All tasks / Models
Woosh v1.0.1 (Flow, DFlow, VFlow, DVFlow)
Sony AI's open-weights sound-effect models for text-to-audio and video-to-audio, with distilled 4-step variants.
- Sony AI
- Open weights
- Released 10 Sep 2026
Where it ranks
- –Sound effectsModels · Local · no result on this task’s benchmarks yet
Facts
- Vendor
- Sony AI
- Family
- Woosh
- Released
- 10 Sep 2026
- 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
Price from github.com, 19 Oct 2026.
Benchmark results
No public benchmark results recorded yet.
Where you can use it
- –ComfyUIWorkflow platforms · Local
Earlier versions
- Woosh v1.0.0 · 16 Mar 2026