Skip to content

Commit 976d7c7

Browse files
crwilcoxcrwilcox
authored
Add protos as an artifact to library (#7205)
1 parent c150f20 commit 976d7c7

File tree

4 files changed

+462
-6
lines changed

4 files changed

+462
-6
lines changed

‎packages/google-cloud-texttospeech/google/cloud/texttospeech_v1/proto/cloud_tts.proto‎

Lines changed: 228 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,228 @@
1+
// Copyright 2018 Google Inc.
2+
//
3+
// Licensed under the Apache License, Version 2.0 (the "License");
4+
// you may not use this file except in compliance with the License.
5+
// You may obtain a copy of the License at
6+
//
7+
// http://www.apache.org/licenses/LICENSE-2.0
8+
//
9+
// Unless required by applicable law or agreed to in writing, software
10+
// distributed under the License is distributed on an "AS IS" BASIS,
11+
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12+
// See the License for the specific language governing permissions and
13+
// limitations under the License.
14+
15+
syntax = "proto3";
16+
17+
package google.cloud.texttospeech.v1beta1;
18+
19+
import "google/api/annotations.proto";
20+
21+
option cc_enable_arenas = true;
22+
option go_package = "google.golang.org/genproto/googleapis/cloud/texttospeech/v1beta1;texttospeech";
23+
option java_multiple_files = true;
24+
option java_outer_classname = "TextToSpeechProto";
25+
option java_package = "com.google.cloud.texttospeech.v1beta1";
26+
27+
28+
// Service that implements Google Cloud Text-to-Speech API.
29+
service TextToSpeech {
30+
// Returns a list of [Voice][google.cloud.texttospeech.v1beta1.Voice]
31+
// supported for synthesis.
32+
rpc ListVoices(ListVoicesRequest) returns (ListVoicesResponse) {
33+
option (google.api.http) = {
34+
get: "/v1beta1/voices"
35+
};
36+
}
37+
38+
// Synthesizes speech synchronously: receive results after all text input
39+
// has been processed.
40+
rpc SynthesizeSpeech(SynthesizeSpeechRequest) returns (SynthesizeSpeechResponse) {
41+
option (google.api.http) = {
42+
post: "/v1beta1/text:synthesize"
43+
body: "*"
44+
};
45+
}
46+
}
47+
48+
// The top-level message sent by the client for the `ListVoices` method.
49+
message ListVoicesRequest {
50+
// Optional (but recommended)
51+
// [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag. If
52+
// specified, the ListVoices call will only return voices that can be used to
53+
// synthesize this language_code. E.g. when specifying "en-NZ", you will get
54+
// supported "en-*" voices; when specifying "no", you will get supported
55+
// "no-*" (Norwegian) and "nb-*" (Norwegian Bokmal) voices; specifying "zh"
56+
// will also get supported "cmn-*" voices; specifying "zh-hk" will also get
57+
// supported "yue-*" voices.
58+
string language_code = 1;
59+
}
60+
61+
// The message returned to the client by the `ListVoices` method.
62+
message ListVoicesResponse {
63+
// The list of voices.
64+
repeated Voice voices = 1;
65+
}
66+
67+
// Description of a voice supported by the TTS service.
68+
message Voice {
69+
// The languages that this voice supports, expressed as
70+
// [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags (e.g.
71+
// "en-US", "es-419", "cmn-tw").
72+
repeated string language_codes = 1;
73+
74+
// The name of this voice. Each distinct voice has a unique name.
75+
string name = 2;
76+
77+
// The gender of this voice.
78+
SsmlVoiceGender ssml_gender = 3;
79+
80+
// The natural sample rate (in hertz) for this voice.
81+
int32 natural_sample_rate_hertz = 4;
82+
}
83+
84+
// The top-level message sent by the client for the `SynthesizeSpeech` method.
85+
message SynthesizeSpeechRequest {
86+
// Required. The Synthesizer requires either plain text or SSML as input.
87+
SynthesisInput input = 1;
88+
89+
// Required. The desired voice of the synthesized audio.
90+
VoiceSelectionParams voice = 2;
91+
92+
// Required. The configuration of the synthesized audio.
93+
AudioConfig audio_config = 3;
94+
}
95+
96+
// Contains text input to be synthesized. Either `text` or `ssml` must be
97+
// supplied. Supplying both or neither returns
98+
// [google.rpc.Code.INVALID_ARGUMENT][]. The input size is limited to 5000
99+
// characters.
100+
message SynthesisInput {
101+
// The input source, which is either plain text or SSML.
102+
oneof input_source {
103+
// The raw text to be synthesized.
104+
string text = 1;
105+
106+
// The SSML document to be synthesized. The SSML document must be valid
107+
// and well-formed. Otherwise the RPC will fail and return
108+
// [google.rpc.Code.INVALID_ARGUMENT][]. For more information, see
109+
// [SSML](/speech/text-to-speech/docs/ssml).
110+
string ssml = 2;
111+
}
112+
}
113+
114+
// Description of which voice to use for a synthesis request.
115+
message VoiceSelectionParams {
116+
// The language (and optionally also the region) of the voice expressed as a
117+
// [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag, e.g.
118+
// "en-US". Required. This should not include a script tag (e.g. use
119+
// "cmn-cn" rather than "cmn-Hant-cn"), because the script will be inferred
120+
// from the input provided in the SynthesisInput. The TTS service
121+
// will use this parameter to help choose an appropriate voice. Note that
122+
// the TTS service may choose a voice with a slightly different language code
123+
// than the one selected; it may substitute a different region
124+
// (e.g. using en-US rather than en-CA if there isn't a Canadian voice
125+
// available), or even a different language, e.g. using "nb" (Norwegian
126+
// Bokmal) instead of "no" (Norwegian)".
127+
string language_code = 1;
128+
129+
// The name of the voice. Optional; if not set, the service will choose a
130+
// voice based on the other parameters such as language_code and gender.
131+
string name = 2;
132+
133+
// The preferred gender of the voice. Optional; if not set, the service will
134+
// choose a voice based on the other parameters such as language_code and
135+
// name. Note that this is only a preference, not requirement; if a
136+
// voice of the appropriate gender is not available, the synthesizer should
137+
// substitute a voice with a different gender rather than failing the request.
138+
SsmlVoiceGender ssml_gender = 3;
139+
}
140+
141+
// Description of audio data to be synthesized.
142+
message AudioConfig {
143+
// Required. The format of the requested audio byte stream.
144+
AudioEncoding audio_encoding = 1;
145+
146+
// Optional speaking rate/speed, in the range [0.25, 4.0]. 1.0 is the normal
147+
// native speed supported by the specific voice. 2.0 is twice as fast, and
148+
// 0.5 is half as fast. If unset(0.0), defaults to the native 1.0 speed. Any
149+
// other values < 0.25 or > 4.0 will return an error.
150+
double speaking_rate = 2;
151+
152+
// Optional speaking pitch, in the range [-20.0, 20.0]. 20 means increase 20
153+
// semitones from the original pitch. -20 means decrease 20 semitones from the
154+
// original pitch.
155+
double pitch = 3;
156+
157+
// Optional volume gain (in dB) of the normal native volume supported by the
158+
// specific voice, in the range [-96.0, 16.0]. If unset, or set to a value of
159+
// 0.0 (dB), will play at normal native signal amplitude. A value of -6.0 (dB)
160+
// will play at approximately half the amplitude of the normal native signal
161+
// amplitude. A value of +6.0 (dB) will play at approximately twice the
162+
// amplitude of the normal native signal amplitude. Strongly recommend not to
163+
// exceed +10 (dB) as there's usually no effective increase in loudness for
164+
// any value greater than that.
165+
double volume_gain_db = 4;
166+
167+
// The synthesis sample rate (in hertz) for this audio. Optional. If this is
168+
// different from the voice's natural sample rate, then the synthesizer will
169+
// honor this request by converting to the desired sample rate (which might
170+
// result in worse audio quality), unless the specified sample rate is not
171+
// supported for the encoding chosen, in which case it will fail the request
172+
// and return [google.rpc.Code.INVALID_ARGUMENT][].
173+
int32 sample_rate_hertz = 5;
174+
175+
// An identifier which selects 'audio effects' profiles that are applied on
176+
// (post synthesized) text to speech.
177+
// Effects are applied on top of each other in the order they are given.
178+
repeated string effects_profile_id = 6;
179+
}
180+
181+
// The message returned to the client by the `SynthesizeSpeech` method.
182+
message SynthesizeSpeechResponse {
183+
// The audio data bytes encoded as specified in the request, including the
184+
// header (For LINEAR16 audio, we include the WAV header). Note: as
185+
// with all bytes fields, protobuffers use a pure binary representation,
186+
// whereas JSON representations use base64.
187+
bytes audio_content = 1;
188+
}
189+
190+
// Gender of the voice as described in
191+
// [SSML voice element](https://www.w3.org/TR/speech-synthesis11/#edef_voice).
192+
enum SsmlVoiceGender {
193+
// An unspecified gender.
194+
// In VoiceSelectionParams, this means that the client doesn't care which
195+
// gender the selected voice will have. In the Voice field of
196+
// ListVoicesResponse, this may mean that the voice doesn't fit any of the
197+
// other categories in this enum, or that the gender of the voice isn't known.
198+
SSML_VOICE_GENDER_UNSPECIFIED = 0;
199+
200+
// A male voice.
201+
MALE = 1;
202+
203+
// A female voice.
204+
FEMALE = 2;
205+
206+
// A gender-neutral voice.
207+
NEUTRAL = 3;
208+
}
209+
210+
// Configuration to set up audio encoder. The encoding determines the output
211+
// audio format that we'd like.
212+
enum AudioEncoding {
213+
// Not specified. Will return result [google.rpc.Code.INVALID_ARGUMENT][].
214+
AUDIO_ENCODING_UNSPECIFIED = 0;
215+
216+
// Uncompressed 16-bit signed little-endian samples (Linear PCM).
217+
// Audio content returned as LINEAR16 also contains a WAV header.
218+
LINEAR16 = 1;
219+
220+
// MP3 audio.
221+
MP3 = 2;
222+
223+
// Opus encoded audio wrapped in an ogg container. The result will be a
224+
// file which can be played natively on Android, and in browsers (at least
225+
// Chrome and Firefox). The quality of the encoding is considerably higher
226+
// than MP3 while using approximately the same bitrate.
227+
OGG_OPUS = 3;
228+
}

0 commit comments

Comments
 (0)