tts

type EdgeProvider ¶

type EdgeProvider struct {
	// contains filtered or unexported fields
}

EdgeProvider implements TTS via Microsoft Edge's speech synthesis service. Uses the same underlying Azure Cognitive Services as the edge-tts Python package, but via direct HTTP calls — no external dependencies needed.

Popular voices:

• pt-BR-FranciscaNeural (Brazilian Portuguese, female)
• pt-BR-AntonioNeural (Brazilian Portuguese, male)
• en-US-JennyNeural (US English, female)
• en-US-GuyNeural (US English, male)
• es-ES-ElviraNeural (Spanish, female)

func NewEdgeProvider(logger *slog.Logger) *EdgeProvider

func (p *EdgeProvider) Synthesize(ctx context.Context, text, voice string) ([]byte, string, error)

type FallbackProvider ¶

type FallbackProvider struct {
	// contains filtered or unexported fields
}

FallbackProvider tries the primary provider and falls back to the secondary if the primary fails. Useful for "auto" mode where OpenAI is preferred but Edge TTS is the free fallback.

func NewFallbackProvider(primary, secondary Provider, primaryVoice, secondaryVoice string, logger *slog.Logger) *FallbackProvider

func (p *FallbackProvider) Synthesize(ctx context.Context, text, voice string) ([]byte, string, error)

type OpenAIProvider ¶

type OpenAIProvider struct {
	// contains filtered or unexported fields
}

OpenAIProvider implements TTS via the OpenAI TTS API.

func NewOpenAIProvider(apiKey, baseURL, model string) *OpenAIProvider

func (p *OpenAIProvider) Synthesize(ctx context.Context, text, voice string) ([]byte, string, error)

type Provider ¶

type Provider interface {
	// Synthesize converts text to audio.
	// Returns audio bytes, MIME type (e.g. "audio/ogg"), and error.
	Synthesize(ctx context.Context, text, voice string) ([]byte, string, error)
}

Provider is the interface for TTS backends.