tts

Generate speech from text

Description

Generate speech from text

Usage

 1tts(
 2  model,
 3  text,
 4  voice,
 5  exaggeration = 0.5,
 6  cfg_weight = 0.5,
 7  temperature = 0.8,
 8  top_p = 0.9,
 9  autocast = NULL,
10  traced = FALSE
11)

Arguments

  • model: Chatterbox model
  • text: Text to synthesize
  • voice: Voice embedding from create_voice_embedding() or path to reference audio
  • exaggeration: Emotion/expression exaggeration level (0-1, default 0.5)
  • cfg_weight: Classifier-free guidance weight (higher = more adherence to text, default 0.5)
  • temperature: Sampling temperature (default 0.8)
  • top_p: Top-p (nucleus) sampling threshold (default 0.9)
  • autocast: Use mixed precision (float16) on CUDA for faster inference (default TRUE on CUDA)

Value

List with audio (numeric vector) and sample_rate