TOOLORA / Local reading edition
Chatterbox
A family for multilingual voice cloning and efficient English TTS, using reference audio, expression controls or non-verbal tags depending on the model.
Overview
Chatterbox is Resemble AI’s deployable TTS family. Multilingual V3 targets multilingual reference-voice generation; Turbo and Nano primarily target English with tags such as laughter or coughing, while Nano serves tighter resource budgets. Python interfaces generate audio from text and optional reference clips, with Perth watermarking. Languages, controls and hardware needs differ by model; multilingual coverage does not apply to every variant. The main project and official model card declare MIT.
- Company country / region
- United States · Company headquarters
Official sources and references
- Official websitehttps://github.com/resemble-ai/chatterbox
- Documentationhttps://huggingface.co/ResembleAI/chatterbox
Descriptions summarize public information; consult official websites for features, pricing and regional availability.