elevenlabs

package module
v0.1.0 Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: Jun 28, 2026 License: MIT Imports: 17 Imported by: 0

Documentation

Overview

Package elevenlabs provides a small Go client for the ElevenLabs API.

Index

Constants

This section is empty.

Variables

This section is empty.

Functions

This section is empty.

Types

type APIError 

type APIError struct {
	StatusCode      int
	Status          string
	Message         string
	Body            []byte
	ProviderType    string
	ProviderCode    string
	ProviderStatus  string
	ProviderMessage string
	RequestID       string
	TraceID         string
	RetryAfter      string
	Validation      []ValidationError
	RawResponse     RawResponse
}

APIError is returned when the ElevenLabs API responds with a non-2xx status.

func (*APIError) Error 

func (e *APIError) Error() string

type Client 

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

Client is an ElevenLabs API client.

func NewClient 

func NewClient(apiKey string, opts ...ClientOption) *Client

NewClient creates a Client that authenticates with apiKey.

func (*Client) ConnectRealtimeTranscript 

func (c *Client) ConnectRealtimeTranscript(ctx context.Context, in RealtimeTranscriptRequest) (*RealtimeTranscriptSession, error)

ConnectRealtimeTranscript opens a realtime speech-to-text WebSocket session.

func (*Client) CreateTranscript 

func (c *Client) CreateTranscript(ctx context.Context, in CreateTranscriptRequest) (*Transcript, error)

CreateTranscript transcribes an audio or video file.

func (*Client) CreateTranscriptWithResponse 

func (c *Client) CreateTranscriptWithResponse(ctx context.Context, in CreateTranscriptRequest) (*Response[*Transcript], error)

CreateTranscriptWithResponse transcribes an audio or video file and returns HTTP response metadata.

func (*Client) DeleteTranscript 

func (c *Client) DeleteTranscript(ctx context.Context, id string) error

DeleteTranscript deletes a previously generated transcript by ID.

func (*Client) DeleteTranscriptWithResponse 

func (c *Client) DeleteTranscriptWithResponse(ctx context.Context, id string) (*Response[any], error)

DeleteTranscriptWithResponse deletes a previously generated transcript by ID and returns HTTP response metadata.

func (*Client) GetTranscript 

func (c *Client) GetTranscript(ctx context.Context, id string) (*Transcript, error)

GetTranscript retrieves a previously generated transcript by ID.

func (*Client) GetTranscriptWithResponse 

func (c *Client) GetTranscriptWithResponse(ctx context.Context, id string) (*Response[*Transcript], error)

GetTranscriptWithResponse retrieves a previously generated transcript by ID and returns HTTP response metadata.

func (*Client) GetUser 

func (c *Client) GetUser(ctx context.Context) (*User, error)

GetUser gets information about the authenticated user.

func (*Client) GetUserWithResponse 

func (c *Client) GetUserWithResponse(ctx context.Context) (*Response[*User], error)

GetUserWithResponse gets information about the authenticated user and returns HTTP response metadata.

func (*Client) ListModels 

func (c *Client) ListModels(ctx context.Context) ([]Model, error)

ListModels gets the list of available models.

func (*Client) ListModelsWithResponse 

func (c *Client) ListModelsWithResponse(ctx context.Context) (*Response[[]Model], error)

ListModelsWithResponse gets the list of available models and returns HTTP response metadata.

func (*Client) SubmitTranscriptWebhook 

func (c *Client) SubmitTranscriptWebhook(ctx context.Context, in CreateTranscriptRequest) (*TranscriptWebhookResponse, error)

SubmitTranscriptWebhook submits a transcript request for asynchronous webhook processing.

func (*Client) SubmitTranscriptWebhookWithResponse 

func (c *Client) SubmitTranscriptWebhookWithResponse(ctx context.Context, in CreateTranscriptRequest) (*Response[*TranscriptWebhookResponse], error)

SubmitTranscriptWebhookWithResponse submits a transcript request for asynchronous webhook processing and returns HTTP response metadata.

type ClientOption 

type ClientOption func(*Client)

ClientOption configures a Client.

func WithBaseURL 

func WithBaseURL(baseURL string) ClientOption

WithBaseURL overrides the ElevenLabs API base URL.

This is primarily useful for tests.

func WithHTTPClient 

func WithHTTPClient(httpClient *http.Client) ClientOption

WithHTTPClient overrides the HTTP client used for requests.

func WithRetryConfig 

func WithRetryConfig(cfg RetryConfig) ClientOption

WithRetryConfig overrides the retry policy used for replayable requests.

func WithoutRetries 

func WithoutRetries() ClientOption

WithoutRetries disables automatic retries.

type CreateTranscriptRequest 

type CreateTranscriptRequest struct {
	ModelID string

	File            *File
	SourceURL       string
	CloudStorageURL string
	EnableLogging   *bool

	LanguageCode            string
	TimestampsGranularity   string
	AdditionalFormats       []TranscriptAdditionalFormatOptions
	Diarize                 *bool
	DiarizationThreshold    *float64
	NumSpeakers             int
	TagAudioEvents          *bool
	NoVerbatim              *bool
	Webhook                 *bool
	WebhookID               string
	WebhookMetadata         map[string]any
	FileFormat              string
	Temperature             *float64
	Seed                    *int
	UseMultiChannel         *bool
	MultichannelOutputStyle string
	EntityDetection         []string
	UseSpeakerLibrary       *bool
	DetectSpeakerRoles      *bool
	EntityRedaction         []string
	EntityRedactionMode     string
	Keyterms                []string
	ExtraFormFields         map[string][]string

	OnUploadProgress func(UploadProgress)
}

CreateTranscriptRequest contains parameters for creating a speech-to-text transcript.

type DetectedEntity 

type DetectedEntity struct {
	Text       string `json:"text"`
	EntityType string `json:"entity_type"`
	StartChar  int    `json:"start_char"`
	EndChar    int    `json:"end_char"`
}

DetectedEntity is an entity detected in a transcript.

type File 

type File struct {
	Name   string
	Reader io.Reader

	// SizeBytes is the total upload size reported in progress callbacks. When
	// it is not positive, the client attempts to infer the size from Reader.
	SizeBytes int64
}

File is a file upload for multipart API requests.

type Model 

type Model struct {
	ModelID                            string          `json:"model_id"`
	Name                               string          `json:"name,omitempty"`
	CanBeFinetuned                     bool            `json:"can_be_finetuned,omitempty"`
	CanDoTextToSpeech                  bool            `json:"can_do_text_to_speech,omitempty"`
	CanDoVoiceConversion               bool            `json:"can_do_voice_conversion,omitempty"`
	CanUseStyle                        bool            `json:"can_use_style,omitempty"`
	CanUseSpeakerBoost                 bool            `json:"can_use_speaker_boost,omitempty"`
	ServesProVoices                    bool            `json:"serves_pro_voices,omitempty"`
	TokenCostFactor                    float64         `json:"token_cost_factor,omitempty"`
	Description                        string          `json:"description,omitempty"`
	RequiresAlphaAccess                bool            `json:"requires_alpha_access,omitempty"`
	MaxCharactersRequestFreeUser       int             `json:"max_characters_request_free_user,omitempty"`
	MaxCharactersRequestSubscribedUser int             `json:"max_characters_request_subscribed_user,omitempty"`
	MaximumTextLengthPerRequest        int             `json:"maximum_text_length_per_request,omitempty"`
	Languages                          []ModelLanguage `json:"languages,omitempty"`
	ModelRates                         *ModelRates     `json:"model_rates,omitempty"`
	ConcurrencyGroup                   string          `json:"concurrency_group,omitempty"`
}

Model contains metadata for an ElevenLabs model.

type ModelLanguage 

type ModelLanguage struct {
	LanguageID string `json:"language_id"`
	Name       string `json:"name"`
}

ModelLanguage contains language metadata supported by a model.

type ModelRates 

type ModelRates struct {
	CharacterCostMultiplier float64 `json:"character_cost_multiplier"`
	CostDiscountMultiplier  float64 `json:"cost_discount_multiplier,omitempty"`
}

ModelRates contains billing rate metadata for a model.

type RawResponse 

type RawResponse struct {
	StatusCode int
	Status     string
	Header     http.Header
	URL        string
}

RawResponse contains HTTP response metadata.

It intentionally does not include the response body.

type RealtimeAudioChunk 

type RealtimeAudioChunk struct {
	Audio        []byte
	AudioBase64  string
	Commit       bool
	SampleRate   int
	PreviousText string
}

RealtimeAudioChunk is an audio chunk sent to a realtime transcription session.

type RealtimeTranscriptConfig 

type RealtimeTranscriptConfig struct {
	SampleRate               int      `json:"sample_rate,omitempty"`
	AudioFormat              string   `json:"audio_format,omitempty"`
	LanguageCode             string   `json:"language_code,omitempty"`
	CommitStrategy           string   `json:"commit_strategy,omitempty"`
	VADSilenceThresholdSecs  float64  `json:"vad_silence_threshold_secs,omitempty"`
	VADThreshold             float64  `json:"vad_threshold,omitempty"`
	MinSpeechDurationMS      int      `json:"min_speech_duration_ms,omitempty"`
	MinSilenceDurationMS     int      `json:"min_silence_duration_ms,omitempty"`
	ModelID                  string   `json:"model_id,omitempty"`
	EnableLogging            bool     `json:"enable_logging,omitempty"`
	IncludeTimestamps        bool     `json:"include_timestamps,omitempty"`
	IncludeLanguageDetection bool     `json:"include_language_detection,omitempty"`
	Keyterms                 []string `json:"keyterms,omitempty"`
	NoVerbatim               bool     `json:"no_verbatim,omitempty"`
}

RealtimeTranscriptConfig describes the started realtime transcription session.

type RealtimeTranscriptEvent 

type RealtimeTranscriptEvent struct {
	MessageType  string                   `json:"message_type"`
	SessionID    string                   `json:"session_id,omitempty"`
	Config       RealtimeTranscriptConfig `json:"config,omitempty"`
	Text         string                   `json:"text,omitempty"`
	LanguageCode string                   `json:"language_code,omitempty"`
	Words        []RealtimeTranscriptWord `json:"words,omitempty"`
	Error        string                   `json:"error,omitempty"`
}

RealtimeTranscriptEvent is a JSON event received from a realtime speech-to-text session.

type RealtimeTranscriptRequest 

type RealtimeTranscriptRequest struct {
	ModelID                  string
	Token                    string
	IncludeTimestamps        *bool
	IncludeLanguageDetection *bool
	AudioFormat              string
	LanguageCode             string
	CommitStrategy           string
	Keyterms                 []string
	NoVerbatim               *bool
	VADSilenceThresholdSecs  *float64
	VADThreshold             *float64
	MinSpeechDurationMS      *int
	MinSilenceDurationMS     *int
	EnableLogging            *bool
}

RealtimeTranscriptRequest configures a realtime speech-to-text session.

type RealtimeTranscriptSession 

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

RealtimeTranscriptSession is an active realtime speech-to-text WebSocket session.

func (*RealtimeTranscriptSession) Close 

func (s *RealtimeTranscriptSession) Close() error

Close closes the realtime transcription session.

func (*RealtimeTranscriptSession) Receive 

func (s *RealtimeTranscriptSession) Receive() (*RealtimeTranscriptEvent, error)

Receive reads one event from the realtime transcription session.

func (*RealtimeTranscriptSession) SendAudioChunk 

func (s *RealtimeTranscriptSession) SendAudioChunk(chunk RealtimeAudioChunk) error

SendAudioChunk sends one audio chunk to the realtime transcription session.

type RealtimeTranscriptWord 

type RealtimeTranscriptWord struct {
	Text       string   `json:"text"`
	Start      float64  `json:"start,omitempty"`
	End        float64  `json:"end,omitempty"`
	Type       string   `json:"type,omitempty"`
	SpeakerID  string   `json:"speaker_id,omitempty"`
	Logprob    float64  `json:"logprob,omitempty"`
	Characters []string `json:"characters,omitempty"`
}

RealtimeTranscriptWord is word-level data in a realtime transcript event.

type Response 

type Response[T any] struct {
	Data        T
	RawResponse RawResponse
}

Response contains parsed API data and HTTP response metadata.

type RetryConfig 

type RetryConfig struct {
	MaxAttempts int
	BaseDelay   time.Duration
	MaxDelay    time.Duration
	StatusCodes []int
}

RetryConfig configures automatic retries for replayable requests.

MaxAttempts is the total number of attempts, including the initial request. Values less than or equal to 1 disable retries.

func DefaultRetryConfig 

func DefaultRetryConfig() RetryConfig

DefaultRetryConfig returns the default retry policy.

type Transcript 

type Transcript struct {
	Text                string                       `json:"text,omitempty"`
	LanguageCode        string                       `json:"language_code,omitempty"`
	LanguageProbability float64                      `json:"language_probability,omitempty"`
	Words               []TranscriptWord             `json:"words,omitempty"`
	ChannelIndex        *int                         `json:"channel_index,omitempty"`
	AdditionalFormats   []TranscriptAdditionalFormat `json:"additional_formats,omitempty"`
	TranscriptionID     string                       `json:"transcription_id,omitempty"`
	AudioDurationSecs   *float64                     `json:"audio_duration_secs,omitempty"`
	Entities            []DetectedEntity             `json:"entities,omitempty"`
	Transcripts         []Transcript                 `json:"transcripts,omitempty"`
}

Transcript is a speech-to-text transcript response.

func (Transcript) Chunks 

func (t Transcript) Chunks() []Transcript

Chunks returns the channel-level transcripts when present, otherwise the transcript itself as a single chunk.

type TranscriptAdditionalFormat 

type TranscriptAdditionalFormat struct {
	RequestedFormat string `json:"requested_format"`
	FileExtension   string `json:"file_extension"`
	ContentType     string `json:"content_type"`
	IsBase64Encoded bool   `json:"is_base64_encoded"`
	Content         string `json:"content"`
}

TranscriptAdditionalFormat is an additional transcript export returned by the API.

type TranscriptAdditionalFormatOptions 

type TranscriptAdditionalFormatOptions struct {
	Format                      string   `json:"format"`
	IncludeSpeakers             *bool    `json:"include_speakers,omitempty"`
	IncludeTimestamps           *bool    `json:"include_timestamps,omitempty"`
	SegmentOnSilenceLongerThanS *float64 `json:"segment_on_silence_longer_than_s,omitempty"`
	MaxSegmentDurationS         *float64 `json:"max_segment_duration_s,omitempty"`
	MaxSegmentChars             *int     `json:"max_segment_chars,omitempty"`
	MaxCharactersPerLine        *int     `json:"max_characters_per_line,omitempty"`
}

TranscriptAdditionalFormatOptions configures an additional transcript export format.

type TranscriptCharacter 

type TranscriptCharacter struct {
	Text  string   `json:"text"`
	Start *float64 `json:"start,omitempty"`
	End   *float64 `json:"end,omitempty"`
}

TranscriptCharacter is a character-level transcript segment.

type TranscriptWebhookResponse 

type TranscriptWebhookResponse struct {
	Message         string  `json:"message"`
	RequestID       string  `json:"request_id"`
	TranscriptionID *string `json:"transcription_id,omitempty"`
}

TranscriptWebhookResponse is returned when a transcript is submitted for asynchronous webhook processing.

type TranscriptWord 

type TranscriptWord struct {
	Text         string                `json:"text"`
	Type         string                `json:"type,omitempty"`
	Start        *float64              `json:"start,omitempty"`
	End          *float64              `json:"end,omitempty"`
	SpeakerID    string                `json:"speaker_id,omitempty"`
	Logprob      float64               `json:"logprob,omitempty"`
	Characters   []TranscriptCharacter `json:"characters,omitempty"`
	ChannelIndex *int                  `json:"channel_index,omitempty"`
}

TranscriptWord is a word-level transcript segment.

type UploadProgress 

type UploadProgress struct {
	SentBytes int64
	// TotalBytes is -1 when the upload size cannot be determined.
	TotalBytes int64
	Done       bool
	// Attempt starts at 1 and increments when a replayable upload is retried.
	Attempt int
}

UploadProgress reports uploaded file bytes for a transcript request.

type User 

type User struct {
	UserID                      string            `json:"user_id,omitempty"`
	Subscription                *UserSubscription `json:"subscription,omitempty"`
	IsNewUser                   bool              `json:"is_new_user,omitempty"`
	XIAPIKey                    string            `json:"xi_api_key,omitempty"`
	CanUseDelayedPaymentMethods bool              `json:"can_use_delayed_payment_methods,omitempty"`
	IsOnboardingCompleted       bool              `json:"is_onboarding_completed,omitempty"`
	FirstName                   string            `json:"first_name,omitempty"`
	CreatedAt                   int64             `json:"created_at,omitempty"`
	SeatType                    string            `json:"seat_type,omitempty"`
	IsAPIKeyHashed              bool              `json:"is_api_key_hashed,omitempty"`
	XIAPIKeyPreview             string            `json:"xi_api_key_preview,omitempty"`
	ShowComplianceTerms         bool              `json:"show_compliance_terms,omitempty"`
	AvailableModels             []string          `json:"available_models,omitempty"`
	NextInvoice                 *UserInvoice      `json:"next_invoice,omitempty"`
}

User contains account metadata returned by the ElevenLabs user endpoint.

type UserInvoice 

type UserInvoice struct {
	AmountDueCents         int64 `json:"amount_due_cents,omitempty"`
	NextPaymentAttemptUnix int64 `json:"next_payment_attempt_unix,omitempty"`
}

UserInvoice contains upcoming invoice metadata.

type UserSubscription 

type UserSubscription struct {
	Tier                                string       `json:"tier,omitempty"`
	CharacterCount                      int64        `json:"character_count,omitempty"`
	CharacterLimit                      int64        `json:"character_limit,omitempty"`
	CanExtendCharacterLimit             bool         `json:"can_extend_character_limit,omitempty"`
	AllowedToExtendCharacterLimit       bool         `json:"allowed_to_extend_character_limit,omitempty"`
	NextCharacterCountResetUnix         int64        `json:"next_character_count_reset_unix,omitempty"`
	VoiceLimit                          int64        `json:"voice_limit,omitempty"`
	MaxVoiceAddEdits                    int64        `json:"max_voice_add_edits,omitempty"`
	VoiceAddEditCounter                 int64        `json:"voice_add_edit_counter,omitempty"`
	ProfessionalVoiceLimit              int64        `json:"professional_voice_limit,omitempty"`
	CanExtendVoiceLimit                 bool         `json:"can_extend_voice_limit,omitempty"`
	CanUseInstantVoiceCloning           bool         `json:"can_use_instant_voice_cloning,omitempty"`
	CanUseProfessionalVoiceCloning      bool         `json:"can_use_professional_voice_cloning,omitempty"`
	Currency                            string       `json:"currency,omitempty"`
	Status                              string       `json:"status,omitempty"`
	BillingPeriod                       string       `json:"billing_period,omitempty"`
	CharacterRefreshPeriod              string       `json:"character_refresh_period,omitempty"`
	NextInvoice                         *UserInvoice `json:"next_invoice,omitempty"`
	HasOpenInvoices                     bool         `json:"has_open_invoices,omitempty"`
	CanUsePVCInstantly                  bool         `json:"can_use_pvc_instantly,omitempty"`
	CanUseVoiceDesign                   bool         `json:"can_use_voice_design,omitempty"`
	CanUseInstantVoiceCloningTrial      bool         `json:"can_use_instant_voice_cloning_trial,omitempty"`
	CanUseProfessionalVoiceCloningTrial bool         `json:"can_use_professional_voice_cloning_trial,omitempty"`
}

UserSubscription contains subscription and quota metadata for a user.

type ValidationError 

type ValidationError struct {
	Loc  []any  `json:"loc"`
	Msg  string `json:"msg"`
	Type string `json:"type"`
}

ValidationError contains validation details returned by the ElevenLabs API.

Source Files

View all Source files

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.