May 2, 2024

La Ronge Northerner

Complete Canadian News World

YouTube teases an AI tool that clones famous singers – with their permission

YouTube teases an AI tool that clones famous singers – with their permission

Google is testing New general AI features for YouTube This will allow people to create music tracks using just a text message or a simple hum tone. The first, Dream Track, which has already been created for a few creators on the platform, is designed to automatically create short, 30-second music tracks in the style of popular artists. The feature can be imitated Nine different artists, who chose to collaborate with YouTube in its development. YouTube is also showing off new tools that can create music tracks through humming.

YouTube says its Dream Track feature is currently being tested with “a small group of select creators in the US,” and can produce tracks in the style of nine artists; Alec Benjamin, Charlie Puth, Charli XCX, Demi Lovato, John Legend, Papoose, Sia, T-Pain, and Troye Sivan. In a pair of video demonstrations, we show how the claim “A song about how opposites attract, upbeat acoustic“You can create a track in the style of Charlie Puth, or”Sunny Morning in Florida, R&B“It can be used to create a T-Pain song. The software can generate lyrics, a backing track and an AI-generated vocal in the artist’s style.

The idea is to use these audio clips with TikTok’s service similar to YouTube’s Shorts service. This is also where YouTube announced a new AI feature called Dream Screen in September, which can create videos and photos to use as wallpapers.

Example of a UI for YouTube’s Music AI tools.
Image: Google

YouTube says participants in the Music AI incubator will be able to test these tools later this year.

See also  Negotiations between Hollywood studios and the actors' union have been suspended

These new AI tools are powered by a music generation model called Lyria from Google’s DeepMind. in Companion blog post from DeepMindThe Google subsidiary says tracks created with Lyria will carry a SynthID watermark that is inaudible to the naked ear and can be preserved when the track is edited. So, even if someone adds more noise to the track, compresses it into an MP3, or speeds it up, it should still theoretically be possible to tell that it contains Lyria’s AI-generated audio.