Grimes launches AI software allowing users to mimic her voice in songs

“We ask for 50% splits on master recording royalties in exchange for a grimes feat and distribution.”

Grimes

Image: Theo Wargo / Getty

When you purchase through affiliate links on MusicTech.com, you may contribute to our site through commissions. Learn more.

Artificial Intelligence advocate Grimes has released an AI software allowing users to mimic her voice in any song of their choosing.

The rollout comes just days after the Canadian artist told creators to “feel free to use my voice without penalty”.

Named Elf.Tech, the new software — currently in beta — supposedly allows fans to convert their decidedly non–Grimes voices to Grimes-sounding vocals simply by singing into the app.

“If you go to http://elf.tech u can upload ur voice singing or record directly into the app (click the “create” button to do this),” Grimes explained on Twitter. “It will output the same audio but with my voice.”

She added that users can “feel to take advantage” of the Grimes IP, and that the platform can collect master recording royalties for users if they choose to distribute their songs through Elf.Tech. There are even stems available on the site (more to be added over time) for artists who’d prefer to train their own Grimes model.

“we ask for 50% splits on master recording royalties in exchange for a grimes feat and distribution,” Grimes wrote. “There’s a *small* chance we can organize getting you publishing $ as well but we can’t guarantee this yet. But I hope we can!! Would be cool.”

And as much as the musician is open to fans using the “Grimes name and likeness”, she did also remind users to “please be tasteful”.

“Grimes is now open source and self replicating,” she declared.

Elsewhere, the 35-year-old also confirmed that she will be releasing “real Grimes music in the coming weeks and months”, adding that singles Music For Machines and I Wanna Be Software are “coming soon”.

AI-powered tracks have been the talk of the music town lately, with tech entrepreneur Roberto Nickson showing us recently how an impressively realistic Kanye West-sounding rap could be created with the help of Generative AI.

“All you have to do is record reference vocals and replace them with a trained model of any musician you like,” Nickson explained, adding that “this is the worst that AI will ever be. In just a few years, every popular musician will have multiple trained models of them.”

logo

Get the latest news, reviews and tutorials to your inbox.

Subscribe
Join Our Mailing List & Get Exclusive DealsSign Up Now
logo

The world’s leading media brand at the intersection of music and technology.

© 2024 MusicTech is part of NME Networks.