GlcoinCore/googleapis
1
0
Fork 0
mirror of https://github.com/googleapis/googleapis.git synced 2026-08-15 12:50:26 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: StreamingSynthesize now supports opus

Browse source 
PiperOrigin-RevId: 707168599
This commit is contained in:
Google APIs 2024-12-17 10:59:32 -08:00 • committed by Copybara-Service
parent 92a92baba4
commit d985436b77
1 changed files with 20 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

20
google/cloud/texttospeech/v1beta1/cloud_tts.proto
View file

@ -115,6 +115,11 @@ enum AudioEncoding {
// 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.
ALAW = 6;
// Uncompressed 16-bit signed little-endian samples (Linear PCM).
// Note that as opposed to LINEAR16, audio will not be wrapped in a WAV (or
// any other) header.
PCM = 7;
}
// The top-level message sent by the client for the `ListVoices` method.
@ -432,10 +437,25 @@ message Timepoint {
double time_seconds = 3;
}
// Description of the desired output audio data.
message StreamingAudioConfig {
// Required. The format of the audio byte stream.
// For now, streaming only supports PCM and OGG_OPUS. All other encodings
// will return an error.
AudioEncoding audio_encoding = 1 [(google.api.field_behavior) = REQUIRED];
// Optional. The synthesis sample rate (in hertz) for this audio.
int32 sample_rate_hertz = 2 [(google.api.field_behavior) = OPTIONAL];
}
// Provides configuration information for the StreamingSynthesize request.
message StreamingSynthesizeConfig {
// Required. The desired voice of the synthesized audio.
VoiceSelectionParams voice = 1 [(google.api.field_behavior) = REQUIRED];
// Optional. The configuration of the synthesized audio.
StreamingAudioConfig streaming_audio_config = 4
[(google.api.field_behavior) = OPTIONAL];
}
// Input to be synthesized.