Skip to content

createVoiceMaker

createVoiceMaker(config?, opts?): Promise<VoiceMaker>

Defined in: packages/runntime/src/zoo/tasks/audio/textToSpeech.ts:308

Loads the voice encoder from config.codecPath, warms the GPU and returns the runner. Other fields are not used. With no config, loads Reverb’s codec from the Hugging Face Hub. The encoder runs in f32 on every device.

TextToSpeechModel = {}

LoadOptions = {}

Promise<VoiceMaker>