "string"
}
},
"protocol": "rest",
"resources": {
"projects": {
"resources": {
"locations": {
"resources": {
"operations": {
"methods": {
"get": {
"description": "Gets the latest state of a long-running operation. Clients can use this\nmethod to poll the operation result at intervals as recommended by the API\nservice.",
"flatPath": "v2beta/projects/{projectsId}/locations/{locationsId}/operations/{operationsId}",
"httpMethod": "GET",
"id": "speech.projects.locations.operations.get",
"parameterOrder": [
"name"
],
"parameters": {
"name": {
"description": "The name of the operation resource.",
"location": "path",
"pattern": "^projects/[^/]+/locations/[^/]+/operations/[^/]+$",
"required": true,
"type": "string"
}
},
"path": "v2beta/{+name}",
"response": {
"$ref": "Operation"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
]
},
"list": {
"description": "Lists operations that match the specified filter in the request. If the\nserver doesn't support this method, it returns `UNIMPLEMENTED`.\n\nNOTE: the `name` binding allows API services to override the binding\nto use different resource name schemes, such as `users/*/operations`. To\noverride the binding, API services can add a binding such as\n`\"/v1/{name=users/*}/operations\"` to their service configuration.\nFor backwards compatibility, the default name includes the operations\ncollection id, however overriding users must ensure the name binding\nis the parent resource, without the operations collection id.",
"flatPath": "v2beta/projects/{projectsId}/locations/{locationsId}/operations",
"httpMethod": "GET",
"id": "speech.projects.locations.operations.list",
"parameterOrder": [
"name"
],
"parameters": {
"filter": {
"description": "The standard list filter.",
"location": "query",
"type": "string"
},
"name": {
"description": "The name of the operation's parent resource.",
"location": "path",
"pattern": "^projects/[^/]+/locations/[^/]+$",
"required": true,
"type": "string"
},
"pageSize": {
"description": "The standard list page size.",
"format": "int32",
"location": "query",
"type": "integer"
},
"pageToken": {
"description": "The standard list page token.",
"location": "query",
"type": "string"
}
},
"path": "v2beta/{+name}/operations",
"response": {
"$ref": "ListOperationsResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
]
}
}
}
}
}
}
}
},
"revision": "20190918",
"rootUrl": "https://speech.googleapis.com/",
"schemas": {
"ListOperationsResponse": {
"description": "The response message for Operations.ListOperations.",
"id": "ListOperationsResponse",
"properties": {
"nextPageToken": {
"description": "The standard List next-page token.",
"type": "string"
},
"operations": {
"description": "A list of operations that matches the specified filter in the request.",
"items": {
"$ref": "Operation"
},
"type": "array"
}
},
"type": "object"
},
"LongRunningRecognizeMetadata": {
"description": "Describes the progress of a long-running `LongRunningRecognize` call. It is\nincluded in the `metadata` field of the `Operation` returned by the\n`GetOperation` call of the `google::longrunning::Operations` service.",
"id": "LongRunningRecognizeMetadata",
"properties": {
"lastUpdateTime": {
"description": "Output only. Time of the most recent processing update.",
"format": "google-datetime",
"type": "string"
},
"progressPercent": {
"description": "Output only. Approximate percentage of audio processed thus far. Guaranteed to be 100\nwhen the audio is fully processed and the results are available.",
"format": "int32",
"type": "integer"
},
"startTime": {
"description": "Output only. Time when the request was received.",
"format": "google-datetime",
"type": "string"
}
},
"type": "object"
},
"LongRunningRecognizeResponse": {
"description": "The only message returned to the client by the `LongRunningRecognize` method.\nIt contains the result as zero or more sequential SpeechRecognitionResult\nmessages. It is included in the `result.response` field of the `Operation`\nreturned by the `GetOperation` call of the `google::longrunning::Operations`\nservice.",
"id": "LongRunningRecognizeResponse",
"properties": {
"results": {
"description": "Output only. Sequential list of transcription results corresponding to\nsequential portions of audio.",
"items": {
"$ref": "SpeechRecognitionResult"
},
"type": "array"
}
},
"type": "object"
},
"Operation": {
"description": "This resource represents a long-running operation that is the result of a\nnetwork API call.",
"id": "Operation",
"properties": {
"done": {
"description": "If the value is `false`, it means the operation is still in progress.\nIf `true`, the operation is completed, and either `error` or `response` is\navailable.",
"type": "boolean"
},
"error": {
"$ref": "Status",
"description": "The error result of the operation in case of failure or cancellation."
},
"metadata": {
"additionalProperties": {
"description": "Properties of the object. Contains field @type with type URL.",
"type": "any"
},
"description": "Service-specific metadata associated with the operation. It typically\ncontains progress information and common metadata such as create time.\nSome services might not provide such metadata. Any method that returns a\nlong-running operation should document the metadata type, if any.",
"type": "object"
},
"name": {
"description": "The server-assigned name, which is only unique within the same service that\noriginally returns it. If you use the default HTTP mapping, the\n`name` should be a resource name ending with `operations/{unique_id}`.",
"type": "string"
},
"response": {
"additionalProperties": {
"description": "Properties of the object. Contains field @type with type URL.",
"type": "any"
},
"description": "The normal response of the operation in case of success. If the original\nmethod returns no data on success, such as `Delete`, the response is\n`google.protobuf.Empty`. If the original method is standard\n`Get`/`Create`/`Update`, the response should be the resource. For other\nmethods, the response should have the type `XxxResponse`, where `Xxx`\nis the original method name. For example, if the original method name\nis `TakeSnapshot()`, the inferred response type is\n`TakeSnapshotResponse`.",
"type": "object"
}
},
"type": "object"
},
"SpeechRecognitionAlternative": {
"description": "Alternative hypotheses (a.k.a. n-best list).",
"id": "SpeechRecognitionAlternative",
"properties": {
"confidence": {
"description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number\nindicates an estimated greater likelihood that the recognized words are\ncorrect. This field is set only for the top alternative of a non-streaming\nresult or, of a streaming result where `is_final=true`.\nThis field is not guaranteed to be accurate and users should not rely on it\nto be always provided.\nThe default of 0.0 is a sentinel value indicating `confidence` was not set.",
"format": "float",
"type": "number"
},
"transcript": {
"description": "Output only. Transcript text representing the words that the user spoke.",
"type": "string"
},
"words": {
"description": "Output only. A list of word-specific information for each recognized word.\nNote: When `enable_speaker_diarization` is true, you will see all the words\nfrom the beginning of the audio.",
"items": {
"$ref": "WordInfo"
},
"type": "array"
}
},
"type": "object"
},
"SpeechRecognitionResult": {
"description": "A speech recognition result corresponding to a portion of the audio.",
"id": "SpeechRecognitionResult",
"properties": {
"alternatives": {
"description": "Output only. May contain one or more recognition hypotheses (up to the\nmaximum specified in `max_alternatives`).\nThese alternatives are ordered in terms of accuracy, with the top (first)\nalternative being the most probable, as ranked by the recognizer.",
"items": {
"$ref": "SpeechRecognitionAlternative"
},
"type": "array"
},
"channelTag": {
"description": "Output only. For multi-channel audio, this is the channel number corresponding to the\nrecognized result for the audio from that channel.\nFor `audio_channel_count` = N, its output values can range from `1` to `N`.",
"format": "int32",
"type": "integer"
},
"languageCode": {
"description": "Output only. The\n[BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the\nlanguage in this result. This language code was detected to have the most\nlikelihood of being spoken in the audio.",
"type": "string"
}
},
"type": "object"
},
"Status": {
"description": "The `Status` type defines a logical error model that is suitable for\ndifferent programming environments, including REST APIs and RPC APIs. It is\nused by [gRPC](https://github.com/grpc). Each `Status` message contains\nthree pieces of data: error code, error message, and error details.\n\nYou can find out more about this error model and how to work with it in the\n[API Design Guide](https://cloud.google.com/apis/design/errors).",
"id": "Status",
"properties": {
"code": {
"description": "The status code, which should be an enum value of google.rpc.Code.",
"format": "int32",
"type": "integer"
},
"details": {
"description": "A list of messages that carry the error details. There is a common set of\nmessage types for APIs to use.",
"items": {
"additionalProperties": {
"description": "Properties of the object. Contains field @type with type URL.",
"type": "any"
},
"type": "object"
},
"type": "array"
},
"message": {
"description": "A developer-facing error message, which should be in English. Any\nuser-facing error message should be localized and sent in the\ngoogle.rpc.Status.details field, or localized by the client.",
"type": "string"
}
},
"type": "object"
},
"WordInfo": {
"description": "Word-specific information for recognized words.",
"id": "WordInfo",
"properties": {
"confidence": {
"description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number\nindicates an estimated greater likelihood that the recognized words are\ncorrect. This field is set only for the top alternative of a non-streaming\nresult or, of a streaming result where `is_final=true`.\nThis field is not guaranteed to be accurate and users should not rely on it\nto be always provided.\nThe default of 0.0 is a sentinel value indicating `confidence` was not set.",
"format": "float",
"type": "number"
},
"endOffset": {
"description": "Output only. Time offset relative to the beginning of the audio,\nand corresponding to the end of the spoken word.\nThis field is only set if `enable_word_time_offsets=true` and only\nin the top hypothesis.\nThis is an experimental feature and the accuracy of the time offset can\nvary.",
"format": "google-duration",
"type": "string"
},
"speakerTag": {
"description": "Output only. A distinct integer value is assigned for every speaker within\nthe audio. This field specifies which one of those speakers was detected to\nhave spoken this word. Value ranges from `1` to\n`diarization_speaker_count`. speaker_tag is set if\n`enable_speaker_diarization` = `true` and only in the top alternative.",
"format": "int32",
"type": "integer"
},
"startOffset": {
"description": "Output only. Time offset relative to the beginning of the audio,\nand corresponding to the start of the spoken word.\nThis field is only set if `enable_word_time_offsets=true` and only\nin the top hypothesis.\nThis is an experimental feature and the accuracy of the time offset can\nvary.",
"format": "google-duration",
"type": "string"
},
"word": {
"description": "Output only. The word corresponding to this set of information.",
"type": "string"
}
},
"type": "object"
}
},
"servicePath": "",
"title": "Cloud Speech-to-Text API",
"version": "v2beta",
"version_module": true
}
|
