Deep learning text-to-speech toolkit with multi-speaker support, voice cloning (XTTS, VITS, Tacotron2), and a built-in demo server.
About
Coqui TTS is a deep learning text-to-speech toolkit supporting multiple architectures including XTTS v2, VITS, Tacotron2, and GlowTTS. It offers multi-speaker synthesis, voice cloning from short audio samples, and supports 16+ languages.
