Lab · multilingual flagship

Chatterbox Multilingual: specs & requirements

The multilingual sibling of Chatterbox: the same 0.5-billion-parameter, MIT-licensed flagship quality, extended to 23 languages with zero-shot voice cloning. Like its English counterpart it needs WebGPU-class hardware and a large one-time download.

Lab tier — heavy/frontier model for enthusiast hardware

Chatterbox Multilingual support is being wired into the tool. Its specs and hardware verdicts are below — meanwhile, the live models are ready to use, and the compatibility check already tells you whether your device could run Chatterbox Multilingual.

Specifications

DeveloperResemble AI
Parameters500 million
Download size1600 MB (q4 mixed)
Output24.0 kHz mono
Voices1
LanguagesEnglish, Arabic, Chinese, Danish, Dutch, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Voice cloningYes
StreamingNo
LicenseMIT
SpeedNear real-time on a desktop WebGPU GPU; impractical on CPU.
RuntimeWebGPU required

Source: onnx-community/chatterbox-multilingual-ONNX

Strengths

  • +Flagship cloning quality across 23 languages
  • +Plain MIT license
  • +Official ONNX export in the transformers.js ecosystem

Limitations

  • −Requires WebGPU and ~8 GB RAM — desktop-class hardware
  • −~1.6 GB one-time download

Chatterbox Multilingual — questions

Is Chatterbox Multilingual free to use?

Yes. The weights are MIT and they run on your device.

What hardware does Chatterbox Multilingual need?

A WebGPU-capable browser and GPU (Chrome/Edge, Safari 26+, Firefox 141+) plus about 8 GB of RAM. It will not run on CPU at usable speed.

Is my text private when using Chatterbox Multilingual here?

Yes. The model executes inside your browser tab — the text you synthesize is never transmitted to a server.

Can I use Chatterbox Multilingual output commercially?

Review the current model, voice, and source-dataset terms before commercial use. The catalog lists MIT for this model.