Coqui
Coqui is an open-source deep learning toolkit for text-to-speech synthesis, offering pretrained models, voice cloning, and tools for training custom TTS models.
About
Coqui TTS is a Python library built on PyTorch that gives developers and researchers a full toolkit for speech synthesis. It ships with more than 1,100 pretrained models across multiple languages and architectures, including Tacotron, VITS, and FastSpeech variants. Voice cloning, multi-speaker support, and multilingual output are all built in, and the library can produce real-time synthesis with very low latency. It is aimed at developers building speech-enabled applications and ML engineers who need to train custom models on proprietary data. Coqui TTS is free and open source under the Mozilla Public License 2.0.