FreeAIRepo
Voice & audio

hkchengrex/MMAudio

[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

MIT6 GB VRAMPython
Stars
2.3k
Forks
269
Open issues
9
Last push
8mo ago

About MMAudio

MMAudio is a free, open-source AI voice and audio tool by hkchengrex, written mainly in Python. [CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis. It has 2.3k GitHub stars and 269 forks, and was last updated 8mo ago. It's released under the MIT license, a standard open-source license. According to the project, it needs a GPU with at least 6 GB of memory.

License
MIT
Language
Python
Stars
2,291
Last update
8mo ago
Runs on Mac
Not stated
GPU
6 GB+ (as stated by the project)
Paid API key
Not stated
Self-hostable
Yes

Similar free tools

All Voice & audio tools →

MMAudio FAQ

Is MMAudio free?

Yes. MMAudio is open source and free to use. It's released under the MIT license, a standard open-source license.

Does MMAudio run on a Mac?

The project doesn't say. Check its installation guide before you start.

Does MMAudio need a GPU?

According to the project, MMAudio needs a GPU with at least 6 GB of memory.

Is MMAudio still maintained?

It was last updated 8mo ago. Check recent issues on GitHub to judge how active it is.

What are alternatives to MMAudio?

Similar free, open-source tools include transformers, mlx-audio, Amphion, pyvideotrans.

Related topics