Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.inworld.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Properties

​
Properties

​
speakerId

speakerId?: string
The voice ID to use for synthesis. See available voices for options.

​
languageCode

languageCode?: string
The language code for the synthesized speech (e.g., ‘en-US’, ‘es-ES’).

​
modelId

modelId?: string
The TTS model to use for synthesis. See available TTS models for options.

​
temperature

temperature?: number
Controls randomness in synthesis. Range (0, 2]. Higher values produce more expressive and creative output, while lower values are more deterministic. Default is typically 1.1.

​
speakingRate

speakingRate?: number
Speaking rate/speed multiplier. Range [0.5, 1.5]. 1.0 is the normal native speed. Values less than 1.0 slow down speech, values greater than 1.0 speed it up.

​
sampleRate

sampleRate?: number
Audio output sample rate in Hz (e.g., 22050, 44100, 48000). Determines the quality and file size of the generated audio.

​
ttsComponent

ttsComponent?: AbstractComponent | RemoteTTSComponent
An existing TTS component to reuse across multiple nodes. If provided, other configuration options (speakerId, modelId, etc.) are ignored in favor of the component’s configuration.