Matt Wolfe shows Meta's audio version of Segment Anything Model, which isolates or removes specific sounds like guitars or vocals. The free tool works on generated songs and podcast clips, and could help musicians and podcasters separate tracks without expensive software.
In Meta's playground — available to test for free (per the video).
Meta rolled out a version of their SAM or segment anything model for audio. You could give it an audio file and say, just isolate the speaking. Just isolate the guitar, things like that. And it is available to test for free right now over inside of Meta's playground. So this is a generated song. Here's a real quick clip of it.
Click the button, don't hesitate.
And we can see over here. I can just type what I want it to isolate. So let's isolate guitars. Let's hear what it sounds like. I can also listen to the version where it took the guitars out completely. So that's what this sounds like.
Click the button, don't hesitate. AI news at your front gate. Faster than a thought.
So we hear the drums kick in and the bass kick in and all the other instruments but the guitar is gone. They've got some other examples here, like these two people speaking on a podcast where they gave it a video. Here's what it sounds like by default.
We're here with Phoenix, our local sound editor. Thank you for everything that you do.
Let's have it. Just isolate male vocals. And here's what we get with that today.
We're here with Phoenix, our local sound editor. Thank you for everything that you do. So tell us a little bit more about the space and how that relates to film, what you've been learning.
Pretty cool thing, especially if you're like a podcaster or you make music.
AI News: Dots, GPT-6.1 Sol, Sonnet 5.5, Gemini 4, and everything you need to know
