resemble-ai/chatterbox

Generate expressive, natural speech. Features unique emotion control, instant voice cloning from short audio, and built-in watermarking.

Input
Configure the inputs for the AI model.

Seed (0 for random)

Text to synthesize

0.2
1

CFG/Pace weight

0.05
5

Temperature

Path to the reference audio file (Optional)

0.25
2

Exaggeration (Neutral = 0.5, extreme values can be unstable)

Output
The generated output will appear here.

No output yet

Click "Generate" to create an output.