Audio ducking automatically lowers music whenever someone speaks and raises it again in the gaps. Doing it by hand across an hour of tape is the kind of task nobody should be doing. This release paired it with studio-quality sound processing.
In the new version of Descript we’re introducing Studio Sound, a powerful new feature that enhances speakers’ voices while reducing and removing background noise, room echo and other sound you don’t want.
Studio Sound is regenerative, meaning it isolates and enhances speaking voices, while reducing everything else. Most other noise reduction tools are subtractive, meaning they reduce your voice along with everything else, which often leaves you sounding tinny, or hollow. Think of Studio Sound as noise reduction that also elevates your speakers’ voices. Also, it has AI.
The bottom line is you can now achieve studio-quality sound whether you recorded in an actual studio or in your kitchen, on an expensive mic or on your iPhone. It’s another big step toward freeing you from the technical stuff so you can focus on making great content.
Studio Sound is in beta, but you can sign up for early access here.
Descript debuts ducking
The new version also includes ducking, which automatically lowers the volume on music and ambient sound track to ensure they stay in the background when they’re playing under speech tracks (audio engineers call this “ducking”). And when you want to add a musical interlude, you can just put a gap clip in the speaking track — Descript will automatically raise the music’s volume. It’s a feature we always planned to add, and now it’s here.
Get the latest Descript software
Make sure you’re using the latest version of Descript, or download the app to get started for free.
