Adobe's MultiFoley turns cat meows into lion roars
Adobe Research just unveiled MultiFoley, a video-aware audio generation method with multimodal controls. It lets creators transform sounds—such as making a typewriter sound like a piano or turning a cat's meow into a lion's roar—while automatically syncing effects to video timing. Why it matters: Foley sound design is notoriously tedious, and this could automate frame-accurate audio alignment.
Adding sound effects to a video is easily one of the most tedious parts of post-production. You have to hunt down the right sample, drag it onto the timeline, and nudge it frame by frame to match the visual action.
Adobe Research is tackling this bottleneck with MultiFoley, a new video-aware audio generation method packed with multimodal controls.
Making cats roar like lions
Basically, the tool watches what is happening in the video and gives creators granular control over how those visuals translate into sound.
In demonstrations shared from the research, MultiFoley can execute creative swaps like turning mechanical typewriter clicks into piano melodies, or making a small house cat unleash a full lion's roar.
On the practical side, it can also take existing sound effects from your library and automatically time them perfectly to the on-screen action.
Why it matters
Foley work has always been a massive time sink for editors. Right now, MultiFoley is strictly an Adobe Research project, meaning you cannot drop it into your editing workflow today.
However, we think Adobe's approach here is clever. Instead of generating a generic, uncontrollable background track from a prompt, MultiFoley focuses on precise frame-level timing and flexible sound replacement. If this technology eventually ships inside Premiere Pro, it could eliminate hours of manual audio scrubbing for video creators.
Sources (1)
- @icreatelife(opens in a new tab)Originaltwitter.com