Chatterbox
Inspect the documented capabilities, access conditions and sources for your task.
Initial research: 2026-09-21. Check current terms before choosing.
Automated fact checks · 8 fields
AI extraction with a second evidence validation pass. These dates apply to the listed fields.
- Open weights · 2026-10-08 · Source
- Commercial use · 2026-10-08 · Source
- Commercial terms · 2026-10-08 · Source
- Commercial source · 2026-09-30 · Source
- Clone a voice · 2026-10-08 · Source
- Stream speech in real time · 2026-10-08 · Source
- Language coverage · 2026-09-30 · Source
- Control tone and emotion · 2026-10-08 · Source
Updated
The facts
- Version
- Turbo (350M), Original (500M), Multilingual (500M, v3)
- Price
- Price not verified. Open the tool record for the available pricing sources.
- API
✓Supported - Open weights
✓Supported - Commercial use
- MIT license; usable in personal, research, and commercial projects including closed-source products, subject to license terms on GitHub
- Voice Cloning
✓Supported Zero-shot voice cloning from ~5 seconds of reference audio; no fine-tuning or training run required
Source for Voice Cloning (opens in a new tab)- Realtime Streaming
✓Supported Up to 6× faster than real-time on a GPU with ~75ms latency; streaming-ready inference for voice assistants and real-time agents
Source for Realtime Streaming (opens in a new tab)- Languages
~Partly 23+ languages supported in the Multilingual variant
Source for Languages (opens in a new tab)- Emotion Control
✓Supported First open-source model with emotion exaggeration control; adjust intensity from monotone to dramatically expressive with a single parameter
Source for Emotion Control (opens in a new tab)
Commercial risk
No litigation found in fetched sources. MIT licensing means no vendor can revoke your right to use it, but it equally means no vendor indemnifies you and no consent gate exists on cloning — you own that policy yourself.
From the publisher
Automatic source checks. These do not change the verification date of the facts above.
Sources
Beyond feature support
Quality evidence.
How well a model performs depends on the task, version, and settings.
We have not published a reviewed quality evaluation for these versions yet. Feature support and price do not establish output quality.
Try the same small task with each option. Check accuracy, consistency, and how much editing you need to get a usable result.