Make your vocals sound like Grimes with her new AI-powered Elf.Tech project
Upload your vocal and the Grimesified version will be sent back to you, says the "self-replicating AI popstar"
Having previously pledged a 50/50 royalty split with anyone who released a track using an AI-generated version of her voice, Grimes (AKA "The Self-replicating AI Popstar for the Martian Ministry of Propaganda," according to her Twitter profile) is now giving you the tools you need to make it happen.
The producer’s new Elf.Tech project enables you to upload or record acapellas that will then be transformed into a ‘GrimesAI-1 voiceprint’ - a Grimesified version of your vocal, basically. You’ll receive your processed audio back as a WAV file and then be free to use it in your own music.
“This is all a beta test so it may be imperfect at first,” the star - whose real name is Claire Boucher - wrote on Twitter. “But! Let's try this out!”
HOW TO MAKE MUSIC FEAT GrimesAI - we can distribute it for you and you can earn royalties from your work: https://t.co/p598CXaXnDApril 30, 2023
Any new recordings made with the voiceprint will be yours. GrimesAI-1 doesn’t claim any ownership of either these or the “underlying composition” (unless you happen to be covering a Grimes song, that is).
There are some potential costs involved, though: if you want to distribute your song to a streaming service you’ll be required to pay $10 a year for the privilege. If you're planning on releasing a GrimesAI-1 recording on a label, via a distributor or on another platform, you’ll have to contact Grimes for approval.
As previously suggested, Grimes will split all royalties from streaming platforms 50/50 with any GrimesAI collaborators. These will be collected and paid out by Elf.Tech. For on-chain sales and royalties creators must agree to add the GrimesAI.eth wallet to the collection when minting.
Elf.Tech says that it wants the Grimes voice model to be “the best self-replicating pop star voice on the market,” and so is open-sourcing Grimes audio stems to music creators and AI voice model companies (these are available for download on its website).
Get the MusicRadar Newsletter
Want all the hottest music and gear news, reviews, deals, features and more, direct to your inbox? Sign up here.
The GrimesAI voice model is currently in beta - the developers say that it will frequently update this, the stems and the distribution service. You can find out more and get started on the Elf.Tech website (email sign-up required).
I’m the Deputy Editor of MusicRadar, having worked on the site since its launch in 2007. I previously spent eight years working on our sister magazine, Computer Music. I’ve been playing the piano, gigging in bands and failing to finish tracks at home for more than 30 years, 24 of which I’ve also spent writing about music and the ever-changing technology used to make it.
"Coated with analogue warmth, and many a chunky nugget for the keen and avid listener to find": Röyksopp get even more Mysterious with new surprise reworking
"We anticipate that the first 1000 will sell out very quickly": Here's how to get your hands on Orchid, Tame Impala's ultra-hyped chord-generating synthesizer