MMAudio
[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis
Generate audio that matches video or text inputs, creating synchronized soundtracks for your projects.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytime[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis
MMAudio has 2.2k stars on GitHub. It has been forked 261 times. MMAudio is written mainly in Python. It has been in active development since 2024. MMAudio is available under the MIT license. Its main topics are audio, audio-synthesis, computer-vision, deep-learning.
What is MMAudio?
[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis
Is MMAudio open source?
MMAudio is an open-source project. It is released under the MIT license.
Is MMAudio free?
Yes. MMAudio is free and open source — you can use, modify and self-host it.
What license does MMAudio use?
MMAudio is available under the MIT license.
What language is MMAudio written in?
MMAudio is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/hkchengrex-mmaudio.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.