MOVA: Towards Scalable and Synchronized Video-Audio Generation
Abstract
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.
Cite
@article{arxiv.2602.08794,
title = {MOVA: Towards Scalable and Synchronized Video-Audio Generation},
author = {OpenMOSS Team and Donghua Yu and Mingshu Chen and Qi Chen and Qi Luo and Qianyi Wu and Qinyuan Cheng and Ruixiao Li and Tianyi Liang and Wenbo Zhang and Wenming Tu and Xiangyu Peng and Yang Gao and Yanru Huo and Ying Zhu and Yinze Luo and Yiyang Zhang and Yuerong Song and Zhe Xu and Zhiyu Zhang and Chenchen Yang and Cheng Chang and Chushu Zhou and Hanfu Chen and Hongnan Ma and Jiaxi Li and Jingqi Tong and Junxi Liu and Ke Chen and Shimin Li and Shiqi Jiang and Songlin Wang and Wei Jiang and Zhaoye Fei and Zhiyuan Ning and Chunguo Li and Chenhui Li and Ziwei He and Zengfeng Huang and Xie Chen and Xipeng Qiu},
journal= {arXiv preprint arXiv:2602.08794},
year = {2026}
}
Comments
Technical report for MOVA (open-source video-audio generation model). 38 pages, 10 figures, 22 tables. Project page: https://mosi.cn/models/mova Code: https://github.com/OpenMOSS/MOVA Models: https://huggingface.co/collections/OpenMOSS-Team/mova. Qinyuan Cheng and Tianyi Liang are project leader. Xie Chen and Xipeng Qiu are corresponding authors