Nodes/comfyui-latent-astronaut-suite/ChatterBox TTS (Manual)
ComfyUI Node

ChatterBox TTS (Manual)

A ComfyUI node in audio/latent-astronaut with 10 inputs and 1 output.

By latentastronaut·Created 7 months ago·Updated 7 months ago· 2
ChatterBox TTS (Manual)
  • model
  • voice_audio
  • audio
textHello, this is a test of voice cloning.
exaggeration0.50
cfg_weight0.50
temperature0.80
top_p1.00
min_p0.05
repetition_penalty1.20
seed0
Categoryaudio/latent-astronaut

Inputs (10)

NameTypeDefaultDescription
modelCHATTERBOX_TTSChatterBox TTS model from loader
textSTRINGHello, this is a test of voice cloning.Text to synthesize into speech
voice_audioAUDIOReference audio for voice cloning (6-10 seconds ideal)
exaggerationFLOAT0.500–1Emotion/expression intensity (0=neutral, 1=exaggerated)
cfg_weightFLOAT0.500–1Classifier-free guidance weight (higher=more adherence to text)
temperatureFLOAT0.800.1–1.5Sampling temperature (higher=more varied/random)
top_pFLOAT1.000–1Nucleus sampling threshold
min_pFLOAT0.050–1Minimum probability threshold for sampling
repetition_penaltyFLOAT1.201–2Penalty for repeating tokens (1.0=no penalty)
seedINT00–18446744073709550000Random seed (0=random)

Outputs (1)

NameTypeDescription
audioAUDIO