Fine-tuning toolkit for Chatterbox TTS & Chatterbox TURBO models. Supports 23 languages with smart vocabulary extension. Features offline preprocessing, automatic VAD trimming, and voice cloning capabilities. Train custom TTS models with your own dataset in LJSpeech and file-based format.

Since most video dubbing services are paid, this project explores an experimental approach to building a free AI powered dubbing app.

A Next-Generation Neural TTS Engine. High-quality, human-like voice synthesis with low latency and multi-language support. Built for developers and creators.