elevenlabs

type ChunkedStream struct {
	*tts.BaseChunkedStream
	// contains filtered or unexported fields
}

type ElevenLabsSTTModels = STTModel

type Plugin struct{}

type PreferredAlignment string

type PronunciationDictionaryLocator struct {
	PronunciationDictionaryID string `json:"pronunciation_dictionary_id"`
	VersionID                 string `json:"version_id"`
}

type ProtocolError struct {
	Message string
	Cause   error
}

type ProviderError struct {
	Type          string
	Message       string
	Details       string
	RetryableFlag bool
	Body          any
}

type STT struct {
	*stt.Base
	// contains filtered or unexported fields
}

type STTModel string

type STTOptions struct {
	APIKey            string
	BaseURL           string
	Language          agents.LanguageCode
	LanguageCode      agents.LanguageCode // Deprecated: use Language.
	TagAudioEvents    *bool
	UseRealtime       *bool // Deprecated: select ScribeV2Realtime with Model.
	SampleRate        STTRealtimeSampleRate
	ServerVAD         *VADOptions
	IncludeTimestamps bool
	Model             STTModel
	ModelID           STTModel // Deprecated: use Model.
	Keyterms          []string
	NoVerbatim        bool
	EnableLogging     *bool

	HTTPClient        *http.Client
	WebSocketDialer   *websocket.Dialer
	InputCapacity     int
	OutputCapacity    int
	ProviderEventCap  int
	MaxResponseBytes  int64
	MaxWSMessageBytes int64
	MaxReplayDuration time.Duration
	ReadWriteTimeout  time.Duration
	UserAgent         string
}

type STTRealtimeSampleRate int

type STTRealtimeSampleRates = STTRealtimeSampleRate

type STTUpdateOptions struct {
	TagAudioEvents *bool
	ServerVAD      agents.Override[VADOptions]
	Keyterms       agents.Override[[]string]
	NoVerbatim     *bool
}

type SpeechStream struct {
	*stt.BaseStream
	// contains filtered or unexported fields
}

type SynthesizeStream struct {
	*tts.BaseSynthesizeStream
	// contains filtered or unexported fields
}

type TTS struct {
	*tts.Base
	// contains filtered or unexported fields
}

type TTSEncoding string

type TTSModel string

type TTSModels = TTSModel

type TTSOptions struct {
	APIKey        string
	VoiceID       string
	VoiceSettings *VoiceSettings
	Model         TTSModel
	Language      agents.LanguageCode

	Voice        *Voice              // Deprecated: use VoiceID and VoiceSettings.
	ModelID      TTSModel            // Deprecated: use Model.
	LanguageCode agents.LanguageCode // Deprecated: use Language.

	BaseURL                         string
	Encoding                        TTSEncoding
	StreamingLatency                *int
	Tokenizer                       TextTokenizer
	WordTokenizer                   TextTokenizer // Deprecated: use Tokenizer.
	ChunkLengthSchedule             []int
	EnableSSMLParsing               bool
	EnableLogging                   *bool
	InactivityTimeout               time.Duration
	SyncAlignment                   *bool
	ApplyTextNormalization          TextNormalization
	ApplyLanguageTextNormalization  *bool
	PreferredAlignment              PreferredAlignment
	AutoMode                        *bool
	PronunciationDictionaryLocators []PronunciationDictionaryLocator

	HTTPClient        *http.Client
	WebSocketDialer   *websocket.Dialer
	InputCapacity     int
	OutputCapacity    int
	WriterCapacity    int
	ProviderEventCap  int
	MaxResponseBytes  int64
	MaxWSMessageBytes int64
	ReadWriteTimeout  time.Duration
	MaxActiveContexts int
	UserAgent         string
}

type TTSUpdateOptions struct {
	VoiceID                         *string
	VoiceSettings                   agents.Override[VoiceSettings]
	Model                           *TTSModel
	Language                        agents.Override[agents.LanguageCode]
	PronunciationDictionaryLocators agents.Override[[]PronunciationDictionaryLocator]
}

type TextNormalization string

type TextTokenizer interface {
	TokenizeSpans(string) []tokenize.Span
}

type UnsupportedEncodingError struct {
	Encoding TTSEncoding
	Reason   string
}

type UnsupportedTransportError struct {
	Model     TTSModel
	Transport string
}

type VADOptions struct {
	VADSilenceThreshold *time.Duration
	VADThreshold        *float64
	MinSpeechDuration   *time.Duration
	MinSilenceDuration  *time.Duration
}

type Voice struct {
	ID       string         `json:"voice_id"`
	Name     string         `json:"name"`
	Category string         `json:"category"`
	Settings *VoiceSettings `json:"settings,omitempty"`
}

type VoiceSettings struct {
	Stability       float64  `json:"stability"`
	SimilarityBoost float64  `json:"similarity_boost"`
	Style           *float64 `json:"style,omitempty"`
	Speed           *float64 `json:"speed,omitempty"`
	UseSpeakerBoost *bool    `json:"use_speaker_boost,omitempty"`
}