dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-25 13:04:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 13

feat: elevenlabs sound-generation api (#3355)

Browse source 
* 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
Download patch file Download diff file Expand all files Collapse all files

65
core/http/endpoints/elevenlabs/soundgeneration.go Normal file
View file

@ -0,0 +1,65 @@
package elevenlabs
import (
"github.com/gofiber/fiber/v2"
"github.com/mudler/LocalAI/core/backend"
"github.com/mudler/LocalAI/core/config"
fiberContext "github.com/mudler/LocalAI/core/http/ctx"
"github.com/mudler/LocalAI/core/schema"
"github.com/mudler/LocalAI/pkg/model"
"github.com/rs/zerolog/log"
)
// SoundGenerationEndpoint is the ElevenLabs SoundGeneration endpoint https://elevenlabs.io/docs/api-reference/sound-generation
// @Summary Generates audio from the input text.
// @Param request body schema.ElevenLabsSoundGenerationRequest true "query params"
// @Success 200 {string} binary "Response"
// @Router /v1/sound-generation [post]
func SoundGenerationEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, appConfig *config.ApplicationConfig) func(c *fiber.Ctx) error {
return func(c *fiber.Ctx) error {
input := new(schema.ElevenLabsSoundGenerationRequest)
// Get input data from the request body
if err := c.BodyParser(input); err != nil {
return err
}
modelFile, err := fiberContext.ModelFromContext(c, cl, ml, input.ModelID, false)
if err != nil {
modelFile = input.ModelID
log.Warn().Str("ModelID", input.ModelID).Msg("Model not found in context")
}
cfg, err := cl.LoadBackendConfigFileByName(modelFile, appConfig.ModelPath,
config.LoadOptionDebug(appConfig.Debug),
config.LoadOptionThreads(appConfig.Threads),
config.LoadOptionContextSize(appConfig.ContextSize),
config.LoadOptionF16(appConfig.F16),
)
if err != nil {
modelFile = input.ModelID
log.Warn().Str("Request ModelID", input.ModelID).Err(err).Msg("error during LoadBackendConfigFileByName, using request ModelID")
} else {
if input.ModelID != "" {
modelFile = input.ModelID
} else {
modelFile = cfg.Model
}
}
log.Debug().Str("modelFile", "modelFile").Str("backend", cfg.Backend).Msg("Sound Generation Request about to be sent to backend")
if input.Duration != nil {
log.Debug().Float32("duration", *input.Duration).Msg("duration set")
}
if input.Temperature != nil {
log.Debug().Float32("temperature", *input.Temperature).Msg("temperature set")
}
// TODO: Support uploading files?
filePath, _, err := backend.SoundGeneration(cfg.Backend, modelFile, input.Text, input.Duration, input.Temperature, input.DoSample, nil, nil, ml, appConfig, *cfg)
if err != nil {
return err
}
return c.Download(filePath)
}
}

2
core/http/routes/elevenlabs.go
View file

@ -16,4 +16,6 @@ func RegisterElevenLabsRoutes(app *fiber.App,
// Elevenlabs
app.Post("/v1/text-to-speech/:voice-id", auth, elevenlabs.TTSEndpoint(cl, ml, appConfig))
app.Post("/v1/sound-generation", auth, elevenlabs.SoundGenerationEndpoint(cl, ml, appConfig))
}