model
F5-TTS
F5‑TTS is a free, open‑source TTS system that turns written text into natural, expressive speech. The code can be installed via pip or Docker and runs on any machine with PyTorch (CPU or GPU). Pre‑trained models are available from the repository and can be used at no cost.
What it can help with
- text-to-speech
- voice cloning
- open weights
- local inference
- non-commercial licence