elevenlabs

type APIError struct {
	StatusCode int
	Message    string
	Detail     string
}

type AlignmentCharacter struct {
	// Text is the character text.
	Text string

	// Start is the start time in seconds.
	Start float64

	// End is the end time in seconds.
	End float64
}

type AlignmentWord struct {
	// Text is the word text.
	Text string

	// Start is the start time in seconds.
	Start float64

	// End is the end time in seconds.
	End float64

	// Loss is the confidence score for this word.
	Loss float64
}

type AudioIsolationRequest struct {
	// Audio is the audio file to process (required).
	Audio io.Reader

	// Filename is the name of the file (required).
	Filename string
}

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

type Chapter struct {
	// ChapterID is the unique identifier.
	ChapterID string

	// Name is the chapter name.
	Name string

	// ConversionProgress is the conversion progress percentage.
	ConversionProgress float64

	// State is the current state.
	State string

	// LastConversionError is the last conversion error if any.
	LastConversionError string
}

type ChapterSnapshot struct {
	// ChapterSnapshotID is the unique identifier.
	ChapterSnapshotID string

	// ProjectID is the parent project ID.
	ProjectID string

	// ChapterID is the chapter ID.
	ChapterID string

	// Name is the snapshot name.
	Name string

	// CreatedAt is when the snapshot was created.
	CreatedAt time.Time
}

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

type CompositionPlan struct {
	// PositiveGlobalStyles are styles that should be present throughout the song.
	PositiveGlobalStyles []string

	// NegativeGlobalStyles are styles that should NOT be present in the song.
	NegativeGlobalStyles []string

	// Sections defines the structure of the song with individual sections.
	Sections []SongSection
}

type CompositionPlanRequest struct {
	// Prompt is the text description of the music to plan.
	Prompt string

	// DurationMs is the target duration in milliseconds (3000-600000).
	DurationMs int

	// SourcePlan is an optional existing plan to use as a starting point.
	SourcePlan *CompositionPlan
}

type CreateProjectRequest struct {
	// Name is the project name (required).
	Name string

	// Description is an optional description.
	Description string

	// Author is an optional author name.
	Author string

	// Language is the two-letter language code (ISO 639-1).
	Language string

	// DefaultModelID is the model to use for TTS.
	DefaultModelID string

	// DefaultParagraphVoiceID is the default voice for paragraphs.
	DefaultParagraphVoiceID string

	// DefaultTitleVoiceID is the default voice for titles.
	DefaultTitleVoiceID string

	// FromURL is a URL to extract content from.
	FromURL string

	// ContentType is the content type (e.g., "Novel", "Short Story").
	ContentType string

	// Genres is a list of genres.
	Genres []string

	// QualityPreset is the output quality: "standard", "high", "ultra", "ultra lossless".
	QualityPreset string

	// AutoConvert automatically converts the project to audio.
	AutoConvert bool
}

type CreatePronunciationDictionaryRequest struct {
	// Name is the name of the dictionary (required).
	Name string

	// Description is an optional description.
	Description string

	// PLSContent is the PLS (Pronunciation Lexicon Specification) XML content.
	// Use this to provide pronunciation rules directly.
	// You can generate this from PronunciationRules using ToPLSString().
	PLSContent string

	// Rules is a convenient alternative to PLSContent.
	// If provided, it will be converted to PLS format automatically.
	// If both PLSContent and Rules are provided, PLSContent takes precedence.
	Rules PronunciationRules

	// Language is the language code for the rules (default: "en-US").
	// Only used when Rules is provided.
	Language string
}

type DialogueInput struct {
	// Text is the text to be spoken.
	Text string

	// VoiceID is the ID of the voice to use.
	VoiceID string
}

type DialogueRequest struct {
	// Inputs is a list of dialogue turns with text and voice pairs.
	Inputs []DialogueInput

	// ModelID is the model to use (default: eleven_multilingual_v2).
	ModelID string

	// LanguageCode is the ISO 639-1 language code (e.g., "en").
	LanguageCode string

	// Seed for deterministic generation (0-4294967295).
	Seed int
}

type DialogueResponse struct {
	// AudioBase64 is the base64-encoded audio data.
	AudioBase64 string

	// VoiceSegments contains timing info for each voice segment.
	VoiceSegments []VoiceSegment
}

type DubbingProject struct {
	// DubbingID is the unique identifier.
	DubbingID string

	// Name is the project name.
	Name string

	// Status is the current status (dubbed, dubbing, failed, cloning).
	Status string

	// TargetLanguages are the target languages for dubbing.
	TargetLanguages []string

	// SourceLanguage is the source language.
	SourceLanguage string

	// Error contains any error message if the project failed.
	Error string

	// CreatedAt is when the project was created.
	CreatedAt time.Time
}

type DubbingRequest struct {
	// Name is the name of the dubbing project.
	Name string

	// SourceURL is the URL of the source media (alternative to file upload).
	SourceURL string

	// File is the source media file (alternative to SourceURL).
	File io.Reader

	// SourceLanguage is the source language code (ISO 639-1).
	SourceLanguage string

	// TargetLanguage is the target language code (ISO 639-1).
	TargetLanguage string

	// NumSpeakers is the number of speakers (0 for auto-detection).
	NumSpeakers int

	// Watermark enables watermark (for free tier).
	Watermark bool

	// StartTime is the start time in seconds for dubbing.
	StartTime int

	// EndTime is the end time in seconds for dubbing.
	EndTime int

	// HighestResolution requests highest resolution output.
	HighestResolution bool

	// DropBackgroundAudio removes background audio.
	DropBackgroundAudio bool
}

type DubbingResponse struct {
	// DubbingID is the ID of the created project.
	DubbingID string

	// ExpectedDurationSeconds is the expected duration.
	ExpectedDurationSeconds float64
}

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

type ForcedAlignmentRequest struct {
	// File is the audio file to align (required).
	File io.Reader

	// Filename is the name of the file (required).
	Filename string

	// Text is the text to align with the audio (required).
	Text string
}

type ForcedAlignmentResponse struct {
	// Words contains word-level timing information.
	Words []AlignmentWord

	// Characters contains character-level timing information.
	Characters []AlignmentCharacter

	// Loss is the average alignment confidence score.
	Loss float64
}

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

type HistoryItem struct {
	// HistoryItemID is the unique identifier.
	HistoryItemID string

	// VoiceID is the ID of the voice used.
	VoiceID string

	// VoiceName is the name of the voice used.
	VoiceName string

	// VoiceCategory is the category of the voice.
	VoiceCategory string

	// ModelID is the ID of the model used.
	ModelID string

	// Text is the text that was converted to speech.
	Text string

	// State is the state of the history item.
	State string

	// Source is the source of the generation.
	Source string

	// ContentType is the content type of the audio.
	ContentType string

	// CharactersUsed is the number of characters used.
	CharactersUsed int

	// CreatedAt is when the item was created.
	CreatedAt time.Time
}

type HistoryListOptions struct {
	// PageSize is the number of items per page.
	PageSize int

	// StartAfterHistoryItemID is for pagination (fetch items after this ID).
	StartAfterHistoryItemID string

	// VoiceID filters by voice ID.
	VoiceID string
}

type HistoryListResponse struct {
	// Items is the list of history items.
	Items []*HistoryItem

	// HasMore indicates if there are more items to fetch.
	HasMore bool

	// LastHistoryItemID is the ID of the last item (for pagination).
	LastHistoryItemID string
}

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

type Language struct {
	// LanguageID is the unique identifier (ISO code).
	LanguageID string

	// Name is the display name of the language.
	Name string
}

type ListPhoneNumbersResponse struct {
	PhoneNumbers []PhoneNumber `json:"phone_numbers"`
}

type Model struct {
	// ModelID is the unique identifier for the model.
	ModelID string

	// Name is the display name of the model.
	Name string

	// Description is the model description.
	Description string

	// CanDoTextToSpeech indicates if the model supports TTS.
	CanDoTextToSpeech bool

	// CanDoVoiceConversion indicates if the model supports voice conversion.
	CanDoVoiceConversion bool

	// CanBeFinetuned indicates if the model can be fine-tuned.
	CanBeFinetuned bool

	// CanUseStyle indicates if the model supports style settings.
	CanUseStyle bool

	// CanUseSpeakerBoost indicates if the model supports speaker boost.
	CanUseSpeakerBoost bool

	// Languages is the list of supported languages.
	Languages []*Language

	// MaxCharactersFreeUser is the max characters for free users.
	MaxCharactersFreeUser int

	// MaxCharactersSubscribedUser is the max characters for subscribed users.
	MaxCharactersSubscribedUser int

	// TokenCostFactor is the cost factor for the model.
	TokenCostFactor float64
}

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

type MusicDetailedRequest struct {
	// Prompt is a simple text description (cannot be used with CompositionPlan).
	Prompt string

	// CompositionPlan is a detailed plan (cannot be used with Prompt).
	CompositionPlan *CompositionPlan

	// DurationMs is the length in milliseconds (only used with Prompt).
	DurationMs int

	// ForceInstrumental ensures no vocals (only used with Prompt).
	ForceInstrumental bool

	// Seed for deterministic generation.
	Seed int

	// WithTimestamps returns word timestamps in the response.
	WithTimestamps bool
}

type MusicDetailedResponse struct {
	// Audio is the generated music.
	Audio io.Reader

	// SongID is the unique identifier for this song.
	SongID string
}

type MusicRequest struct {
	// Prompt is a simple text description of the music to generate.
	// Cannot be used with CompositionPlan.
	Prompt string

	// DurationMs is the length of the song in milliseconds (3000-600000).
	// If not provided, the model will choose based on the prompt.
	DurationMs int

	// ForceInstrumental ensures the song has no vocals.
	ForceInstrumental bool

	// Seed for deterministic generation (optional).
	Seed int
}

type MusicResponse struct {
	// Audio is the generated music.
	Audio io.Reader

	// SongID is the unique identifier for this song.
	SongID string
}

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

type Option func(*clientOptions)

type PhoneNumber struct {
	ID          string `json:"phone_number_id"`
	PhoneNumber string `json:"phone_number"`
	Label       string `json:"label"`
	AgentID     string `json:"agent_id,omitempty"`
	Provider    string `json:"provider"` // "twilio", "sip"
	Status      string `json:"status"`
	CreatedAt   string `json:"created_at"`
}

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

type Project struct {
	// ProjectID is the unique identifier.
	ProjectID string

	// Name is the project name.
	Name string

	// Description is the project description.
	Description string

	// Author is the project author.
	Author string

	// Language is the two-letter language code (ISO 639-1).
	Language string

	// DefaultModelID is the default model for TTS.
	DefaultModelID string

	// DefaultParagraphVoiceID is the default voice for paragraphs.
	DefaultParagraphVoiceID string

	// DefaultTitleVoiceID is the default voice for titles.
	DefaultTitleVoiceID string

	// ContentType is the content type (e.g., "Novel", "Short Story").
	ContentType string

	// CoverImageURL is the cover image URL.
	CoverImageURL string

	// CreatedAt is the creation timestamp.
	CreatedAt time.Time

	// CanBeDownloaded indicates if the project can be downloaded.
	CanBeDownloaded bool

	// AccessLevel is the access level of the project.
	AccessLevel string
}

type ProjectSnapshot struct {
	// ProjectSnapshotID is the unique identifier.
	ProjectSnapshotID string

	// ProjectID is the parent project ID.
	ProjectID string

	// Name is the snapshot name.
	Name string

	// CreatedAt is when the snapshot was created.
	CreatedAt time.Time
}

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

type PronunciationDictionary struct {
	// ID is the unique identifier.
	ID string

	// Name is the display name.
	Name string

	// Description is the dictionary description.
	Description string

	// LatestVersionID is the ID of the latest version.
	LatestVersionID string

	// RulesCount is the number of rules in the latest version.
	RulesCount int

	// CreatedBy is the user ID who created the dictionary.
	CreatedBy string

	// CreatedAt is when the dictionary was created.
	CreatedAt time.Time
}

type PronunciationDictionaryListOptions struct {
	// PageSize is the number of items per page (max 100).
	PageSize int

	// Cursor is the pagination cursor.
	Cursor string
}

type PronunciationDictionaryListResponse struct {
	// Dictionaries is the list of pronunciation dictionaries.
	Dictionaries []*PronunciationDictionary

	// HasMore indicates if there are more items to fetch.
	HasMore bool

	// NextCursor is the cursor for pagination.
	NextCursor string
}

type PronunciationRule struct {
	// Grapheme is the text to match (required).
	Grapheme string `json:"grapheme"`

	// Alias is the replacement text (mutually exclusive with Phoneme).
	// This is the easier option - just specify what text should be read instead.
	Alias string `json:"alias,omitempty"`

	// Phoneme is the IPA pronunciation (mutually exclusive with Alias).
	// Use this for precise phonetic control.
	Phoneme string `json:"phoneme,omitempty"`
}

type PronunciationRules []PronunciationRule

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

type SIPOutboundCallRequest struct {
	// AgentID is the ElevenLabs agent ID to handle the call.
	AgentID string `json:"agent_id"`

	// ToNumber is the phone number to call (E.164 format).
	ToNumber string `json:"to_number"`

	// SIPTrunkID is the SIP trunk ID to use.
	SIPTrunkID string `json:"sip_trunk_id"`

	// FromNumber is the caller ID to display (must be verified).
	FromNumber string `json:"from_number,omitempty"`

	// CustomLLMExtraBody is additional data to pass to the LLM.
	CustomLLMExtraBody map[string]any `json:"custom_llm_extra_body,omitempty"`

	// DynamicVariables are variables to inject into the agent prompt.
	DynamicVariables map[string]string `json:"dynamic_variables,omitempty"`

	// FirstMessage overrides the agent's default first message.
	FirstMessage string `json:"first_message,omitempty"`

	// SystemPrompt overrides the agent's system prompt.
	SystemPrompt string `json:"system_prompt,omitempty"`
}

type SIPOutboundCallResponse struct {
	// ConversationID is the ElevenLabs conversation ID for this call.
	ConversationID string `json:"conversation_id"`

	// Status is the initial call status.
	Status string `json:"status"`
}

type STTTranscript struct {
	// Text is the transcribed text.
	Text string `json:"text"`

	// IsFinal indicates if this is a final (non-partial) result.
	IsFinal bool `json:"is_final"`

	// Confidence is the confidence score (0.0 to 1.0).
	Confidence float64 `json:"confidence,omitempty"`

	// Words contains word-level timing if enabled.
	Words []STTWord `json:"words,omitempty"`

	// LanguageCode is the detected language.
	LanguageCode string `json:"language_code,omitempty"`

	// StartTime is the start time in seconds.
	StartTime float64 `json:"start_time,omitempty"`

	// EndTime is the end time in seconds.
	EndTime float64 `json:"end_time,omitempty"`
}

type STTWord struct {
	Word       string  `json:"word"`
	Start      float64 `json:"start"`
	End        float64 `json:"end"`
	Confidence float64 `json:"confidence,omitempty"`
}

type SaveVoiceRequest struct {
	// GeneratedVoiceID from the design response.
	GeneratedVoiceID string

	// VoiceName is the name for the saved voice.
	VoiceName string

	// VoiceDescription describes the voice.
	VoiceDescription string

	// Labels are optional metadata tags.
	Labels map[string]string
}

type SongSection struct {
	// SectionName is the name of the section (e.g., "intro", "verse", "chorus").
	SectionName string

	// DurationMs is the duration in milliseconds (3000-120000).
	DurationMs int

	// Lines are the lyrics for this section (max 200 chars per line).
	Lines []string

	// PositiveLocalStyles are styles for this specific section.
	PositiveLocalStyles []string

	// NegativeLocalStyles are styles to avoid in this section.
	NegativeLocalStyles []string
}

type SoundEffectRequest struct {
	// Text is the description of the sound effect to generate.
	// Examples: "car engine starting", "thunder and rain", "crowd cheering"
	Text string

	// DurationSeconds is the target duration (0.5 to 30 seconds).
	// If not set, the optimal duration will be guessed from the prompt.
	DurationSeconds float64

	// PromptInfluence controls how closely the generation follows the prompt (0.0 to 1.0).
	// Higher values = more faithful to prompt but less variation.
	// Default is 0.3.
	PromptInfluence float64

	// Loop creates a sound effect that loops smoothly.
	Loop bool

	// OutputFormat specifies the audio format (e.g., "mp3_44100_128").
	OutputFormat string
}

type SoundEffectResponse struct {
	// Audio is the generated sound effect data.
	Audio io.Reader
}

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

type SpeechToSpeechRequest struct {
	// VoiceID is the target voice to convert to.
	VoiceID string

	// Audio is the source audio data to convert.
	Audio io.Reader

	// AudioFilename is the filename for the audio (optional, helps with format detection).
	AudioFilename string

	// ModelID is the model to use. Defaults to "eleven_english_sts_v2".
	ModelID string

	// VoiceSettings configures the voice parameters.
	VoiceSettings *VoiceSettings

	// OutputFormat specifies the audio output format.
	// Examples: "mp3_44100_128", "pcm_16000", "pcm_22050"
	OutputFormat string

	// RemoveBackgroundNoise removes background noise from the source audio.
	RemoveBackgroundNoise bool

	// SeedAudio is optional seed audio to influence the conversion.
	SeedAudio io.Reader

	// SeedAudioFilename is the filename for the seed audio.
	SeedAudioFilename string
}

type SpeechToSpeechResponse struct {
	// Audio is the converted audio data.
	Audio io.Reader
}

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

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

type StemSeparationRequest struct {
	// File is the audio file to separate.
	File io.Reader

	// Filename is the name of the file.
	Filename string

	// StemVariation specifies which stem variation to use.
	// Options: "two_stems_v1" (vocals + music), "six_stems_v1" (vocals, drums, bass, other - default)
	StemVariation string
}

type Subscription struct {
	// Tier is the subscription tier (e.g., "free", "starter", "creator").
	Tier string

	// Status is the subscription status.
	Status string

	// CharacterCount is the number of characters used.
	CharacterCount int

	// CharacterLimit is the maximum characters allowed.
	CharacterLimit int

	// VoiceLimit is the maximum number of voices allowed.
	VoiceLimit int

	// VoiceSlotsUsed is the number of voice slots used.
	VoiceSlotsUsed int

	// CanUseInstantVoiceCloning indicates if instant cloning is available.
	CanUseInstantVoiceCloning bool

	// CanUseProfessionalVoiceCloning indicates if pro cloning is available.
	CanUseProfessionalVoiceCloning bool

	// NextCharacterResetUnix is when characters reset (Unix timestamp).
	NextCharacterResetUnix int64
}

type TTSAlignment struct {
	Characters     []string  `json:"characters"`
	CharacterStart []float64 `json:"character_start_times_seconds"`
	CharacterEnd   []float64 `json:"character_end_times_seconds"`
}

type TTSRequest struct {
	// VoiceID is the voice to use for generation.
	VoiceID string

	// Text is the text to convert to speech.
	Text string

	// ModelID is the model to use. Defaults to DefaultModelID.
	ModelID string

	// VoiceSettings configures the voice parameters.
	// If nil, default settings will be used.
	VoiceSettings *VoiceSettings

	// OutputFormat specifies the audio output format.
	// Examples: "mp3_44100_128", "pcm_16000", "pcm_22050"
	OutputFormat string

	// LanguageCode is the ISO 639-1 language code for text normalization.
	LanguageCode string
}

type TTSResponse struct {
	// Audio is the generated audio data.
	Audio io.Reader
}

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

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

type TranscriptionRequest struct {
	// FileURL is the HTTPS URL of the file to transcribe.
	// Either FileURL or FileContent must be provided.
	FileURL string

	// FileContent is the base64-encoded file content.
	// Either FileURL or FileContent must be provided.
	FileContent string

	// LanguageCode is an ISO-639-1 or ISO-639-3 language code.
	// If not provided, language is auto-detected.
	LanguageCode string

	// Diarize enables speaker diarization (who said what).
	Diarize bool

	// NumSpeakers is the expected number of speakers (for diarization).
	NumSpeakers int

	// TagAudioEvents tags audio events like laughter, applause, etc.
	TagAudioEvents bool

	// ModelID is the transcription model to use (default: "scribe_v1").
	ModelID string
}

type TranscriptionResponse struct {
	// Text is the full transcribed text.
	Text string

	// LanguageCode is the detected language.
	LanguageCode string

	// Words contains word-level details with timestamps.
	Words []TranscriptionWord

	// Utterances contains speaker-labeled segments (when diarization is enabled).
	Utterances []TranscriptionUtterance
}

type TranscriptionUtterance struct {
	// Text is the utterance text.
	Text string

	// Start is the start time in seconds.
	Start float64

	// End is the end time in seconds.
	End float64

	// Speaker is the speaker ID.
	Speaker string
}

type TranscriptionWord struct {
	// Text is the word text.
	Text string

	// Start is the start time in seconds.
	Start float64

	// End is the end time in seconds.
	End float64

	// Confidence is the confidence score (0-1).
	Confidence float64

	// Speaker is the speaker ID (when diarization is enabled).
	Speaker string

	// Type is the word type (e.g., "word", "punctuation").
	Type string
}

type TwilioOutboundCallRequest struct {
	// AgentID is the ElevenLabs agent ID to handle the call.
	AgentID string `json:"agent_id"`

	// AgentPhoneNumberID is the ElevenLabs phone number ID to call from.
	AgentPhoneNumberID string `json:"agent_phone_number_id"`

	// ToNumber is the phone number to call (E.164 format).
	ToNumber string `json:"to_number"`

	// CustomLLMExtraBody is additional data to pass to the LLM.
	CustomLLMExtraBody map[string]any `json:"custom_llm_extra_body,omitempty"`

	// DynamicVariables are variables to inject into the agent prompt.
	DynamicVariables map[string]string `json:"dynamic_variables,omitempty"`

	// FirstMessage overrides the agent's default first message.
	FirstMessage string `json:"first_message,omitempty"`

	// SystemPrompt overrides the agent's system prompt.
	SystemPrompt string `json:"system_prompt,omitempty"`
}

type TwilioOutboundCallResponse struct {
	// CallSID is the Twilio call SID.
	CallSID string `json:"call_sid"`

	// ConversationID is the ElevenLabs conversation ID for this call.
	ConversationID string `json:"conversation_id"`

	// Status is the initial call status.
	Status string `json:"status"`
}

type TwilioRegisterCallRequest struct {
	// AgentID is the ElevenLabs agent ID to handle the call.
	AgentID string `json:"agent_id"`

	// AgentPhoneNumberID is the ElevenLabs phone number ID (if using imported number).
	AgentPhoneNumberID string `json:"agent_phone_number_id,omitempty"`

	// CustomLLMExtraBody is additional data to pass to the LLM.
	CustomLLMExtraBody map[string]any `json:"custom_llm_extra_body,omitempty"`

	// DynamicVariables are variables to inject into the agent prompt.
	DynamicVariables map[string]string `json:"dynamic_variables,omitempty"`

	// FirstMessage overrides the agent's default first message.
	FirstMessage string `json:"first_message,omitempty"`

	// SystemPrompt overrides the agent's system prompt.
	SystemPrompt string `json:"system_prompt,omitempty"`
}

type TwilioRegisterCallResponse struct {
	// TwiML is the TwiML response to return to Twilio.
	TwiML string `json:"twiml"`

	// ConversationID is the ElevenLabs conversation ID for this call.
	ConversationID string `json:"conversation_id,omitempty"`
}

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

type UpdatePhoneNumberRequest struct {
	// Label is a descriptive label for the phone number.
	Label string `json:"label,omitempty"`

	// AgentID is the agent to associate with this phone number.
	AgentID string `json:"agent_id,omitempty"`
}

type UpdateProjectRequest struct {
	// Name is the new project name (required).
	Name string

	// DefaultParagraphVoiceID is the new default paragraph voice (required).
	DefaultParagraphVoiceID string

	// DefaultTitleVoiceID is the new default title voice (required).
	DefaultTitleVoiceID string

	// Author is an optional author name.
	Author string

	// Title is an optional title.
	Title string
}

type User struct {
	// UserID is the unique user identifier.
	UserID string

	// FirstName is the user's first name.
	FirstName string

	// Subscription contains the user's subscription details.
	Subscription *Subscription

	// CreatedAt is when the user was created.
	CreatedAt time.Time
}

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

type ValidationError struct {
	Field   string
	Message string
}

type Voice struct {
	// VoiceID is the unique identifier for the voice.
	VoiceID string

	// Name is the display name of the voice.
	Name string

	// Category is the category of the voice (e.g., "premade", "cloned").
	Category string

	// Description is the description of the voice.
	Description string

	// PreviewURL is the URL to preview the voice.
	PreviewURL string

	// Labels contains additional metadata about the voice.
	Labels map[string]string
}

type VoiceAccent string

type VoiceAge string

type VoiceDesignRequest struct {
	// Gender of the voice (required).
	Gender VoiceGender

	// Age category of the voice (required).
	Age VoiceAge

	// Accent of the voice (required).
	Accent VoiceAccent

	// AccentStrength controls accent prominence (0.3 to 2.0).
	AccentStrength float64

	// Text for voice preview (100-1000 characters).
	Text string
}

type VoiceDesignResponse struct {
	// Audio is the generated voice sample.
	Audio io.Reader

	// GeneratedVoiceID can be used to save this voice permanently.
	GeneratedVoiceID string
}

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

type VoiceGender string

type VoiceSegment struct {
	// VoiceID is the voice used for this segment.
	VoiceID string

	// StartTime is the start time in seconds.
	StartTime float64

	// EndTime is the end time in seconds.
	EndTime float64
}

type VoiceSettings struct {
	// Stability determines how stable the voice is (0.0 to 1.0).
	// Lower values introduce broader emotional range.
	Stability float64

	// SimilarityBoost determines how closely the AI should adhere to
	// the original voice (0.0 to 1.0).
	SimilarityBoost float64

	// Style determines the style exaggeration (0.0 to 1.0).
	// Higher values amplify the original speaker's style.
	Style float64

	// Speed adjusts the speed of the voice (0.25 to 4.0).
	// 1.0 is the default speed.
	Speed float64

	// UseSpeakerBoost boosts similarity to the original speaker.
	UseSpeakerBoost bool
}

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

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

type WebSocketSTTOptions struct {
	// ModelID is the transcription model to use.
	// Options: "scribe_v1" (default), "scribe_v1_experimental"
	ModelID string

	// LanguageCode is the expected language (e.g., "en", "es").
	// If not specified, language will be auto-detected.
	LanguageCode string

	// SampleRate is the audio sample rate in Hz.
	// Common values: 8000, 16000, 22050, 44100
	SampleRate int

	// Encoding is the audio encoding format.
	// Options: "pcm_s16le" (default), "pcm_mulaw"
	Encoding string

	// EnablePartials enables partial/interim transcription results.
	EnablePartials bool

	// EnableWordTimestamps enables word-level timing information.
	EnableWordTimestamps bool

	// MaxAlternatives is the maximum number of transcription alternatives.
	MaxAlternatives int
}

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

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

type WebSocketTTSOptions struct {
	// ModelID is the model to use. Defaults to "eleven_turbo_v2_5" for low latency.
	ModelID string

	// OutputFormat specifies the audio output format.
	// Recommended for real-time: "pcm_16000", "pcm_22050", "pcm_24000", "pcm_44100"
	// Also supports: "mp3_44100_64", "mp3_44100_96", "mp3_44100_128", "mp3_44100_192"
	OutputFormat string

	// VoiceSettings configures the voice parameters.
	VoiceSettings *VoiceSettings

	// OptimizeStreamingLatency reduces latency at the cost of quality (0-4).
	// 0 = no optimization, 4 = maximum optimization.
	OptimizeStreamingLatency int

	// EnableSSMLParsing enables SSML parsing for the input text.
	EnableSSMLParsing bool

	// LanguageCode is the ISO language code (e.g., "en", "es").
	LanguageCode string

	// ChunkLengthSchedule controls text chunking for audio generation.
	// Array of integers representing character counts before generating audio.
	ChunkLengthSchedule []int

	// InactivityTimeout is the context timeout in seconds (default 20).
	InactivityTimeout int

	// PronunciationDictionaryIDs is a list of pronunciation dictionary IDs to use.
	PronunciationDictionaryIDs []string
}

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