Files
LocalAI/core/http/endpoints/elevenlabs/tts.go
Ettore Di Giacinto 697f6aa71c feat(audio): set audio content type (#8416)
* feat(audio): set audio content type

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore: add tests

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2026-02-05 19:14:12 +01:00

50 lines
1.6 KiB
Go

package elevenlabs
import (
"path/filepath"
"github.com/labstack/echo/v4"
"github.com/mudler/LocalAI/core/backend"
"github.com/mudler/LocalAI/core/config"
"github.com/mudler/LocalAI/core/http/middleware"
"github.com/mudler/LocalAI/core/schema"
"github.com/mudler/LocalAI/pkg/audio"
"github.com/mudler/LocalAI/pkg/model"
"github.com/mudler/xlog"
)
// TTSEndpoint is the OpenAI Speech API endpoint https://platform.openai.com/docs/api-reference/audio/createSpeech
// @Summary Generates audio from the input text.
// @Param voice-id path string true "Account ID"
// @Param request body schema.TTSRequest true "query params"
// @Success 200 {string} binary "Response"
// @Router /v1/text-to-speech/{voice-id} [post]
func TTSEndpoint(cl *config.ModelConfigLoader, ml *model.ModelLoader, appConfig *config.ApplicationConfig) echo.HandlerFunc {
return func(c echo.Context) error {
voiceID := c.Param("voice-id")
input, ok := c.Get(middleware.CONTEXT_LOCALS_KEY_LOCALAI_REQUEST).(*schema.ElevenLabsTTSRequest)
if !ok || input.ModelID == "" {
return echo.ErrBadRequest
}
cfg, ok := c.Get(middleware.CONTEXT_LOCALS_KEY_MODEL_CONFIG).(*config.ModelConfig)
if !ok || cfg == nil {
return echo.ErrBadRequest
}
xlog.Debug("elevenlabs TTS request received", "modelName", input.ModelID)
filePath, _, err := backend.ModelTTS(input.Text, voiceID, input.LanguageCode, ml, appConfig, *cfg)
if err != nil {
return err
}
filePath, contentType := audio.NormalizeAudioFile(filePath)
if contentType != "" {
c.Response().Header().Set("Content-Type", contentType)
}
return c.Attachment(filePath, filepath.Base(filePath))
}
}