Class TTS<TModel>

constructor

• new TTS<TModel>(opts): inference.TTS<TModel>

• Type Parameters

  • TModel extends inference.TTSModels

  Parameters

  • opts: {
        apiKey?: string;
        apiSecret?: string;
        baseURL?: string;
        connOptions?: APIConnectOptions;
        encoding?: "pcm_s16le";
        fallback?: TTSFallbackModelType | TTSFallbackModelType[];
        language?: string;
        model: TModel;
        modelOptions?: inference.TTSOptions<TModel>;
        sampleRate?: number;
        voice?: string;
    }

    • Optional apiKey?: string

    • Optional apiSecret?: string

    • Optional baseURL?: string

    • Optional connOptions?: APIConnectOptions

    • Optional encoding?: "pcm_s16le"

    • Optional fallback?: TTSFallbackModelType | TTSFallbackModelType[]

    • Optional language?: string

    • model: TModel

    • Optional modelOptions?: inference.TTSOptions<TModel>

      Flat provider-specific inference options forwarded as the extra payload field.

    • Optional sampleRate?: number

    • Optional voice?: string

  Returns inference.TTS<TModel>

pool

label

• get label(): string

• Returns string

model

• get model(): string

• Get the model name/identifier for this TTS instance.

  Returns string

  The model name if available, "unknown" otherwise.

  Remarks

  Plugins should override this property to provide their model information.

provider

• get provider(): string

• Get the provider name for this TTS instance.

  Returns string

  The provider name if available, "unknown" otherwise.

  Remarks

  Plugins should override this property to provide their provider information.

close

• close(): Promise<void>

• Returns Promise<void>

closeWs

• closeWs(ws): Promise<void>

• Parameters

  • ws: WebSocket

  Returns Promise<void>

connectWs

• connectWs(timeout): Promise<WebSocket>

• Parameters

  • timeout: number

  Returns Promise<WebSocket>

prewarm

• prewarm(): void

• Returns void

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 configuration including connection options

    • Optional connOptions?: APIConnectOptions

  Returns inference.tts.SynthesizeStream<TModel>

synthesize

• synthesize(_): tts.ChunkedStream

• Receives text and returns synthesis in the form of a ChunkedStream

  Parameters

  • _: string

  Returns tts.ChunkedStream

updateOptions

• updateOptions(opts): void

• Parameters

  • opts: Partial<Pick<InferenceTTSOptions<TModel>, "model" | "language" | "voice">>

  Returns void

Static fromModelString

• fromModelString(modelString): inference.TTS<AnyString>

• Parameters

  • modelString: string

  Returns inference.TTS<AnyString>