All tasks / Models
F5-TTS v1
Open-weights flow-matching text-to-speech model for zero-shot voice cloning, with non-commercial weights.
- SWivid (Shanghai Jiao Tong University)
- Open weights
Where it ranks
- –Text to speechModels · Local · no result on this task’s benchmarks yet
Facts
- Vendor
- SWivid (Shanghai Jiao Tong University)
- Family
- F5-TTS
- Released
- —
- Weights
- Open: download and run it yourself
- License
- CC-BY-NC-4.0 (weights); MIT (code)
- Access
- Free (open weights)
- Last verified
- 19 Oct 2026
Benchmark results
No public benchmark results recorded yet.
Where you can use it
No tracked tool lists this model yet; as open weights it runs in local runtimes.