1{
2 "auth": {
3 "oauth2": {
4 "scopes": {
5 "https://www.googleapis.com/auth/cloud-platform": {
6 "description": "View and manage your data across Google Cloud Platform services"
7 }
8 }
9 }
10 },
11 "basePath": "",
12 "baseUrl": "https://speech.googleapis.com/",
13 "batchPath": "batch",
14 "canonicalName": "Speech",
15 "description": "Converts audio to text by applying powerful neural network models.",
16 "discoveryVersion": "v1",
17 "documentationLink": "https://cloud.google.com/speech-to-text/docs/quickstart-protocol",
18 "fullyEncodeReservedExpansion": true,
19 "icons": {
20 "x16": "http://www.google.com/images/icons/product/search-16.gif",
21 "x32": "http://www.google.com/images/icons/product/search-32.gif"
22 },
23 "id": "speech:v2beta",
24 "kind": "discovery#restDescription",
25 "name": "speech",
26 "ownerDomain": "google.com",
27 "ownerName": "Google",
28 "parameters": {
29 "$.xgafv": {
30 "description": "V1 error format.",
31 "enum": [
32 "1",
33 "2"
34 ],
35 "enumDescriptions": [
36 "v1 error format",
37 "v2 error format"
38 ],
39 "location": "query",
40 "type": "string"
41 },
42 "access_token": {
43 "description": "OAuth access token.",
44 "location": "query",
45 "type": "string"
46 },
47 "alt": {
48 "default": "json",
49 "description": "Data format for response.",
50 "enum": [
51 "json",
52 "media",
53 "proto"
54 ],
55 "enumDescriptions": [
56 "Responses with Content-Type of application/json",
57 "Media download with context-dependent Content-Type",
58 "Responses with Content-Type of application/x-protobuf"
59 ],
60 "location": "query",
61 "type": "string"
62 },
63 "callback": {
64 "description": "JSONP",
65 "location": "query",
66 "type": "string"
67 },
68 "fields": {
69 "description": "Selector specifying which fields to include in a partial response.",
70 "location": "query",
71 "type": "string"
72 },
73 "key": {
74 "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.",
75 "location": "query",
76 "type": "string"
77 },
78 "oauth_token": {
79 "description": "OAuth 2.0 token for the current user.",
80 "location": "query",
81 "type": "string"
82 },
83 "prettyPrint": {
84 "default": "true",
85 "description": "Returns response with indentations and line breaks.",
86 "location": "query",
87 "type": "boolean"
88 },
89 "quotaUser": {
90 "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.",
91 "location": "query",
92 "type": "string"
93 },
94 "uploadType": {
95 "description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").",
96 "location": "query",
97 "type": "string"
98 },
99 "upload_protocol": {
100 "description": "Upload protocol for media (e.g. \"raw\", \"multipart\").",
101 "location": "query",
102 "type": "string"
103 }
104 },
105 "protocol": "rest",
106 "resources": {
107 "projects": {
108 "resources": {
109 "locations": {
110 "resources": {
111 "operations": {
112 "methods": {
113 "get": {
114 "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.",
115 "flatPath": "v2beta/projects/{projectsId}/locations/{locationsId}/operations/{operationsId}",
116 "httpMethod": "GET",
117 "id": "speech.projects.locations.operations.get",
118 "parameterOrder": [
119 "name"
120 ],
121 "parameters": {
122 "name": {
123 "description": "The name of the operation resource.",
124 "location": "path",
125 "pattern": "^projects/[^/]+/locations/[^/]+/operations/[^/]+$",
126 "required": true,
127 "type": "string"
128 }
129 },
130 "path": "v2beta/{+name}",
131 "response": {
132 "$ref": "Operation"
133 },
134 "scopes": [
135 "https://www.googleapis.com/auth/cloud-platform"
136 ]
137 },
138 "list": {
139 "description": "Lists operations that match the specified filter in the request. If the\nserver doesn't support this method, it returns `UNIMPLEMENTED`.\n\nNOTE: the `name` binding allows API services to override the binding\nto use different resource name schemes, such as `users/*/operations`. To\noverride the binding, API services can add a binding such as\n`\"/v1/{name=users/*}/operations\"` to their service configuration.\nFor backwards compatibility, the default name includes the operations\ncollection id, however overriding users must ensure the name binding\nis the parent resource, without the operations collection id.",
140 "flatPath": "v2beta/projects/{projectsId}/locations/{locationsId}/operations",
141 "httpMethod": "GET",
142 "id": "speech.projects.locations.operations.list",
143 "parameterOrder": [
144 "name"
145 ],
146 "parameters": {
147 "filter": {
148 "description": "The standard list filter.",
149 "location": "query",
150 "type": "string"
151 },
152 "name": {
153 "description": "The name of the operation's parent resource.",
154 "location": "path",
155 "pattern": "^projects/[^/]+/locations/[^/]+$",
156 "required": true,
157 "type": "string"
158 },
159 "pageSize": {
160 "description": "The standard list page size.",
161 "format": "int32",
162 "location": "query",
163 "type": "integer"
164 },
165 "pageToken": {
166 "description": "The standard list page token.",
167 "location": "query",
168 "type": "string"
169 }
170 },
171 "path": "v2beta/{+name}/operations",
172 "response": {
173 "$ref": "ListOperationsResponse"
174 },
175 "scopes": [
176 "https://www.googleapis.com/auth/cloud-platform"
177 ]
178 }
179 }
180 }
181 }
182 }
183 }
184 }
185 },
186 "revision": "20190918",
187 "rootUrl": "https://speech.googleapis.com/",
188 "schemas": {
189 "ListOperationsResponse": {
190 "description": "The response message for Operations.ListOperations.",
191 "id": "ListOperationsResponse",
192 "properties": {
193 "nextPageToken": {
194 "description": "The standard List next-page token.",
195 "type": "string"
196 },
197 "operations": {
198 "description": "A list of operations that matches the specified filter in the request.",
199 "items": {
200 "$ref": "Operation"
201 },
202 "type": "array"
203 }
204 },
205 "type": "object"
206 },
207 "LongRunningRecognizeMetadata": {
208 "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.",
209 "id": "LongRunningRecognizeMetadata",
210 "properties": {
211 "lastUpdateTime": {
212 "description": "Output only. Time of the most recent processing update.",
213 "format": "google-datetime",
214 "type": "string"
215 },
216 "progressPercent": {
217 "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.",
218 "format": "int32",
219 "type": "integer"
220 },
221 "startTime": {
222 "description": "Output only. Time when the request was received.",
223 "format": "google-datetime",
224 "type": "string"
225 }
226 },
227 "type": "object"
228 },
229 "LongRunningRecognizeResponse": {
230 "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.",
231 "id": "LongRunningRecognizeResponse",
232 "properties": {
233 "results": {
234 "description": "Output only. Sequential list of transcription results corresponding to\nsequential portions of audio.",
235 "items": {
236 "$ref": "SpeechRecognitionResult"
237 },
238 "type": "array"
239 }
240 },
241 "type": "object"
242 },
243 "Operation": {
244 "description": "This resource represents a long-running operation that is the result of a\nnetwork API call.",
245 "id": "Operation",
246 "properties": {
247 "done": {
248 "description": "If the value is `false`, it means the operation is still in progress.\nIf `true`, the operation is completed, and either `error` or `response` is\navailable.",
249 "type": "boolean"
250 },
251 "error": {
252 "$ref": "Status",
253 "description": "The error result of the operation in case of failure or cancellation."
254 },
255 "metadata": {
256 "additionalProperties": {
257 "description": "Properties of the object. Contains field @type with type URL.",
258 "type": "any"
259 },
260 "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.",
261 "type": "object"
262 },
263 "name": {
264 "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}`.",
265 "type": "string"
266 },
267 "response": {
268 "additionalProperties": {
269 "description": "Properties of the object. Contains field @type with type URL.",
270 "type": "any"
271 },
272 "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`.",
273 "type": "object"
274 }
275 },
276 "type": "object"
277 },
278 "SpeechRecognitionAlternative": {
279 "description": "Alternative hypotheses (a.k.a. n-best list).",
280 "id": "SpeechRecognitionAlternative",
281 "properties": {
282 "confidence": {
283 "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.",
284 "format": "float",
285 "type": "number"
286 },
287 "transcript": {
288 "description": "Output only. Transcript text representing the words that the user spoke.",
289 "type": "string"
290 },
291 "words": {
292 "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.",
293 "items": {
294 "$ref": "WordInfo"
295 },
296 "type": "array"
297 }
298 },
299 "type": "object"
300 },
301 "SpeechRecognitionResult": {
302 "description": "A speech recognition result corresponding to a portion of the audio.",
303 "id": "SpeechRecognitionResult",
304 "properties": {
305 "alternatives": {
306 "description": "Output only. May contain one or more recognition hypotheses (up to the\nmaximum specified in `max_alternatives`).\nThese alternatives are ordered in terms of accuracy, with the top (first)\nalternative being the most probable, as ranked by the recognizer.",
307 "items": {
308 "$ref": "SpeechRecognitionAlternative"
309 },
310 "type": "array"
311 },
312 "channelTag": {
313 "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`.",
314 "format": "int32",
315 "type": "integer"
316 },
317 "languageCode": {
318 "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.",
319 "type": "string"
320 }
321 },
322 "type": "object"
323 },
324 "Status": {
325 "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).",
326 "id": "Status",
327 "properties": {
328 "code": {
329 "description": "The status code, which should be an enum value of google.rpc.Code.",
330 "format": "int32",
331 "type": "integer"
332 },
333 "details": {
334 "description": "A list of messages that carry the error details. There is a common set of\nmessage types for APIs to use.",
335 "items": {
336 "additionalProperties": {
337 "description": "Properties of the object. Contains field @type with type URL.",
338 "type": "any"
339 },
340 "type": "object"
341 },
342 "type": "array"
343 },
344 "message": {
345 "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.",
346 "type": "string"
347 }
348 },
349 "type": "object"
350 },
351 "WordInfo": {
352 "description": "Word-specific information for recognized words.",
353 "id": "WordInfo",
354 "properties": {
355 "confidence": {
356 "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.",
357 "format": "float",
358 "type": "number"
359 },
360 "endOffset": {
361 "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.",
362 "format": "google-duration",
363 "type": "string"
364 },
365 "speakerTag": {
366 "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.",
367 "format": "int32",
368 "type": "integer"
369 },
370 "startOffset": {
371 "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.",
372 "format": "google-duration",
373 "type": "string"
374 },
375 "word": {
376 "description": "Output only. The word corresponding to this set of information.",
377 "type": "string"
378 }
379 },
380 "type": "object"
381 }
382 },
383 "servicePath": "",
384 "title": "Cloud Speech-to-Text API",
385 "version": "v2beta",
386 "version_module": true
387}View as plain text