Coqui TTS
Open-source deep learning toolkit for text-to-speech with over 1,100 pretrained models, voice cloning, and multi-language support.
About
Coqui TTS is a free, open-source text-to-speech toolkit built for both research and production use. It provides over 1,100 pretrained models spanning dozens of languages, as well as tools for training new models and fine-tuning existing ones.
The library supports voice cloning and voice conversion, and can be accessed through a Python API, command-line interface, or Docker container. It implements modern neural architectures including Tacotron2, VITS, and XTTS, with HiFiGAN vocoders for high-quality output. It suits researchers, developers, and teams who want full control over their TTS pipeline without licensing costs.
The library supports voice cloning and voice conversion, and can be accessed through a Python API, command-line interface, or Docker container. It implements modern neural architectures including Tacotron2, VITS, and XTTS, with HiFiGAN vocoders for high-quality output. It suits researchers, developers, and teams who want full control over their TTS pipeline without licensing costs.