WorldSonus: Bringing Sound to Worlds

Pretrained weights for generating stereo audio from video and text.

For installation and usage, see NoizAI/WorldSonus.

Download

From the code repository, run:

python scripts/download_model.py --output assets
python scripts/download_encoders.py --output assets

python -m worldsonus.infer --video input.mp4 \
  --prompt "A train passes beside a river." --output output.wav

Add --stream for streaming generation, or omit --prompt for video-only input.

Released under CC BY-NC 4.0 for non-commercial use with attribution. Third-party components retain their own licenses; see Third-party notices.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support