Qwen-Audio-VAE Technical Report
摘要
We introduce \textbf{Qwen-Audio-VAE}, a suite of low-bitrate, fast-encoding continuous audio autoencoders designed for scalable general audio generation. The model is built around a simple but important principle: an audio VAE should not only reconstruct diverse audio with high fidelity, but also produce compact latent representations fast enough to support large-scale text-to-audio training. Qwen-Audio-VAE combines a causal encoder-decoder, window Transformer blocks, and multi-discriminator training to achieve a strong balance between reconstruction quality and compression rate. The model is trained at scale on 5 million hours of multi-domain audio, enabling robust reconstruction across heterogeneous acoustic conditions. To further improve computational efficiency, we adopt an asymmetric encoder-decoder backbone and introduce latency-aware encoder pruning to maximize encoding throughput. Experiments on public speech, music, and sound reconstruction benchmarks show that Qwen-Audio-VAE generalizes well across diverse audio domains and is particularly efficient, requiring only 541 ms to encode 32 minutes of audio. Overall, Qwen-Audio-VAE provides a high-quality, compact, and high-throughput representation backbone for efficient general audio generation.
引用
@article{arxiv.2607.11738,
title = {Qwen-Audio-VAE Technical Report},
author = {Ziyue Jiang and Dake Guo and Zekai Zhang and Hangrui Hu and Ting He and Xinfa Zhu and Xiong Wang and Yongqi Wang and Jiapeng Wang and Wenxiang Guo and Zhifang Guo and Chenfei Wu and Dayiheng Liu and Jin Xu},
journal= {arXiv preprint arXiv:2607.11738},
year = {2026}
}