Grimes is beta testing her own AI voice mimicking software

Grimes has unveiled Elf.Tech, her own AI voice mimicking software that will allow users to record vocals in Grimes’ voice.

• READ MORE: Grimes – ‘Miss Anthropocene’ review: an iconoclast continues to march to the beat of her own drum 

The singer-producer announced Elf.Tech via her social media on April 30, confirming that it is currently in its beta testing phase. “If you go to elf.tech u can upload ur voice singing or record directly into the app (click the “create” button to do this). It will output the same audio but with my voice,” Grimes explained.

1 – this is all a beta test so it may be imperfect at first. But! Let's try this out! If you go to https://t.co/7OEKD2XbPd u can upload ur voice singing or record directly into the app (click the "create" button to do this). It will output the same audio but with my voice

— 𝔊𝔯𝔦𝔪𝔢𝔰 (@Grimezsz) April 30, 2023

In her Twitter thread, Grimes also said users can “feel free to take advantage” of the Grimes IP, and that the platform can collect master recording royalties for users if they distribute their songs through Elf.Tech.

“You can use Grimes name and likeness (I humbly ask that you please be tasteful tho). Grimes is now open source and self replicating,” she wrote on Twitter before adding that Elf.Tech will seek a 50 per cent split on master recording royalties “in exchange for a Grimes feat and distribution”.

Grimes also confirmed that she will be releasing “real Grimes music in the coming weeks and months”, adding that ‘Music For Machines’ and ‘I Wanna Be Software’ are “coming soon” though release dates are currently unknown.

6 – & I'll be releasing real Grimes music in the coming weeks and months too ofc ^_^ Music for Machines and I wanna be software coming soon !

And again plz excuse any hiccups or bugs – this is all new and we're workshopping it! Xo

— 𝔊𝔯𝔦𝔪𝔢𝔰 (@Grimezsz) April 30, 2023

Grimes first announced Elf.Tech last week (April 24), saying she and her team were working on “a program that should simulate my voice well”. The following day, Grimes revealed that Elf.Tech had been set up and they were figuring out how to register uses and import vocals.

She also outlined several conditions in which tracks might be taken down. “We may do copyright takedowns ONLY for rly rly toxic lyrics w grimes voice: imo you’d rly have to push it for me to wanna take smthn down but I guess plz don’t be *the worst*. as in, try not to exit the current Overton window of lyrical content w regards to sex/violence. Like no baby murder songs plz,” she wrote.

Ok hate this part but we may do copyright takedowns ONLY for rly rly toxic lyrics w grimes voice: imo you'd rly have to push it for me to wanna take smthn down but I guess plz don't be *the worst*. as in, try not to exit the current Overton window of lyrical content w regards to…

— 𝔊𝔯𝔦𝔪𝔢𝔰 (@Grimezsz) April 24, 2023

In late April, Grimes confirmed that she had parted ways with Columbia Records. She had only been on their roster since March 2021. She also spoke at the annual International Music Summit (IMS) in Ibiza on April 28, where she delivered the keynote speech moderated by BBC Radio 1 Dance DJ Jaguar. In her speech, she went into topics surrounding artificial intelligence, music rights management and technology.

“I feel strongly that there’s way too much gatekeeping in music,” said Grimes. “Copyright sucks. Art is a conversation with everyone that’s come before us. Intertwining it with the ego is a modern concept. The music industry has been defined by lawyers, and that strangles creativity.”

The post Grimes is beta testing her own AI voice mimicking software appeared first on NME.