v1.d.ts
13.6 KB
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
/**
* Copyright 2019 Google LLC
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
import { OAuth2Client, JWT, Compute, UserRefreshClient } from 'google-auth-library';
import { GoogleConfigurable, MethodOptions, GlobalOptions, BodyResponseCallback, APIRequestContext } from 'googleapis-common';
import { GaxiosPromise } from 'gaxios';
export declare namespace texttospeech_v1 {
export interface Options extends GlobalOptions {
version: 'v1';
}
interface StandardParameters {
/**
* V1 error format.
*/
'$.xgafv'?: string;
/**
* OAuth access token.
*/
access_token?: string;
/**
* Data format for response.
*/
alt?: string;
/**
* JSONP
*/
callback?: string;
/**
* Selector specifying which fields to include in a partial response.
*/
fields?: string;
/**
* API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.
*/
key?: string;
/**
* OAuth 2.0 token for the current user.
*/
oauth_token?: string;
/**
* Returns response with indentations and line breaks.
*/
prettyPrint?: boolean;
/**
* Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.
*/
quotaUser?: string;
/**
* Legacy upload protocol for media (e.g. "media", "multipart").
*/
uploadType?: string;
/**
* Upload protocol for media (e.g. "raw", "multipart").
*/
upload_protocol?: string;
}
/**
* Cloud Text-to-Speech API
*
* Synthesizes natural-sounding speech by applying powerful neural network models.
*
* @example
* const {google} = require('googleapis');
* const texttospeech = google.texttospeech('v1');
*
* @namespace texttospeech
* @type {Function}
* @version v1
* @variation v1
* @param {object=} options Options for Texttospeech
*/
export class Texttospeech {
context: APIRequestContext;
text: Resource$Text;
voices: Resource$Voices;
constructor(options: GlobalOptions, google?: GoogleConfigurable);
}
/**
* Description of audio data to be synthesized.
*/
export interface Schema$AudioConfig {
/**
* Required. The format of the audio byte stream.
*/
audioEncoding?: string | null;
/**
* 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.
*/
effectsProfileId?: string[] | null;
/**
* 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.
*/
pitch?: number | null;
/**
* 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.
*/
sampleRateHertz?: number | null;
/**
* 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 < 0.25 or > 4.0 will return an error.
*/
speakingRate?: number | null;
/**
* 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.
*/
volumeGainDb?: number | null;
}
/**
* The message returned to the client by the `ListVoices` method.
*/
export interface Schema$ListVoicesResponse {
/**
* The list of voices.
*/
voices?: Schema$Voice[];
}
/**
* 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.
*/
export interface Schema$SynthesisInput {
/**
* The SSML document to be synthesized. The SSML document must be valid and well-formed. Otherwise the RPC will fail and return google.rpc.Code.INVALID_ARGUMENT. For more information, see [SSML](/speech/text-to-speech/docs/ssml).
*/
ssml?: string | null;
/**
* The raw text to be synthesized.
*/
text?: string | null;
}
/**
* The top-level message sent by the client for the `SynthesizeSpeech` method.
*/
export interface Schema$SynthesizeSpeechRequest {
/**
* Required. The configuration of the synthesized audio.
*/
audioConfig?: Schema$AudioConfig;
/**
* Required. The Synthesizer requires either plain text or SSML as input.
*/
input?: Schema$SynthesisInput;
/**
* Required. The desired voice of the synthesized audio.
*/
voice?: Schema$VoiceSelectionParams;
}
/**
* The message returned to the client by the `SynthesizeSpeech` method.
*/
export interface Schema$SynthesizeSpeechResponse {
/**
* 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.
*/
audioContent?: string | null;
}
/**
* Description of a voice supported by the TTS service.
*/
export interface Schema$Voice {
/**
* The languages that this voice supports, expressed as [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags (e.g. "en-US", "es-419", "cmn-tw").
*/
languageCodes?: string[] | null;
/**
* The name of this voice. Each distinct voice has a unique name.
*/
name?: string | null;
/**
* The natural sample rate (in hertz) for this voice.
*/
naturalSampleRateHertz?: number | null;
/**
* The gender of this voice.
*/
ssmlGender?: string | null;
}
/**
* Description of which voice to use for a synthesis request.
*/
export interface Schema$VoiceSelectionParams {
/**
* 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)".
*/
languageCode?: string | null;
/**
* 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.
*/
name?: string | null;
/**
* 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.
*/
ssmlGender?: string | null;
}
export class Resource$Text {
context: APIRequestContext;
constructor(context: APIRequestContext);
/**
* texttospeech.text.synthesize
* @desc Synthesizes speech synchronously: receive results after all text input has been processed.
* @alias texttospeech.text.synthesize
* @memberOf! ()
*
* @param {object} params Parameters for request
* @param {().SynthesizeSpeechRequest} params.resource Request body data
* @param {object} [options] Optionally override request options, such as `url`, `method`, and `encoding`.
* @param {callback} callback The callback that handles the response.
* @return {object} Request object
*/
synthesize(params?: Params$Resource$Text$Synthesize, options?: MethodOptions): GaxiosPromise<Schema$SynthesizeSpeechResponse>;
synthesize(params: Params$Resource$Text$Synthesize, options: MethodOptions | BodyResponseCallback<Schema$SynthesizeSpeechResponse>, callback: BodyResponseCallback<Schema$SynthesizeSpeechResponse>): void;
synthesize(params: Params$Resource$Text$Synthesize, callback: BodyResponseCallback<Schema$SynthesizeSpeechResponse>): void;
synthesize(callback: BodyResponseCallback<Schema$SynthesizeSpeechResponse>): void;
}
export interface Params$Resource$Text$Synthesize extends StandardParameters {
/**
* Auth client or API Key for the request
*/
auth?: string | OAuth2Client | JWT | Compute | UserRefreshClient;
/**
* Request body metadata
*/
requestBody?: Schema$SynthesizeSpeechRequest;
}
export class Resource$Voices {
context: APIRequestContext;
constructor(context: APIRequestContext);
/**
* texttospeech.voices.list
* @desc Returns a list of Voice supported for synthesis.
* @alias texttospeech.voices.list
* @memberOf! ()
*
* @param {object} params Parameters for request
* @param {string=} params.languageCode Optional. Recommended. [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag. 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-*" 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-*" voices.
* @param {object} [options] Optionally override request options, such as `url`, `method`, and `encoding`.
* @param {callback} callback The callback that handles the response.
* @return {object} Request object
*/
list(params?: Params$Resource$Voices$List, options?: MethodOptions): GaxiosPromise<Schema$ListVoicesResponse>;
list(params: Params$Resource$Voices$List, options: MethodOptions | BodyResponseCallback<Schema$ListVoicesResponse>, callback: BodyResponseCallback<Schema$ListVoicesResponse>): void;
list(params: Params$Resource$Voices$List, callback: BodyResponseCallback<Schema$ListVoicesResponse>): void;
list(callback: BodyResponseCallback<Schema$ListVoicesResponse>): void;
}
export interface Params$Resource$Voices$List extends StandardParameters {
/**
* Auth client or API Key for the request
*/
auth?: string | OAuth2Client | JWT | Compute | UserRefreshClient;
/**
* Optional. Recommended. [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag. 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-*" 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-*" voices.
*/
languageCode?: string;
}
export {};
}