cinemasetfree.com
← Back to all generators
resemble-ai/chatterbox
Official
View on Replicate →
Generate expressive, natural speech. Features unique emotion control, instant voice cloning from short audio, and built-in watermarking.
Capabilities
Seed
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
prompt * | string | Text to synthesize | — | — |
audio_prompt | string (uri) | Path to the reference audio file (Optional) | — | — |
cfg_weight | number | CFG/Pace weight | 0.5 | min: 0.2, max: 1 |
exaggeration | number | Exaggeration (Neutral = 0.5, extreme values can be unstable) | 0.5 | min: 0.25, max: 2 |
seed | integer | Seed (0 for random) | 0 | — |
temperature | number | Temperature | 0.8 | min: 0.05, max: 5 |
prompt required string Text to synthesize
audio_prompt string Path to the reference audio file (Optional)
cfg_weight number CFG/Pace weight
Default:
0.5 min: 0.2, max: 1 exaggeration number Exaggeration (Neutral = 0.5, extreme values can be unstable)
Default:
0.5 min: 0.25, max: 2 seed integer Seed (0 for random)
Default:
0 temperature number Temperature
Default:
0.8 min: 0.05, max: 5 Version:
1b8422bc4963 Updated: 2/26/2026 228.2K runs