All models
voice-cloning

F5-TTS

MIT

Flow-matching TTS, fast zero-shot voice cloning

F5-TTS uses flow matching with a diffusion transformer to produce fluent, faithful zero-shot voice clones from a single short reference. It became a community favorite for its simple architecture, fast inference, and surprisingly robust cloning quality.

Voices

1 voice
Female
Reference clonedefault
american

The scripts

Neutral
“The quick brown fox jumps over the lazy dog near the riverbank.”
Emotional
“I can't believe you actually did it. This is incredible!”
Numbers & Dates
“On March 14th, 2025, the team raised $4.2 million at a 38% margin.”

Install

pip install f5-tts

F5-TTS FAQ

Do I need a GPU to run F5-TTS?

For practical speeds, yes — plan on roughly 8 GB of VRAM. If you'd rather not manage a GPU, hosted access to every model in this directory is coming via OpenSpeech Cloud.

Can F5-TTS clone voices?

Yes — F5-TTS supports voice cloning from reference audio.

What license is F5-TTS released under?

F5-TTS is released under the MIT license. Always check the repository for the exact terms — some models license code and weights separately.

What languages does F5-TTS support?

F5-TTS supports English, Chinese.

Is there a hosted F5-TTS API?

Yes — OpenSpeech Cloud is launching hosted, pay-per-minute access to F5-TTS and every other model in this directory. No CUDA, Docker, or GPU needed.