Class TTS<TModel>

Livekit Cloud Inference TTS

Type Parameters

TModel extends inference.TTSModels

Hierarchy (view full)

tts.TTS
- TTS

Index

Constructors

Accessors

capabilities label numChannels sampleRate

Methods

close closeWs connectWs stream synthesize updateOptions fromModelString

Constructors

constructor

new TTS<TModel>(opts): inference.TTS<TModel>
Type Parameters
- TModel extends inference.TTSModels
Parameters
- opts: {
      apiKey?: string;
      apiSecret?: string;
      baseURL?: string;
      encoding?: "pcm_s16le";
      language?: string;
      model: TModel;
      modelOptions?: inference.TTSOptions<TModel>;
      sampleRate?: number;
      voice?: string;
  }
  - Optional apiKey?: string
  - Optional apiSecret?: string
  - Optional baseURL?: string
  - Optional encoding?: "pcm_s16le"
  - Optional language?: string
  - model: TModel
  - Optional modelOptions?: inference.TTSOptions<TModel>
  - Optional sampleRate?: number
  - Optional voice?: string
Returns inference.TTS<TModel>
Overrides TTS.constructor
- Defined in inference/tts.ts:104

Accessors

capabilities

get capabilities(): TTSCapabilities
Returns this TTS's capabilities

Returns TTSCapabilities
Inherited from BaseTTS.capabilities
- Defined in tts/tts.ts:74

label

get label(): string
Returns string
Overrides BaseTTS.label
- Defined in inference/tts.ts:173

numChannels

get numChannels(): number
Returns the channel count of audio frames returned by this TTS

Returns number
Inherited from BaseTTS.numChannels
- Defined in tts/tts.ts:84

sampleRate

get sampleRate(): number
Returns the sample rate of audio frames returned by this TTS

Returns number
Inherited from BaseTTS.sampleRate
- Defined in tts/tts.ts:79

Methods

close

close(): Promise<void>
Returns Promise<void>
- Defined in inference/tts.ts:233

closeWs

closeWs(ws): Promise<void>
Parameters
- ws: WebSocket
Returns Promise<void>
- Defined in inference/tts.ts:229

connectWs

connectWs(timeout): Promise<WebSocket>
Parameters
- timeout: number
Returns Promise<WebSocket>
- Defined in inference/tts.ts:203

stream

stream(options?): inference.tts.SynthesizeStream<TModel>
Returns a SynthesizeStream that can be used to push text and receive audio data
Parameters
- Optional options: {
  connOptions?: APIConnectOptions;
  }
  - Optional connOptions?: APIConnectOptions
Returns inference.tts.SynthesizeStream<TModel>
Overrides TTS.stream
- Defined in inference/tts.ts:196

synthesize

synthesize(_): tts.ChunkedStream
Receives text and returns synthesis in the form of a ChunkedStream
Parameters
- _: string
Returns tts.ChunkedStream
Overrides TTS.synthesize
- Defined in inference/tts.ts:192

updateOptions

updateOptions(opts): void
Parameters
- opts: Partial<Pick<InferenceTTSOptions<TModel>, "language" | "model" | "voice">>
Returns void
- Defined in inference/tts.ts:185

`Static` fromModelString

fromModelString(modelString): inference.TTS<AnyString>
Parameters
- modelString: string
Returns inference.TTS<AnyString>
- Defined in inference/tts.ts:177