YouTube launches AI tool that lets you CLONE pop stars’ voices – so, would this Charlie Puth track fool you?

YouTube has sidestepped the controversy surrounding the use of artificial intelligence (AI) to create new music with a new tool that reproduces singers’ voices.

The new feature, called Dream Track, is available in YouTube Shorts – the Google-owned platform’s answer to TikTok that allows users to post short videos.

Users can enter a prompt for what type of music style they want — such as “upbeat” or “ballad” — and choose the artist they want the AI ​​to imitate.

Nine artists have allowed their voices to be copied for the tool, including Alec Benjamin, Charlie Puth, Charli XCX, John Legend, Sia, and Troye Sivan.

YouTube has posted a short clip of what a clone of American singer Charlie Puth looks like, and it’s impressively close to the real thing.

The AI ​​singer also sings a new set of lyrics: “Baby, we don’t have anything in common, but I know I’m what you wanted.”

Dream Track is the creation of DeepMind, the London AI company founded in 2010 and bought by Google in 2014 for $500 million.

in Blog postYouTube employees said that artificial intelligence “brought music to the cusp of a new creative era” and that it could “boost creativity.”

“When technological innovation, human imagination and music come together, extraordinary things can happen,” they said.

“It’s still early days but we’re excited about the progress we’ve made in AI and music and energized by the possibilities that lie ahead.”

Dream Track is currently only being tested with “a small group of select creators in the US” and is not yet available to the general public.

MailOnline has contacted Google about when users in the UK will be able to try it out.

With Dream Track, users can create audio clips of up to 30 seconds for their short YouTube videos.

They first need to write an idea in the composition message – such as “a song about how opposites attract” which is “upbeat” and “sonic”.

They then have to choose one of the nine artists who agree to collaborate on this “experience” from the carousel.

“An original Shorts soundtrack will be produced that includes that artist’s AI-generated audio for the creator to use in their short film,” YouTube said.

It’s not clear how much Puth and the other artists were paid for the use of their images, but the New Jersey singer seemed excited about the possibilities of the technology.

“YouTube has been a great partner in defining their approach to AI and understands the need to work together to develop this technology responsibly, ensuring it will accelerate creativity rather than replace it,” he said.

Meanwhile, Florida rapper T-Pain said he has “always strived to push the boundaries of technology and harness it to make the most interesting music for his fans.”

AI tools, like OpenAI’s Dream Track and Jukebox, are fed an artist’s songs to “learn” their vocal styles and musical signatures, and are able to create entirely new approximations, with new lyrics and melodies.

Some musicians are excited about the possibility of offloading at least part of the songwriting process to the instrument.

Earlier this year, British pop icons the Pet Shop Boys argued that artificial intelligence could be used in a positive way in the creative process.

The group’s singer, Neil Tennant, said the AI ​​could “fill in the blanks” if a song is left unfinished, such as when a composer suffers from writer’s block.

However, others are more cautious because the technology can raise music copyright issues and undermine artistic integrity.

AI-generated music blurs the line between using a copyrighted song and using a cheaper or copyright-free approximation.

Canadian rapper Drake recently fell victim to artificial intelligence songs developed to sound like him, which his record label is trying to put a stop to.

“If someone doesn’t use the actual recording, you don’t have any legal action against them in terms of copyright in relation to the audio recording,” said Robert Skillett, head of legal at British record label Beggars Group.

However, not all forms of AI in the music industry are designed to digitally replicate artists’ voices in this way.

For example, Paul McCartney used an AI tool called MAL to isolate John Lennon’s voice from a 1970s home demo and make it “crystal clear.”

MAL – who can be trained to recognize and separate different instruments such as guitar, piano and vocals – allowed him and Ringo Starr to finish “The Beatles’ Last Song”, which reached the top of the singles chart last week.