Audio
GA
Open source
Chatterbox
Open-source expressive TTS and voice cloning
Release2025-05
Context—
Max output—
ParametersUndisclosed
Local / VRAM8–16 GB
LicenseOpen source
Overview
Chatterbox is a model in the Audio category from Resemble AI. It was released in 2025-05. The vendor is based in Canada. Best for: Open-source expressive TTS and voice cloning.
Notes: Positioning from the vendor site; specs, access and pricing can change — verify before production use.
Strengths
- Emotion control
- Runs locally
- Open weights
Limits
- Needs GPU
- Consent rules for cloning
Specifications
| Vendor | Resemble AI |
|---|---|
| Category | Audio |
| Release | 2025-05 |
| Status | GA |
| License | Open source |
| License name | MIT |
| Commercial use | Not specified |
| Input modalities | Text |
| Output modalities | Audio |
| Prompt types | Text |
| Negative prompts | No |
| Max outputs | 1 |
| Local deployment | Yes |
| VRAM | 8–16 GB |
| System RAM | 16–32 GB |
| API access | Yes |
| Pricing | Free (self-host) / enterprise API |
| Confidence | Medium |
| Vendor country | Canada |
| Vendor type | Media lab |
Pricing & hardware
Free (self-host) / enterprise API
This model can be self-hosted or run locally. Approximate GPU memory: 8–16 GB. Approximate system RAM: 16–32 GB. API access is available.