All tasks / Models
MMAudio (large_44k_v2)
Open-weights video-to-audio and text-to-audio model that generates sound effects synchronised to video clips.
- UIUC and Sony AI
- Open weights
- Released Dec 2024
Where it ranks
- –Sound effectsModels · Local · no result on this task’s benchmarks yet
Facts
- Vendor
- UIUC and Sony AI
- Family
- MMAudio
- Released
- Dec 2024
- Weights
- Open: download and run it yourself
- License
- CC-BY-NC-4.0 (weights)
- GPU memory to run locally
- ~6 GB (README: inference takes around 6 GB of GPU memory in 16-bit mode (default large_44k_v2 model).)
- Access
- Free (open weights)
- Last verified
- 18 Oct 2026
Price from huggingface.co, 18 Oct 2026.
Benchmark results
No public benchmark results recorded yet.
Where you can use it
- –ComfyUIWorkflow platforms · Local
- –WanGP (Wan2GP)Apps · Local