types

Documentation

Index

• func NewSpeechRequestOptions(body io.ReadCloser) mo.Result[SpeechRequestOptions]
• func NewSpeechStreamStartOptions(payload []byte) mo.Result[SpeechRequestOptions]
• func NewVoicesRequestOptions(request *http.Request) mo.Result[VoicesRequestOptions]
• type ListVoicesResponse
• type OpenAISpeechRequestOptions
• type SpeechRequestOptions
  • func (o SpeechRequestOptions) AsBuffer() mo.Option[*bytes.Buffer]
  • func (o SpeechRequestOptions) AsMap() map[string]any
• type SpeechStreamClientEvent
• type SpeechStreamClientEventType
• type SpeechStreamServerEvent
• type SpeechStreamServerEventType
• type Voice
• type VoiceCommonLabels
• type VoiceFormat
• type VoiceLabelKey
• type VoiceLanguage
• type VoicesRequestOptions

Functions

func NewSpeechRequestOptions

func NewSpeechRequestOptions(body io.ReadCloser) mo.Result[SpeechRequestOptions]

func NewSpeechStreamStartOptions

func NewSpeechStreamStartOptions(payload []byte) mo.Result[SpeechRequestOptions]

NewSpeechStreamStartOptions parses the WS `start` frame. Unlike NewSpeechRequestOptions, `input` is optional because text flows through later `text` frames.

func NewVoicesRequestOptions

func NewVoicesRequestOptions(request *http.Request) mo.Result[VoicesRequestOptions]

Types

type ListVoicesResponse

type ListVoicesResponse struct {
	Voices []Voice `json:"voices"`
}

type OpenAISpeechRequestOptions

type OpenAISpeechRequestOptions struct {
	// (required) One of the available TTS models.
	Model string `json:"model"`
	// (required) The text to generate audio for.
	Input string `json:"input"`
	// (required) The voice to use when generating the audio.
	Voice string `json:"voice"`

	// The format to audio in.
	// Supported formats are mp3, opus, aac, flac, wav, and pcm.
	// mp3 is the default.
	ResponseFormat string `json:"response_format,omitempty"`
	// The speed of the generated audio.
	// Select a value from 0.25 to 4.0.
	// 1.0 is the default.
	Speed int `json:"speed,omitempty"`

	// Extension: allows you to add custom content to body.
	ExtraBody map[string]any `json:"extra_body,omitempty"`
}

OpenAISpeechRequestOptions represent API parameters refer to https://platform.openai.com/docs/api-reference/audio/createSpeech

type SpeechRequestOptions

type SpeechRequestOptions struct {
	OpenAISpeechRequestOptions

	Backend string `json:"backend"`
	Model   string `json:"model"`
	// contains filtered or unexported fields
}

func (SpeechRequestOptions) AsBuffer

func (o SpeechRequestOptions) AsBuffer() mo.Option[*bytes.Buffer]

func (SpeechRequestOptions) AsMap

func (o SpeechRequestOptions) AsMap() map[string]any

type SpeechStreamClientEvent

type SpeechStreamClientEvent struct {
	Event SpeechStreamClientEventType `json:"event"`
	Text  string                      `json:"text,omitempty"`
}

type SpeechStreamClientEventType

type SpeechStreamClientEventType string

SpeechStreamClientEventType is the discriminator for events the client sends to unspeech on a streaming TTS WebSocket (JSON text frames).

const (
	SpeechStreamClientEventStart  SpeechStreamClientEventType = "start"
	SpeechStreamClientEventText   SpeechStreamClientEventType = "text"
	SpeechStreamClientEventFinish SpeechStreamClientEventType = "finish"
	SpeechStreamClientEventCancel SpeechStreamClientEventType = "cancel"
)

type SpeechStreamServerEvent

type SpeechStreamServerEvent struct {
	Event   SpeechStreamServerEventType `json:"event"`
	Text    string                      `json:"text,omitempty"`
	Code    string                      `json:"code,omitempty"`
	Message string                      `json:"message,omitempty"`
	Payload map[string]any              `json:"payload,omitempty"`
}

type SpeechStreamServerEventType

type SpeechStreamServerEventType string

SpeechStreamServerEventType is the discriminator for events unspeech sends back to the client (JSON text frames). Audio bytes travel as binary frames and do not use this envelope.

const (
	SpeechStreamServerEventSessionStarted  SpeechStreamServerEventType = "session.started"
	SpeechStreamServerEventSentenceStart   SpeechStreamServerEventType = "sentence.start"
	SpeechStreamServerEventSentenceEnd     SpeechStreamServerEventType = "sentence.end"
	SpeechStreamServerEventSubtitle        SpeechStreamServerEventType = "subtitle"
	SpeechStreamServerEventSessionFinished SpeechStreamServerEventType = "session.finished"
	SpeechStreamServerEventError           SpeechStreamServerEventType = "error"
)

type Voice

type Voice struct {
	ID          string `json:"id"`
	Name        string `json:"name"`
	Description string `json:"description"`

	Labels map[string]any `json:"labels"`
	Tags   []string       `json:"tags"`

	Languages         []VoiceLanguage `json:"languages"`
	Formats           []VoiceFormat   `json:"formats"`
	CompatibleModels  []string        `json:"compatible_models"`
	PredefinedOptions map[string]any  `json:"predefined_options"`
	PreviewAudioURL   string          `json:"preview_audio_url"`
}

type VoiceCommonLabels

type VoiceCommonLabels struct {
	Gender       string `json:"gender"`
	Language     string `json:"language"`
	LanguageCode string `json:"language_code"`
	SampleRate   int    `json:"sample_rate"`
}

type VoiceFormat

type VoiceFormat struct {
	Name       string `json:"name"`
	Extension  string `json:"extension"`
	MimeType   string `json:"mime_type"`
	SampleRate int    `json:"sample_rate,omitempty"`
	Bitrate    int    `json:"bitrate,omitempty"`
	FormatCode string `json:"format_code,omitempty"` // For provider-specific format codes
}

type VoiceLabelKey

type VoiceLabelKey = string

const (
	VoiceLabelKeyAge    VoiceLabelKey = "age"
	VoiceLabelKeyGender VoiceLabelKey = "gender"
	VoiceLabelKeyAccent VoiceLabelKey = "accent"
	VoiceLabelKeyType   VoiceLabelKey = "type"
)

type VoiceLanguage

type VoiceLanguage struct {
	Title string `json:"title"`
	Code  string `json:"code"`
}

type VoicesRequestOptions

type VoicesRequestOptions struct {
	Backend string `json:"provider"`

	ExtraQuery url.Values `json:"extra_query"`
}