AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Gaming › Woosh
✦ Free & open sourceGaming

Woosh

Generates and decodes sound effects from text prompts or video sequences using open foundation models.

Text-to-audio and video-to-audio SFX generation

Sony AI's open foundation models for audio encoding, text-driven sound effects, and video-synced audio.

Free forever · open source · Apache-2.0
✓ Light setup✓ Browser-based✓ Real-time collaboration
6.9
ZEKAI
Powerful local SFX generator
Free & open source · Gaming
Ease of setup5
Usefulness8
Maintenance9.5
Community5
★ 388
GITHUB
Sep 2026
UPDATED
Apache-2.0
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

Woosh is a sound effect foundation toolkit built by Sony AI for text-to-audio and video-to-audio synthesis. It offers latent diffusion models alongside an audio encoder and decoder for sound designers and game developers. You can run inference scripts, launch local browser interfaces, or integrate generation into custom pipelines via an API server.

Runs on
Cross-platform
Hosting
Self-host
Languages
Python
License
Apache-2.0

What it is

The repository provides a suite of models including Woosh-AE for latent audio encoding, Woosh-CLAP for text conditioning, and latent diffusion models like Woosh-Flow and Woosh-VFlow. It synthesizes audio directly from descriptive text prompts or aligns generated audio to input video files. You manage and execute the tools through Python scripts using the uv environment manager.

Who it's for

It suits game developers, technical sound designers, and AI audio researchers looking to generate original audio assets locally. It is less suited for non-technical creators who require a finished digital audio workstation plugin or immediate commercial rights.

Key features

Text-to-Audio Generation

Synthesizes custom sound effects directly from text descriptions using standard and distilled diffusion models.

Video-to-Audio Synchronization

Creates audio tracks aligned with input video sequences using multimodal latent diffusion.

Audio Latent Encoding

Compresses raw audio into neural latents and reconstructs high-quality waveforms with Woosh-AE.

Local Gradio Demos

Provides web-based user interfaces to test text-to-sound generation in your local browser.

How to start

Up and running in 3 steps

1
Install uv and build your environment by running `uv sync --extra cuda` for GPU execution.
2
Download the release package from GitHub releases and extract checkpoints into the `checkpoints/` folder.
3
Launch the local web test tool by running `uv run gradio_Woosh-Flow.py` and navigating to localhost.
Real talk

Our honest verdict

What's great

  • Includes dedicated video-to-audio models for video frame sound synchronization
  • Offers distilled models like Woosh-DFlow for faster inference times
  • Provides built-in API server code to hook models into external game engines
  • Uses modern uv environment isolation for clean dependency management

Where it falls short

  • Model weights are licensed under CC-BY-NC, restricting commercial game releases
  • Requires local GPU hardware with CUDA support for practical generation speeds
  • Requires manual downloading and extraction of model weights from GitHub releases
  • Lacks a production digital audio workstation GUI or DAW plugin wrapper
Cost

Pricing & license

The source code is free and open under MIT and Apache-2.0 licenses. However, the pre-trained model weights use a non-commercial CC-BY-NC license. Running the project requires your own local GPU compute hardware.

Paid work

Open remote AI-training roles

896 open remote AI-training roles, updated November 16, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

🎁 Free & open-source alternatives

These reviewed AI tools do the same job instantly — from our scored directory.

Get more

Use it, or have us set it up

📄 Free PDF: Woosh for Gaming
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure Woosh for you — and train your team.
Get it done for you ↗
Questions

FAQ

Can I use generated sounds in a commercial game project?

The repository source code uses Apache-2.0 and MIT licenses, but the open model weights provided on GitHub releases are licensed under CC-BY-NC, restricting commercial usage without separate arrangements.

Does Woosh require an active internet connection to generate audio?

No. Once you install the dependencies and download the model checkpoints locally, all audio generation runs offline.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Gaming — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google