{"ID":6537398,"CreatedAt":"2026-07-14T02:54:43.516908796Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.11738","arxiv_id":"2607.11738","title":"Qwen-Audio-VAE Technical Report","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2607.11738","url_pdf":"https://arxiv.org/pdf/2607.11738v1","authors":"[\"Ziyue Jiang\",\"Dake Guo\",\"Zekai Zhang\",\"Hangrui Hu\",\"Ting He\",\"Xinfa Zhu\",\"Xiong Wang\",\"Yongqi Wang\",\"Jiapeng Wang\",\"Wenxiang Guo\",\"Zhifang Guo\",\"Chenfei Wu\",\"Dayiheng Liu\",\"Jin Xu\"]","published":"2026-07-13T16:00:03Z","proceeding":"eess.AS","tasks":"[\"eess.AS\"]","methods":"[\"Transformer\",\"Variational Autoencoder\"]","has_code":false}