Now in 5 languages!
An end-to-end (e2e) Voice Language Model by Fish Audio.
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
Fast, efficient, & multilingual text-to-speech
Efficient, fast, and natural text to speech with StyleTTS 2!
High-fidelity Text-To-Speech
Erase any object just by naming it!