Google tests new generative AI features for YouTube This will allow people to create music tracks using just a text prompt or a simple hummed melody. The first, Dream Track, already distributed by a few creators on the platform, is designed to automatically generate short 30-second pieces of music in the style of famous artists. The functionality can imitate nine different artists, which chose to collaborate with YouTube on its development. YouTube is also introducing new tools that can generate music tracks from a hum.
YouTube says its Dream Track feature is currently being tested with a “small group of select US creators” 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 two video demonstrations, we are shown how to prompt “A ballad about how opposites attract, with upbeat acoustics“can create a piece in the style of Charlie Puth, or”A Sunny Morning in Florida, R&B» can be used to create a T-Pain song. The software can generate lyrics, a backing track, and an AI-generated voice in the artist’s style.
The idea is for these tracks to be used with YouTube’s TikTok-style Shorts service. This is also where YouTube announced a new AI feature called Dream Screen in September, which can generate videos and photos to use as backgrounds.
YouTube says participants in its Music AI incubator will be able to test these tools later this year.
These new AI tools are powered by a music generation model called Lyria from Google’s DeepMind. In a DeepMind’s accompanying blog post, the Google subsidiary claims that tracks created using Lyria will carry a SynthID watermark that is inaudible to the naked ear and may be retained when a track is edited. So even if someone adds more noise to a track, compresses it into an MP3 file, or speeds it up, it should theoretically still be possible to tell that it contains AI-generated audio from Lyria.