Chatterbox TTS

Resemble AI's state-of-the-art zero-shot voice cloning model with independent emotion control.

Chatterbox by Resemble AI is a leading open-source zero-shot voice cloning model that replicates a voice from a single audio sample, capturing not just timbre but speaking style and emotional nuance. Its distinctive feature is fine-grained emotion control that operates independently of the voice identity, so you can keep a cloned voice but shift its emotional intensity. Built around ResembleEnhance and flow matching, it targets professional-grade cloning for content creation, dubbing, and character voices. Released under the permissive MIT license, Chatterbox has become a popular foundation for derivative models — TTS.ai also runs a Saudi-Arabic fine-tune of it. It favors quality, with a modest per-request character limit.