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
|
{
"auth": {
"oauth2": {
"scopes": {
"https://www.googleapis.com/auth/cloud-platform": {
"description": "See, edit, configure, and delete your Google Cloud data and see the email address for your Google Account."
},
"https://www.googleapis.com/auth/dialogflow": {
"description": "View, manage and query your Dialogflow agents"
}
}
}
},
"basePath": "",
"baseUrl": "https://texttospeech.googleapis.com/",
"batchPath": "batch",
"canonicalName": "Texttospeech",
"description": "Synthesizes natural-sounding speech by applying powerful neural network models.",
"discoveryVersion": "v1",
"documentationLink": "https://cloud.google.com/text-to-speech/",
"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": "texttospeech:v1",
"kind": "discovery#restDescription",
"mtlsRootUrl": "https://texttospeech.mtls.googleapis.com/",
"name": "texttospeech",
"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": {
"datasets": {
"methods": {
"import": {
"description": "Imports audio+text data for training custom voice.",
"flatPath": "v1/projects/{projectsId}/locations/{locationsId}/datasets/{datasetsId}:import",
"httpMethod": "POST",
"id": "texttospeech.projects.locations.datasets.import",
"parameterOrder": [
"name"
],
"parameters": {
"name": {
"description": "The name of the Dataset resource. Format: `projects/{project}/locations/{location}/datasets/{dataset}`",
"location": "path",
"pattern": "^projects/[^/]+/locations/[^/]+/datasets/[^/]+$",
"required": true,
"type": "string"
}
},
"path": "v1/{+name}:import",
"request": {
"$ref": "ImportDataRequest"
},
"response": {
"$ref": "Operation"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/dialogflow"
]
}
}
}
}
}
}
},
"text": {
"methods": {
"synthesize": {
"description": "Synthesizes speech synchronously: receive results after all text input has been processed.",
"flatPath": "v1/text:synthesize",
"httpMethod": "POST",
"id": "texttospeech.text.synthesize",
"parameterOrder": [],
"parameters": {},
"path": "v1/text:synthesize",
"request": {
"$ref": "SynthesizeSpeechRequest"
},
"response": {
"$ref": "SynthesizeSpeechResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
]
}
}
},
"voices": {
"methods": {
"list": {
"description": "Returns a list of Voice supported for synthesis.",
"flatPath": "v1/voices",
"httpMethod": "GET",
"id": "texttospeech.voices.list",
"parameterOrder": [],
"parameters": {
"languageCode": {
"description": "Optional. Recommended. [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag. If not specified, the API will return all supported voices. If specified, the ListVoices call will only return voices that can be used to synthesize this language_code. E.g. when specifying `\"en-NZ\"`, you will get supported `\"en-NZ\"` voices; when specifying `\"no\"`, you will get supported `\"no-\\*\"` (Norwegian) and `\"nb-\\*\"` (Norwegian Bokmal) voices; specifying `\"zh\"` will also get supported `\"cmn-\\*\"` voices; specifying `\"zh-hk\"` will also get supported `\"yue-hk\"` voices.",
"location": "query",
"type": "string"
}
},
"path": "v1/voices",
"response": {
"$ref": "ListVoicesResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
]
}
}
}
},
"revision": "20211105",
"rootUrl": "https://texttospeech.googleapis.com/",
"schemas": {
"AudioConfig": {
"description": "Description of audio data to be synthesized.",
"id": "AudioConfig",
"properties": {
"audioEncoding": {
"description": "Required. The format of the audio byte stream.",
"enum": [
"AUDIO_ENCODING_UNSPECIFIED",
"LINEAR16",
"MP3",
"OGG_OPUS",
"MULAW",
"ALAW"
],
"enumDescriptions": [
"Not specified. Will return result google.rpc.Code.INVALID_ARGUMENT.",
"Uncompressed 16-bit signed little-endian samples (Linear PCM). Audio content returned as LINEAR16 also contains a WAV header.",
"MP3 audio at 32kbps.",
"Opus encoded audio wrapped in an ogg container. The result will be a file which can be played natively on Android, and in browsers (at least Chrome and Firefox). The quality of the encoding is considerably higher than MP3 while using approximately the same bitrate.",
"8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law. Audio content returned as MULAW also contains a WAV header.",
"8-bit samples that compand 14-bit audio samples using G.711 PCMU/A-law. Audio content returned as ALAW also contains a WAV header."
],
"type": "string"
},
"effectsProfileId": {
"description": "Optional. Input only. An identifier which selects 'audio effects' profiles that are applied on (post synthesized) text to speech. Effects are applied on top of each other in the order they are given. See [audio profiles](https://cloud.google.com/text-to-speech/docs/audio-profiles) for current supported profile ids.",
"items": {
"type": "string"
},
"type": "array"
},
"pitch": {
"description": "Optional. Input only. Speaking pitch, in the range [-20.0, 20.0]. 20 means increase 20 semitones from the original pitch. -20 means decrease 20 semitones from the original pitch.",
"format": "double",
"type": "number"
},
"sampleRateHertz": {
"description": "Optional. The synthesis sample rate (in hertz) for this audio. When this is specified in SynthesizeSpeechRequest, if this is different from the voice's natural sample rate, then the synthesizer will honor this request by converting to the desired sample rate (which might result in worse audio quality), unless the specified sample rate is not supported for the encoding chosen, in which case it will fail the request and return google.rpc.Code.INVALID_ARGUMENT.",
"format": "int32",
"type": "integer"
},
"speakingRate": {
"description": "Optional. Input only. Speaking rate/speed, in the range [0.25, 4.0]. 1.0 is the normal native speed supported by the specific voice. 2.0 is twice as fast, and 0.5 is half as fast. If unset(0.0), defaults to the native 1.0 speed. Any other values \u003c 0.25 or \u003e 4.0 will return an error.",
"format": "double",
"type": "number"
},
"volumeGainDb": {
"description": "Optional. Input only. Volume gain (in dB) of the normal native volume supported by the specific voice, in the range [-96.0, 16.0]. If unset, or set to a value of 0.0 (dB), will play at normal native signal amplitude. A value of -6.0 (dB) will play at approximately half the amplitude of the normal native signal amplitude. A value of +6.0 (dB) will play at approximately twice the amplitude of the normal native signal amplitude. Strongly recommend not to exceed +10 (dB) as there's usually no effective increase in loudness for any value greater than that.",
"format": "double",
"type": "number"
}
},
"type": "object"
},
"ImportDataRequest": {
"description": "A request to import data.",
"id": "ImportDataRequest",
"properties": {
"csvCloudStorageUri": {
"description": "Customer provide a Cloud Storage link which point to a .csv file which stores all the truth text and Cloud Storage link of audio data.",
"type": "string"
}
},
"type": "object"
},
"ListVoicesResponse": {
"description": "The message returned to the client by the `ListVoices` method.",
"id": "ListVoicesResponse",
"properties": {
"voices": {
"description": "The list of voices.",
"items": {
"$ref": "Voice"
},
"type": "array"
}
},
"type": "object"
},
"Operation": {
"description": "This resource represents a long-running operation that is the result of a network API call.",
"id": "Operation",
"properties": {
"done": {
"description": "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.",
"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 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.",
"type": "object"
},
"name": {
"description": "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}`.",
"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 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`.",
"type": "object"
}
},
"type": "object"
},
"Status": {
"description": "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).",
"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 message 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 user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.",
"type": "string"
}
},
"type": "object"
},
"SynthesisInput": {
"description": "Contains text input to be synthesized. Either `text` or `ssml` must be supplied. Supplying both or neither returns google.rpc.Code.INVALID_ARGUMENT. The input size is limited to 5000 characters.",
"id": "SynthesisInput",
"properties": {
"ssml": {
"description": "The SSML document to be synthesized. The SSML document must be valid and well-formed. Otherwise the RPC will fail and return google.rpc.Code.INVALID_ARGUMENT. For more information, see [SSML](https://cloud.google.com/text-to-speech/docs/ssml).",
"type": "string"
},
"text": {
"description": "The raw text to be synthesized.",
"type": "string"
}
},
"type": "object"
},
"SynthesizeSpeechRequest": {
"description": "The top-level message sent by the client for the `SynthesizeSpeech` method.",
"id": "SynthesizeSpeechRequest",
"properties": {
"audioConfig": {
"$ref": "AudioConfig",
"description": "Required. The configuration of the synthesized audio."
},
"input": {
"$ref": "SynthesisInput",
"description": "Required. The Synthesizer requires either plain text or SSML as input."
},
"voice": {
"$ref": "VoiceSelectionParams",
"description": "Required. The desired voice of the synthesized audio."
}
},
"type": "object"
},
"SynthesizeSpeechResponse": {
"description": "The message returned to the client by the `SynthesizeSpeech` method.",
"id": "SynthesizeSpeechResponse",
"properties": {
"audioContent": {
"description": "The audio data bytes encoded as specified in the request, including the header for encodings that are wrapped in containers (e.g. MP3, OGG_OPUS). For LINEAR16 audio, we include the WAV header. Note: as with all bytes fields, protobuffers use a pure binary representation, whereas JSON representations use base64.",
"format": "byte",
"type": "string"
}
},
"type": "object"
},
"Voice": {
"description": "Description of a voice supported by the TTS service.",
"id": "Voice",
"properties": {
"languageCodes": {
"description": "The languages that this voice supports, expressed as [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags (e.g. \"en-US\", \"es-419\", \"cmn-tw\").",
"items": {
"type": "string"
},
"type": "array"
},
"name": {
"description": "The name of this voice. Each distinct voice has a unique name.",
"type": "string"
},
"naturalSampleRateHertz": {
"description": "The natural sample rate (in hertz) for this voice.",
"format": "int32",
"type": "integer"
},
"ssmlGender": {
"description": "The gender of this voice.",
"enum": [
"SSML_VOICE_GENDER_UNSPECIFIED",
"MALE",
"FEMALE",
"NEUTRAL"
],
"enumDescriptions": [
"An unspecified gender. In VoiceSelectionParams, this means that the client doesn't care which gender the selected voice will have. In the Voice field of ListVoicesResponse, this may mean that the voice doesn't fit any of the other categories in this enum, or that the gender of the voice isn't known.",
"A male voice.",
"A female voice.",
"A gender-neutral voice. This voice is not yet supported."
],
"type": "string"
}
},
"type": "object"
},
"VoiceSelectionParams": {
"description": "Description of which voice to use for a synthesis request.",
"id": "VoiceSelectionParams",
"properties": {
"languageCode": {
"description": "Required. The language (and potentially also the region) of the voice expressed as a [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag, e.g. \"en-US\". This should not include a script tag (e.g. use \"cmn-cn\" rather than \"cmn-Hant-cn\"), because the script will be inferred from the input provided in the SynthesisInput. The TTS service will use this parameter to help choose an appropriate voice. Note that the TTS service may choose a voice with a slightly different language code than the one selected; it may substitute a different region (e.g. using en-US rather than en-CA if there isn't a Canadian voice available), or even a different language, e.g. using \"nb\" (Norwegian Bokmal) instead of \"no\" (Norwegian)\".",
"type": "string"
},
"name": {
"description": "The name of the voice. If not set, the service will choose a voice based on the other parameters such as language_code and gender.",
"type": "string"
},
"ssmlGender": {
"description": "The preferred gender of the voice. If not set, the service will choose a voice based on the other parameters such as language_code and name. Note that this is only a preference, not requirement; if a voice of the appropriate gender is not available, the synthesizer should substitute a voice with a different gender rather than failing the request.",
"enum": [
"SSML_VOICE_GENDER_UNSPECIFIED",
"MALE",
"FEMALE",
"NEUTRAL"
],
"enumDescriptions": [
"An unspecified gender. In VoiceSelectionParams, this means that the client doesn't care which gender the selected voice will have. In the Voice field of ListVoicesResponse, this may mean that the voice doesn't fit any of the other categories in this enum, or that the gender of the voice isn't known.",
"A male voice.",
"A female voice.",
"A gender-neutral voice. This voice is not yet supported."
],
"type": "string"
}
},
"type": "object"
}
},
"servicePath": "",
"title": "Cloud Text-to-Speech API",
"version": "v1",
"version_module": true
}
|
