F5-TTS
Open-source voice-cloning TTS that copies a voice from a few seconds of audio.
About F5-TTS
F5-TTS is a text-to-speech model from researchers at SJTU X-LANCE that clones a voice from a short reference clip plus its transcript (leave the transcript empty and it runs speech recognition for you). It uses flow matching on a Diffusion Transformer backbone. The released base model was trained on Chinese and English data from the Emilia dataset. Install with pip install f5-tts; it also ships a Gradio web UI, Docker images and finetuning scripts. The code is MIT, but the pretrained weights are CC-BY-NC, so commercial use of the stock checkpoints is not allowed.
Key Features
💰 Pricing
Free. Code MIT; pretrained weights CC-BY-NC (non-commercial).
Frequently Asked Questions
Is F5-TTS free?
What is F5-TTS used for?
What platforms does F5-TTS work on?
What are the best alternatives to F5-TTS?
Reviews
Loading reviews...
Questions & Answers
Questions submitted will appear here soon
Join the community to share knowledge about F5-TTS
📊 Comparison vs Alternatives
| Feature | ||||
|---|---|---|---|---|
| Pricing | Free | Free | Freemium | Paid |
| Rating | — | ⭐ 4.4 | ⭐ 4.5 | ⭐ 5.0 |
| Free Tier | ✅ | ✅ | ✅ | ❌ |
| Popularity | 45% | 82% | 80% | 80% |
Are you the creator of F5-TTS?
Claim this listing to get a verified badge, edit tool details, and respond to reviews. You’ll sign in and confirm a work email so we can verify ownership.
Claim this listingQuick Stats
Categories
F5-TTS Alternatives
The Weekly AI Tools & Skills Digest
Launching soon: trending agent skills, new tools, and what's actually worth trying. Sign up to get the first issue.
Free forever. Unsubscribe anytime.