Adobe previews new AI-powered audio tool for voice processing and video creation

Adobe unveiled Project Sound Lift, an AI-powered technology capable of separating speech recordings into distinct tracks of voices, non-speech sounds and other background noise in a video.

Adobe unveiled Project Sound Lift, an AI-powered technology capable of separating speech recordings into distinct tracks of voices, non-speech sounds and other background noise in a video.

Developed by speech AI researchers at Adobe Research, Project Sound Lift is a one-click solution that helps users manipulate audio recordings across a range of scenarios, leveraging AI to independently enhance, transform, and control speech and sound independently, the company shared in a release.

Earlier audio AI models required clean, distinct input sounds – such as a single speaker or sound event without background noise or echoes, that limited audio AI’s application in everyday recordings.

Adobe’s Enhance Speech technology is integrated within Project Sound Lift to further transform the way creators produce and control studio-quality audio content.

(For top technology news of the day, subscribe to our tech newsletter Today’s Cache)

Adobe’s Project Sound Lift is available in Adobe applications like Premiere Pro.