# NVIDIA releases open multilingual RE-USE model for speech cleanup

> Original title: Sound on 🔊 Listen to the difference.

- Source: NVIDIA AI
- Published: 2026-10-30T20:15:04.000Z
- Bad Influence: https://badinfluence.news/items/vzx4x5s8cyxa889z5q33ep4j0
- Original: https://x.com/NVIDIAAI/status/2116262634349818190

## Summary

NVIDIA researchers release NemotronLabs RE-USE, an open multilingual model that removes background noise, echo and other audio distortions from speech. The model has 9.6M parameters, and a demo and download are available on Hugging Face.

## Post

Sound on 🔊 Listen to the difference.

Our new open multilingual NemotronLabs RE-USE model from NVIDIA researchers cleans up background noise, echo and other audio distortions to make speech clearer. All with just 9.6M parameters.

Try the demo and download the model on @huggingface → https://huggingface.co/nvidia/NVIDIA-NemotronLabs-RE-USE

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2116262434046726144%2Fimg%2Fs8UWjnqIUC1p8Zgy.jpg&mode=thumb&exp=1793577600&sig=b46457d0743b5204)