MOVA: Towards Scalable and Synchronized Video-Audio Generation

SII-OpenMOSS Team, Donghua Yu, Mingshu Chen, Qi Chen, Qi Luo, Qianyi Wu, QinyuanCheng, Ruixiao Li, SII-liangtianyi, Wenbo Zhang, Wenming Tu, Xiangyu Peng, Yang Gao, Yanru Huo, Ying Zhu, Luo Yinze, Yiyang Zhang, Yuerong Song, Xu Zhe, ZHIYU ZHANG, Chenchen Yang, Cheng Chang, zhouchushu(SII), Hanfu Chen, Hongnan Ma, Jiaxi Li, tongjingqi(SII), junxiliu, Ke Chen, Shimin Li, Songlin Wang, Wei Jiang, Zhaoye Fei, Zhiyuan Ning, Chunguo Li, Chenhui Li, Ziwei He, Zengfeng Huang, Xie Chen, Xipeng Qiu

MOVA: Towards Scalable and Synchronized Video-Audio Generation: 159 upvotes on Hugging Face Daily Papers, #4 of 58 papers on 2026-02-10. Day-by-day upvote history.

Audio is indispensable for real-world video, yet generation models have largely overlooked audio components. Current approaches to producing audio-visual content often rely on cascaded pipelines, which increase cost, accumulate errors, and degrade overall quality. While systems such as Veo 3 and Sora 2 emphasize the value of simultaneous generation, joint multimodal modeling introduces unique challenges in architecture, data, and training. Moreover, the closed-source nature of existing systems limits progress in the field. In this work, we introduce MOVA (MOSS Video and Audio), an open-source model capable of generating high-quality, synchronized audio-visual content, including realistic lip-synced speech, environment-aware sound effects, and content-aligned music. MOVA employs a Mixture-of-Experts (MoE) architecture, with a total of 32B parameters, of which 18B are active during inference. It supports IT2VA (Image-Text to Video-Audio) generation task. By releasing the model weights and code, we aim to advance research and foster a vibrant community of creators. The released codebase features comprehensive support for efficient inference, LoRA fine-tuning, and prompt enhancement.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.