The Fab Four will reunite for one last time.
The Beatles are back — well, sort of.
It seems impossible: The Fab Four famously broke up in 1969, then John Lennon died in 1980, followed by George Harrison in 2001. And yet we’re about to get never-heard-before music from the iconic band, thanks to the help of artificial intelligence.
In an interview with BBC Radio 4’s “Today,” the legendary Sir Paul McCartney explained that the technology was able to extract Lennon’s voice from an old demo to create a brand-new recording.
“We just finished it up, it’ll be released this year,” McCartney said in an interview released on Tuesday, adding that it’ll be “the last Beatles record.”
But hold on — how, exactly, can this happen? Well, here’s what we know about the upcoming track — and why McCartney still remains skeptical about the use of A.I. in music.
What do we know about the forthcoming Beatles song?
McCartney didn’t detail what The Beatles‘ final record would be, but there are some inklings about which songs it could potentially include. According to author Keith Badman, Lennon’s widow, Yoko Ono, reportedly gave McCartney several of the late singer’s home recordings, including the love song “Now and Then.”
It’s worth noting that there was a previous attempt to record this track with some of the surviving Beatles around 1995, but it was ultimately shelved because the band thought it needed to be reworked at the time. The sound quality was apparently another issue — the original recording had a persistent buzzing noise that affected its quality. George Harrison also wasn’t a fan, so the band voted to scrap it.
“It didn’t have a very good title, it needed a bit of reworking, but it had a beautiful verse and it had John singing it,” McCartney told Q Magazine. “[But] George didn’t like it. The Beatles being a democracy, we didn’t do it.”
There’s no official word on whether “Now and Then” is actually the song in question, but eagle-eyed fans say the track is the likeliest contender.
How was the new Beatles song created?
You’re probably imagining McCartney asking ChatGPT to sing Lennon’s verse, but that’s not exactly how it went down.
The reality was much more sophisticated: His team used a custom A.I.-powered system to restore Lennon’s vocals to a place where McCartney said it was possible to mix the track as if they were recorded for the first time.
“We were able to take John’s voice and get it pure through this A.I., so that then we could mix the record as you would normally do,” McCartney said. “So, it gives you some sort of leeway.”
McCartney said he first got the idea for using A.I. after seeing filmmaker Peter Jackson use it to resurrect archival materials for The Beatles: Get Back, a 2021 docuseries about the band making the 1970 album Let It Be. According to the singer-songwriter, Jackson was able to tell the machine to separate the vocals of various Beatles members from background noise to create a high-quality sound. “[Jackson] was able to extricate John’s voice from a ropey little bit of cassette which had John’s voice and a piano,” McCartney said.
But McCartney remains skeptical about A.I.-generated music: He told BBC that using the technology to create recordings that sound like originals from Lennon was “kind of scary, but exciting because it’s the future.” And this cautious optimism is well-placed — vocal A.I. deep-fakes have started to creep up, raising both legal and ethical questions. For instance, Universal Music Group pulled a computer-generated song by an anonymous TikTok user that was created (without permission) by using vocal replicas of pop sensations Drake and The Weeknd. (But not before the track racked up more than 20 million views on Twitter alone.)
According to McCartney, A.I.-generated music is “something we’re all sort of tackling at the moment and trying to deal with.”
