1 // Copyright 2018 Google LLC
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
7 // http://www.apache.org/licenses/LICENSE-2.0
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.
17 package google.cloud.dialogflow.v2beta1;
19 import "google/api/annotations.proto";
21 option cc_enable_arenas = true;
22 option csharp_namespace = "Google.Cloud.Dialogflow.V2beta1";
23 option go_package = "google.golang.org/genproto/googleapis/cloud/dialogflow/v2beta1;dialogflow";
24 option java_multiple_files = true;
25 option java_outer_classname = "AudioConfigProto";
26 option java_package = "com.google.cloud.dialogflow.v2beta1";
27 option objc_class_prefix = "DF";
29 // Description of which voice to use for speech synthesis.
30 message VoiceSelectionParams {
31 // Optional. The name of the voice. If not set, the service will choose a
32 // voice based on the other parameters such as language_code and gender.
35 // Optional. The preferred gender of the voice. If not set, the service will
36 // choose a voice based on the other parameters such as language_code and
37 // name. Note that this is only a preference, not requirement. If a
38 // voice of the appropriate gender is not available, the synthesizer should
39 // substitute a voice with a different gender rather than failing the request.
40 SsmlVoiceGender ssml_gender = 2;
43 // Configuration of how speech should be synthesized.
44 message SynthesizeSpeechConfig {
45 // Optional. Speaking rate/speed, in the range [0.25, 4.0]. 1.0 is the normal
46 // native speed supported by the specific voice. 2.0 is twice as fast, and
47 // 0.5 is half as fast. If unset(0.0), defaults to the native 1.0 speed. Any
48 // other values < 0.25 or > 4.0 will return an error.
49 double speaking_rate = 1;
51 // Optional. Speaking pitch, in the range [-20.0, 20.0]. 20 means increase 20
52 // semitones from the original pitch. -20 means decrease 20 semitones from the
56 // Optional. Volume gain (in dB) of the normal native volume supported by the
57 // specific voice, in the range [-96.0, 16.0]. If unset, or set to a value of
58 // 0.0 (dB), will play at normal native signal amplitude. A value of -6.0 (dB)
59 // will play at approximately half the amplitude of the normal native signal
60 // amplitude. A value of +6.0 (dB) will play at approximately twice the
61 // amplitude of the normal native signal amplitude. We strongly recommend not
62 // to exceed +10 (dB) as there's usually no effective increase in loudness for
63 // any value greater than that.
64 double volume_gain_db = 3;
66 // Optional. An identifier which selects 'audio effects' profiles that are
67 // applied on (post synthesized) text to speech. Effects are applied on top of
68 // each other in the order they are given.
69 repeated string effects_profile_id = 5;
71 // Optional. The desired voice of the synthesized audio.
72 VoiceSelectionParams voice = 4;
75 // Instructs the speech synthesizer how to generate the output audio content.
76 message OutputAudioConfig {
77 // Required. Audio encoding of the synthesized audio content.
78 OutputAudioEncoding audio_encoding = 1;
80 // Optional. The synthesis sample rate (in hertz) for this audio. If not
81 // provided, then the synthesizer will use the default sample rate based on
82 // the audio encoding. If this is different from the voice's natural sample
83 // rate, then the synthesizer will honor this request by converting to the
84 // desired sample rate (which might result in worse audio quality).
85 int32 sample_rate_hertz = 2;
87 // Optional. Configuration of how speech should be synthesized.
88 SynthesizeSpeechConfig synthesize_speech_config = 3;
91 // Gender of the voice as described in
92 // [SSML voice element](https://www.w3.org/TR/speech-synthesis11/#edef_voice).
93 enum SsmlVoiceGender {
94 // An unspecified gender, which means that the client doesn't care which
95 // gender the selected voice will have.
96 SSML_VOICE_GENDER_UNSPECIFIED = 0;
99 SSML_VOICE_GENDER_MALE = 1;
102 SSML_VOICE_GENDER_FEMALE = 2;
104 // A gender-neutral voice.
105 SSML_VOICE_GENDER_NEUTRAL = 3;
108 // Audio encoding of the output audio format in Text-To-Speech.
109 enum OutputAudioEncoding {
111 OUTPUT_AUDIO_ENCODING_UNSPECIFIED = 0;
113 // Uncompressed 16-bit signed little-endian samples (Linear PCM).
114 // Audio content returned as LINEAR16 also contains a WAV header.
115 OUTPUT_AUDIO_ENCODING_LINEAR_16 = 1;
118 OUTPUT_AUDIO_ENCODING_MP3 = 2;
120 // Opus encoded audio wrapped in an ogg container. The result will be a
121 // file which can be played natively on Android, and in browsers (at least
122 // Chrome and Firefox). The quality of the encoding is considerably higher
123 // than MP3 while using approximately the same bitrate.
124 OUTPUT_AUDIO_ENCODING_OGG_OPUS = 3;