dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-28 06:25:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 12

TTS API improvements (#2308)

Browse source 
* update doc on COQUI_LANGUAGE env variable

Signed-off-by: blob42 <contact@blob42.xyz>

* return errors from tts gRPC backend

Signed-off-by: blob42 <contact@blob42.xyz>

* handle speaker_id and language in coqui TTS backend

Signed-off-by: blob42 <contact@blob42.xyz>

* TTS endpoint: add optional language paramter

Signed-off-by: blob42 <contact@blob42.xyz>

* tts fix: empty language string breaks non-multilingual models

Signed-off-by: blob42 <contact@blob42.xyz>

* allow tts param definition in config file

- consolidate TTS options under `tts` config entry

Signed-off-by: blob42 <contact@blob42.xyz>

* tts: update doc

Signed-off-by: blob42 <contact@blob42.xyz>

---------

Signed-off-by: blob42 <contact@blob42.xyz>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
This commit is contained in:
Chakib Benziane 2024-06-01 20:26:27 +02:00 • committed by GitHub
parent 95c65d67f5
commit b99182c8d4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 166 additions and 78 deletions
Download patch file Download diff file Expand all files Collapse all files

2
core/http/endpoints/elevenlabs/tts.go
View file

@ -52,7 +52,7 @@ func TTSEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, appConfi
}
log.Debug().Msgf("Request for model: %s", modelFile)
filePath, _, err := backend.ModelTTS(cfg.Backend, input.Text, modelFile, voiceID, ml, appConfig, *cfg)
filePath, _, err := backend.ModelTTS(cfg.Backend, input.Text, modelFile, "", voiceID, ml, appConfig, *cfg)
if err != nil {
return err
}

22
core/http/endpoints/localai/tts.go
View file

@ -12,10 +12,13 @@ import (
)
// TTSEndpoint is the OpenAI Speech API endpoint https://platform.openai.com/docs/api-reference/audio/createSpeech
// @Summary Generates audio from the input text.
// @Param request body schema.TTSRequest true "query params"
// @Success 200 {string} binary "Response"
// @Router /v1/audio/speech [post]
// @Summary Generates audio from the input text.
// @Accept json
// @Produce audio/x-wav
// @Param request body schema.TTSRequest true "query params"
// @Success 200 {string} binary "generated audio/wav file"
// @Router /v1/audio/speech [post]
// @Router /tts [post]
func TTSEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, appConfig *config.ApplicationConfig) func(c *fiber.Ctx) error {
return func(c *fiber.Ctx) error {
@ -40,6 +43,7 @@ func TTSEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, appConfi
)
if err != nil {
log.Err(err)
modelFile = input.Model
log.Warn().Msgf("Model not found in context: %s", input.Model)
} else {
@ -51,7 +55,15 @@ func TTSEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, appConfi
cfg.Backend = input.Backend
}
filePath, _, err := backend.ModelTTS(cfg.Backend, input.Input, modelFile, input.Voice, ml, appConfig, *cfg)
if input.Language != "" {
cfg.Language = input.Language
}
if input.Voice != "" {
cfg.Voice = input.Voice
}
filePath, _, err := backend.ModelTTS(cfg.Backend, input.Input, modelFile, cfg.Voice, cfg.Language, ml, appConfig, *cfg)
if err != nil {
return err
}