Explore more free AI tools in the same category:
Woosh is an open sound effects foundation model developed by Sony AI that helps researchers and developers generate high-quality audio using artificial intelligence.
They provide text-to-audio and video-to-audio generation, allowing users to create sound effects from written descriptions or video content.
Their standout feature is video-conditioned sound generation, which creates audio suited to visual scenes, such as engines, applause, aircraft, and physical actions.
They also include audio encoding and decoding models, text-audio alignment, and distilled models for faster inference, supporting research and audio development workflows.
Woosh offers public model weights and inference code through its GitHub repository.
Quick View
| Free Usage Policy | Project Demos |
| Paid Upgrade Option? | Yes |
| Tool Release Year | 2026 |
| Founded by | Sony AI |
| Employees | NA |
| Location | Japan | Social media presence |
| Popularity Index | 8.5 |
| Main Features | Text-to-audio sound effects generation, video-to-audio generation, open model weights and inference code, distilled models for faster low-resource inference |
| Best Used For | Generating sound effects for games, creating Foley for film scenes, adding audio to video footage, experimenting with sound-generation research |
WJ-AI
ComfyUI Workflow Blog
Benji’s AI PlaygroundProject Demos
| Credit Card Required? | |
| Phone Number Required? | |
| Paid Upgrade From | Custom Pricing |
