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.

SoTA open-source TTS with multilingual support. Supports text chunking to allow more than 300 characters. Runs on RTX 5000 series GPUs. Has various audio effects built in such as Echo, Reverb, Pitch shift, 3d spatial audio, background music and noise removing capabilities.