🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

An advanced singing voice synthesis system with high fidelity, expressiveness, controllability and flexibility based on DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism

Massively multilingual pronunciation mining

🐸 - A general purpose model trainer, as flexible as it gets

pytorch implementation of DNN-HSMM for TTS

Python script to convert NNSVS DBs to Diffsinger without the NNSVS Python Library

g2p ID: Indonesian Grapheme-to-Phoneme Converter

Gui for users who use the coqui-TTS vits model.