tts

type AudioFormat string

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

type Consent struct {
	ID             string     `json:"id"`
	UserID         string     `json:"user_id"`
	Service        string     `json:"service"` // 'edge-tts', 'espeak'
	ConsentGiven   bool       `json:"consent_given"`
	ConsentDate    *time.Time `json:"consent_date,omitempty"`
	ConsentVersion string     `json:"consent_version"`
	CreatedAt      time.Time  `json:"created_at"`
	UpdatedAt      time.Time  `json:"updated_at"`
}

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

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

type EspeakModelManager struct{}

type EspeakNGAdapter struct{}

type EspeakNGProvider struct{}

type EspeakNGRequest struct {
	Text     string  `json:"text"`
	Language string  `json:"language"`
	Rate     float32 `json:"rate"`
	Pitch    float32 `json:"pitch"`
	Volume   float32 `json:"volume"`
}

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

type KokoroModelManager struct{}

type LanguageStats struct {
	CJKHan   int // CJK Unified Ideographs (shared: zh, ja, ko)
	Kana     int // Hiragana + Katakana (unique to Japanese)
	Hangul   int // Korean Hangul (unique to Korean)
	Latin    int // Latin script (en, fr, de, es, pt, etc.)
	Cyrillic int // Cyrillic script (ru, uk, bg, etc.)
	Arabic   int // Arabic script (ar, fa, ur, etc.)
	Thai     int // Thai script
	Devanag  int // Devanagari script (hi, mr, ne, etc.)
	Other    int // Other letters/numbers
	Total    int // Total scored characters
}

type LocalSpeaker interface {
	SpeakLocally(ctx context.Context, text string, speed float32) error
	StopSpeaking()
}

type MacOSNativeTTS struct{}

type Phonemizer interface {
	// TextToPhonemes converts text to IPA phonemes.
	// lang is a language code (e.g. "en", "cmn", "ja").
	TextToPhonemes(text, lang string) (string, error)
}

type Provider interface {
	// Name returns the provider name.
	Name() string
	// Type returns the provider type.
	Type() ProviderType
	// Synthesize synthesizes text to speech.
	Synthesize(ctx context.Context, req *SynthesizeRequest) (*SynthesizeResponse, error)
	// SynthesizeStream synthesizes text with streaming audio output.
	SynthesizeStream(ctx context.Context, req *SynthesizeRequest, callback StreamCallback) error
	// ListVoices returns available voices.
	ListVoices(ctx context.Context) ([]Voice, error)
	// SupportedFormats returns the supported audio formats.
	SupportedFormats() []AudioFormat
	// MaxTextLength returns the maximum text length.
	MaxTextLength() int
}

type ProviderConfig struct {
	// Type is the provider type.
	Type ProviderType `json:"type" yaml:"type"`
	// Enabled indicates if this provider is enabled.
	Enabled bool `json:"enabled" yaml:"enabled"`
	// APIKey is the API key for the provider.
	APIKey string `json:"api_key,omitempty" yaml:"api_key,omitempty"`
	// BaseURL is the base URL for the API.
	BaseURL string `json:"base_url,omitempty" yaml:"base_url,omitempty"`
	// DefaultVoice is the default voice ID.
	DefaultVoice string `json:"default_voice,omitempty" yaml:"default_voice,omitempty"`
	// DefaultFormat is the default audio format.
	DefaultFormat AudioFormat `json:"default_format,omitempty" yaml:"default_format,omitempty"`
	// MaxTextLength is the maximum text length.
	MaxTextLength int `json:"max_text_length,omitempty" yaml:"max_text_length,omitempty"`
}

type ProviderFactory struct{}

type ProviderType string

type Service interface {
	// Synthesize synthesizes text using the default provider.
	Synthesize(ctx context.Context, req *SynthesizeRequest) (*SynthesizeResponse, error)
	// SynthesizeWithProvider synthesizes text using a specific provider.
	SynthesizeWithProvider(ctx context.Context, providerType ProviderType, req *SynthesizeRequest) (*SynthesizeResponse, error)
	// SynthesizeStream synthesizes text with streaming audio output.
	SynthesizeStream(ctx context.Context, req *SynthesizeRequest, callback StreamCallback) error
	// ListVoices returns available voices from the default provider.
	ListVoices(ctx context.Context) ([]Voice, error)
	// ListProviders returns all available providers.
	ListProviders() []ProviderType
	// GetDefaultProvider returns the default provider type.
	GetDefaultProvider() ProviderType
	// SetDefaultProvider sets the default provider type.
	SetDefaultProvider(providerType ProviderType) error
	// GetProvider returns the provider instance for a given provider type.
	GetProvider(providerType ProviderType) Provider
	// GetConfig returns the current TTS configuration (speed, pitch, volume).
	GetConfig() (speed, pitch, volume float32)
	// SetConfig sets the TTS configuration (speed, pitch, volume).
	SetConfig(speed, pitch, volume float32)
	// GetVocoderStatus returns vocoder model status.
	GetVocoderStatus() map[string]interface{}
	// DownloadVocoderModel starts downloading the vocoder model.
	DownloadVocoderModel(ctx context.Context) error
	// CancelVocoderDownload cancels the vocoder download.
	CancelVocoderDownload()
	// GetKokoroStatus returns Kokoro model status.
	GetKokoroStatus() map[string]interface{}
	// DownloadKokoroModel starts downloading the Kokoro model.
	DownloadKokoroModel(ctx context.Context) error
	// CancelKokoroDownload cancels the Kokoro download.
	CancelKokoroDownload()
	// Close cleans up all provider resources.
	Close()
}

type ServiceConfig struct {
	DefaultProvider ProviderType
	Providers       []ProviderConfig
	DataPath        string // Path for model downloads
}

type StreamCallback func(chunk []byte) error

type SynthesizeRequest struct {
	// Text is the text to synthesize.
	Text string
	// Voice is the voice ID to use.
	Voice string
	// Format is the output audio format.
	Format AudioFormat
	// Speed is the speech speed (0.25-4.0, default 1.0).
	Speed float32
	// Pitch is the speech pitch adjustment.
	Pitch float32
	// Volume is the speech volume (0-200, default 100).
	Volume float32
}

type SynthesizeResponse struct {
	// Audio is the synthesized audio data.
	Audio io.ReadCloser
	// Format is the audio format.
	Format AudioFormat
	// ContentType is the MIME content type.
	ContentType string
	// Duration is the estimated audio duration in seconds.
	Duration float64
}

type VocoderModelManager struct{}

type Voice struct {
	// ID is the voice identifier.
	ID string `json:"id"`
	// Name is the display name.
	Name string `json:"name"`
	// Language is the voice language.
	Language string `json:"language"`
	// Gender is the voice gender.
	Gender string `json:"gender,omitempty"`
	// Description is the voice description.
	Description string `json:"description,omitempty"`
	// PreviewURL is a URL to preview the voice.
	PreviewURL string `json:"preview_url,omitempty"`
	// Provider is the TTS provider name (e.g., "Kokoro", "eSpeak-NG (Robotic)").
	Provider string `json:"provider,omitempty"`
	// Quality indicates voice quality level (e.g., "high", "medium", "low").
	Quality string `json:"quality,omitempty"`
}