---
license: mit
---
<div align="center">
<p align="center">
  <h1 style="white-space: pre-line;">
  AudioGAN: A Compact and Efficient Framework<br>
  for Real-Time High-Fidelity Text-to-Audio Generation
  </h1>

  [![Paper](https://img.shields.io/badge/Paper-arXiv-b31b1b?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2512.22166)
  [![Code](https://img.shields.io/badge/Code-Repo-black?style=flat&logo=github&logoColor=white)](https://github.com/SeaSky1027/AudioGAN)
  [![Hugging Face Space](https://img.shields.io/badge/Space-HuggingFace-blueviolet?logo=huggingface)](https://huggingface.co/spaces/SeaSky1027/AudioGAN)
  [![Webpage](https://img.shields.io/badge/Website-Visit-orange?logo=googlechrome&logoColor=white)](https://seasky1027.github.io/AudioGAN/)


</p>
</div>


## Overview 
AudioGAN is a novel GAN-based model tailored for compact and efficient text-to-audio generation.