The creators of TikTok have been challenged by shorter shorts with music-making artificial intelligence
Dream Track and Lyria: Generative Artificial Intelligence for Imitating Popular Artists on YouTube – Results and Open Questions
People can create music tracks using just a text or hummed tune on the new generative artificial intelligence features that are being tested onYouTube. The first, Dream Track, already seeded to a few creators on the platform, is designed to auto-generate short 30-second music tracks in the style of famous artists. The feature can imitate nine different artists, who’ve chosen to collaborate with YouTube on its development. New tools that can generate music tracks from a hum are on display at YouTube.
These new AI tools are powered by a music generation model called Lyria from Google’s DeepMind. When a track is changed, it will carry a SynthID watermark that is inaudible to the naked ear, and can be preserved, according to a post from DeepMind. Even if someone adds a lot of noise to a song, it should be possible to know that it’s got an audio product from their friends at Lyria.
Just days before the new tools were revealed, the platform announced new guidelines for content creators meant to protect people and the music industry.
To make a 30-second Dream Track clip a creator just needs to enter a prompt, like “a ballad about how opposites attract, upbeat acoustic,” and then choose which artist the song should be styled on.