feat: elevenlabs sound-generation api (#3355)

* initial version of elevenlabs compatible soundgeneration api and cli command

Signed-off-by: Dave Lee <dave@gray101.com>

* minor cleanup

Signed-off-by: Dave Lee <dave@gray101.com>

* restore TTS, add test

Signed-off-by: Dave Lee <dave@gray101.com>

* remove stray s

Signed-off-by: Dave Lee <dave@gray101.com>

* fix

Signed-off-by: Dave Lee <dave@gray101.com>

---------

Signed-off-by: Dave Lee <dave@gray101.com>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
This commit is contained in:
Dave 2024-08-23 20:20:28 -04:00 committed by GitHub
parent 84d6e5a987
commit 81ae92f017
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
20 changed files with 450 additions and 37 deletions

View file

@ -16,6 +16,7 @@ service Backend {
rpc GenerateImage(GenerateImageRequest) returns (Result) {}
rpc AudioTranscription(TranscriptRequest) returns (TranscriptResult) {}
rpc TTS(TTSRequest) returns (Result) {}
rpc SoundGeneration(SoundGenerationRequest) returns (Result) {}
rpc TokenizeString(PredictOptions) returns (TokenizationResponse) {}
rpc Status(HealthMessage) returns (StatusResponse) {}
@ -270,6 +271,17 @@ message TTSRequest {
optional string language = 5;
}
message SoundGenerationRequest {
string text = 1;
string model = 2;
string dst = 3;
optional float duration = 4;
optional float temperature = 5;
optional bool sample = 6;
optional string src = 7;
optional int32 src_divisor = 8;
}
message TokenizationResponse {
int32 length = 1;
repeated int32 tokens = 2;