Model · Resemble AI · Text-To-Speech
Chatterbox
Resemble AI's MIT-licensed open text-to-speech family. Multilingual V3 (500M) clones a voice in 23 languages; Turbo (350M) and Nano (110M) are English-only models for fast voice agents, with [laugh]-style tags. Every output is watermarked.
- Modality
- Text-To-Speech
- License
- MIT (Open)
- Parameter size
- 500M (Multilingual V3); 350M (Turbo); 110M (Nano)
- Released
- June 10, 2026
- Last verified
- October 28, 2026
- Runs locally
- Yes
What you need to run it
- Mac
- Yes. Any Apple Silicon Mac (M1 or newer) with at least 8 GB (16 GB recommended) of memory. Newer chips are faster, but memory is what decides whether it runs.
- Windows / Linux PC
- NVIDIA works best. A graphics card with at least 4 GB (8 GB recommended) of video memory.
- No graphics card
- Works. Runs on a normal computer's processor, just slower.
The README shows Apple 'mps' as a device and MLX ports exist; only the small Nano model is meant to run on a plain CPU.
Numbers are for: Nano (110M) for the minimum, Multilingual V3 (500M) for the recommended. Our estimate from the model’s size — the maker publishes no figure.
Strengths
- MIT licence — free for commercial use
- Zero-shot voice cloning from a short reference clip
- Multilingual V3 covers 23 languages, with six dedicated single-language finetunes (e.g. Hindi, Brazilian Portuguese)
- Turbo and Nano accept paralinguistic tags such as [laugh], [cough] and [chuckle]
- Nano runs on a plain CPU — 3x faster than real time on 8 cores
Weaknesses
- Every generated file carries Resemble AI's PerTh watermark, which survives MP3 compression and editing — outputs can always be identified as Chatterbox audio
- Turbo and Nano are English-only
- The fastest path (sub-200 ms) Resemble advertises is its paid hosted service, not the open models
Try it
| Where | Type | Notes |
|---|---|---|
| Hugging Face | weights | MIT; Turbo and Nano in separate repos |
| GitHub (chatterbox-tts package) | local | pip install chatterbox-tts; CUDA, CPU or Apple MPS |
| Resemble AI | hosted-api | Paid hosted TTS from the same company |
Official sources
- Model card model
- GitHub github
- PerTh watermarker github
Change log
- — Added hardware requirements (Mac support, memory, NVIDIA). Source: GitHub README + mlx-community/Chatterbox-TTS-4bit + size.
- — Initial entry. Added 2026-10-28 from the popularity sweep: 27.4k GitHub stars, 1.98M Hugging Face downloads/month. Released date is the Multilingual V3 release (GitHub commit 'v3 multilingual and single language pack release', 2026-06-10). Turbo arrived 2025-12-15; Nano code landed 2026-07-21 (its Hugging Face repo dates from 2026-04-14). The README itself gives no dates.
Esc