zsxkib / mmaudio

Add sound to video using the MMAudio V2 model. An advanced AI model that synthesizes high-quality audio from video content, enabling seamless video-to-audio transformation.

  • Public
  • 261.7K runs
  • GitHub
  • Weights
  • Paper
  • License
Run with an API
Playground API Examples README Versions
  1. Author
    @zsxkib
    Version
    v0.1-112-gf4f95ee
    Commit
    f4f95eea8ef7ec5fc981b32040b74df50be7d1d4

    62871fb5

    Latest
  2. Author
    @zsxkib
    Version
    v0.1-111-g081afc1
    Commit
    081afc1d26f406e29751ac2678666fcd93552a45

    0e759d66

    62871fb5 Latest

    This version has been automatically upgraded to a newer version.

  3. Author
    @zsxkib
    Version
    cuda11.8-python3.11-X64
    Commit
    dafe7eab89a6434e505d0460329aec029caab2f7

    4b9f801a

    62871fb5 Latest

    This version has been automatically upgraded to a newer version.

  4. Author
    @zsxkib
    Version
    cuda11.8-python3.11-X64
    Commit
    03013d2151270a01c15244182e98a64fdc3c31ae

    266543bf

    62871fb5 Latest

    This version has been automatically upgraded to a newer version.

  5. Author
    @zsxkib
    Version
    cuda11.8-python3.11-X64
    Commit
    03013d2151270a01c15244182e98a64fdc3c31ae

    5a83c7dd

    62871fb5 Latest

    This version has been automatically upgraded to a newer version.