tts

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

type GoogleOpts struct {
	APIKey string
	Voice  string // e.g. "de-DE-Neural2-B", "en-US-Neural2-J"
}

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

type HuggingFaceOpts struct {
	Token string // HF API token
	Model string // Model ID, e.g. "parler-tts/parler-tts-mini-multilingual-v1.1"
}

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

type OpenAIOpts struct {
	APIKey string
	Model  string // "tts-1" or "tts-1-hd"
	Voice  string // alloy, echo, fable, onyx, nova, shimmer
}

type Provider interface {
	// Synthesize converts text to audio bytes.
	Synthesize(ctx context.Context, text string, opts SynthesizeOpts) (*Result, error)

	// Name returns the provider identifier (e.g. "openai", "google", "kokoro").
	Name() string

	// Health checks if the provider is reachable and ready.
	Health(ctx context.Context) error
}

type Result struct {
	Audio      []byte
	Format     string        // Actual format of the audio data
	SampleRate int           // Sample rate in Hz (e.g. 24000)
	Duration   time.Duration // Estimated duration of the audio
	Provider   string
	Voice      string
}

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

type Strategy string

type SynthesizeOpts struct {
	Locale string  // "de-DE", "en-US", "auto"
	Voice  string  // Provider-specific voice ID; empty = default
	Speed  float64 // 0.25 - 4.0, default 1.0
	Format string  // "wav", "mp3", "opus", "pcm"; default "mp3"
}