diff options
Diffstat (limited to 'google/cloud/dialogflow/v2/audio_config.proto')
-rw-r--r-- | google/cloud/dialogflow/v2/audio_config.proto | 126 |
1 files changed, 126 insertions, 0 deletions
diff --git a/google/cloud/dialogflow/v2/audio_config.proto b/google/cloud/dialogflow/v2/audio_config.proto new file mode 100644 index 000000000..d3ae64e9f --- /dev/null +++ b/google/cloud/dialogflow/v2/audio_config.proto @@ -0,0 +1,126 @@ +// 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. +// + +syntax = "proto3"; + +package google.cloud.dialogflow.v2; + +import "google/api/annotations.proto"; + +option cc_enable_arenas = true; +option csharp_namespace = "Google.Cloud.Dialogflow.V2"; +option go_package = "google.golang.org/genproto/googleapis/cloud/dialogflow/v2;dialogflow"; +option java_multiple_files = true; +option java_outer_classname = "AudioConfigProto"; +option java_package = "com.google.cloud.dialogflow.v2"; +option objc_class_prefix = "DF"; + +// Gender of the voice as described in +// [SSML voice element](https://www.w3.org/TR/speech-synthesis11/#edef_voice). +enum SsmlVoiceGender { + // An unspecified gender, which means that the client doesn't care which + // gender the selected voice will have. + SSML_VOICE_GENDER_UNSPECIFIED = 0; + + // A male voice. + SSML_VOICE_GENDER_MALE = 1; + + // A female voice. + SSML_VOICE_GENDER_FEMALE = 2; + + // A gender-neutral voice. + SSML_VOICE_GENDER_NEUTRAL = 3; +} + +// Description of which voice to use for speech synthesis. +message VoiceSelectionParams { + // Optional. 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. + string name = 1; + + // Optional. 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. + SsmlVoiceGender ssml_gender = 2; +} + +// Configuration of how speech should be synthesized. +message SynthesizeSpeechConfig { + // Optional. 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. + double speaking_rate = 1; + + // Optional. 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. + double pitch = 2; + + // Optional. 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. We strongly recommend not + // to exceed +10 (dB) as there's usually no effective increase in loudness for + // any value greater than that. + double volume_gain_db = 3; + + // Optional. 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. + repeated string effects_profile_id = 5; + + // Optional. The desired voice of the synthesized audio. + VoiceSelectionParams voice = 4; +} + +// Audio encoding of the output audio format in Text-To-Speech. +enum OutputAudioEncoding { + // Not specified. + OUTPUT_AUDIO_ENCODING_UNSPECIFIED = 0; + + // Uncompressed 16-bit signed little-endian samples (Linear PCM). + // Audio content returned as LINEAR16 also contains a WAV header. + OUTPUT_AUDIO_ENCODING_LINEAR_16 = 1; + + // MP3 audio. + OUTPUT_AUDIO_ENCODING_MP3 = 2; + + // 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. + OUTPUT_AUDIO_ENCODING_OGG_OPUS = 3; +} + +// Instructs the speech synthesizer how to generate the output audio content. +message OutputAudioConfig { + // Required. Audio encoding of the synthesized audio content. + OutputAudioEncoding audio_encoding = 1; + + // Optional. The synthesis sample rate (in hertz) for this audio. If not + // provided, then the synthesizer will use the default sample rate based on + // the audio encoding. 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). + int32 sample_rate_hertz = 2; + + // Optional. Configuration of how speech should be synthesized. + SynthesizeSpeechConfig synthesize_speech_config = 3; +} |