Skip to content
Submit

MMAudio: auto-foley for silent AI clips

Generates synced sound effects from a silent video, ideal for Seedance clips.

Try it in 60 seconds

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118 --upgrade
git clone https://github.com/hkchengrex/MMAudio.git
pip install -e .

Install command copied from the project README. Check the README for the latest version.

What it does

Generates synced sound effects from a silent video, ideal for Seedance clips.

MMAudio Paper | Webpage | Models | Huggingface Demo | Colab Demo | Replicate Demo

Ho Kei Cheng, Masato Ishii, Akio Hayakawa, Takashi Shibuya, Alexander Schwing, Yuki Mitsufuji

Quoted from the README of hkchengrex/MMAudio.

Inside the repo

[Taming Multimodal Joint Training for High-QualityHighlightResultsInstallationPrerequisitesDemoCommand-line interfaceGradio interfaceFAQKnown limitationsTrainingEvaluation

Step by step

  1. Install per README.
  2. Feed your silent clip.
  3. Mux the audio back with ffmpeg.

Sources & credit

All credit to the original authors. We rewrite in our own words and link back. Something wrong? Report it.

Related

AGENT USE CASE1:21

Let sound design lead the scene

Building many scene variants with sound first, the creator says the result looks less like AI slop and renders fast.

Claude Code♥ 988
AGENT USE CASE1:30

Music video coded in Codex with Remotion + Suno

A complete music video built only with code (Remotion via Codex), with the song made in Suno.

Codex★ 64.3k
SKILL

AudioCraft: MusicGen + AudioGen SFX

Meta's open library for local music and sound-effect generation.

Claude Code +1★ 23.7k
SKILL

ACE-Step: free local music generation

Open-source music model for royalty-free beds you generate on your own machine.

Claude Code +1★ 4.9k
AGENT USE CASE

Make a track in Ableton Live by chatting

An MCP server lets the agent drive Ableton: drums, bass, melody and a rough mix from chat.

Codex★ 229
SKILL

ElevenLabs official agent skills

Lets your coding agent call ElevenLabs for voiceover, sound effects and music.

Claude Code +1★ 486

Coming soon

AgentsUses Weekly

A free weekly email with the best new skills and agent workflows is coming soon. Want a heads-up when the first issue goes out? Email [email protected] and we will let you know.

Get notified by email