{"id":71111,"date":"2026-02-14T11:47:47","date_gmt":"2026-02-14T11:47:47","guid":{"rendered":"https:\/\/youzum.net\/als-stole-this-musicians-voice-ai-let-him-sing-again\/"},"modified":"2026-02-14T11:47:47","modified_gmt":"2026-02-14T11:47:47","slug":"als-stole-this-musicians-voice-ai-let-him-sing-again","status":"publish","type":"post","link":"https:\/\/youzum.net\/th\/als-stole-this-musicians-voice-ai-let-him-sing-again\/","title":{"rendered":"ALS stole this musician\u2019s voice. AI let him sing again."},"content":{"rendered":"

There are tears in the audience as Patrick Darling\u2019s song begins to play. It\u2019s a heartfelt song written for his great-grandfather, whom he never got the chance to meet. But this performance is emotional for another reason: It\u2019s Darling\u2019s first time on stage with his bandmates since he lost the ability to sing two years ago.<\/p>\n

The 32-year-old musician was diagnosed with amyotrophic lateral sclerosis (ALS) when he was 29 years old. Like other types of motor neuron disease (MND), it affects nerves that supply the body\u2019s muscles. People with ALS eventually lose the ability to control their muscles, including those that allow them to move, speak, and breathe.<\/p>\n

Darling\u2019s last stage performance was over two years ago. By that point, he had already lost the ability to stand and play his instruments and was struggling to sing or speak. But recently, he was able to re-create his lost voice using an AI tool trained on snippets of old audio recordings. Another AI tool has enabled him to use this \u201cvoice clone\u201d to compose new songs. Darling is able to make music again.<\/p>\n

\u201cSadly, I have lost the ability to sing and play my instruments,\u201d Darling said on stage at the event, which took place in London on Wednesday, using his voice clone. \u201cDespite this, most of my time these days is spent still continuing to compose and produce my music. Doing so feels more important than ever to me now.\u201d<\/p>\n

Losing a voice<\/h3>\n

Darling says he\u2019s been a musician and a composer since he was around 14 years old. \u201cI learned to play bass guitar, acoustic guitar, piano, melodica, mandolin, and tenor banjo,\u201d he said at the event. \u201cMy biggest love, though, was singing.\u201d<\/p>\n

He met bandmate Nick Cocking over 10 years ago, while he was still a university student, says Cocking. Darling joined Cocking\u2019s Irish folk outfit, the Ceili House Band<\/a>, shortly afterwards, and their first gig together was in April 2014. Darling, who joined the band as a singer and guitarist, \u201celevated the musicianship of the band,\u201d says Cocking.<\/p>\n

\n
\"The
Patrick Darling (second from left) with his former bandmates, including Nick Cocking (far right).<\/figcaption>
COURTESY OF NICK COCKING<\/div>\n<\/figure>\n<\/div>\n

But a few years ago, Cocking and his other bandmates started noticing changes in Darling. He became clumsy, says Cocking. He recalls one night when the band had to walk across the city of Cardiff in the rain: \u201cHe just kept slipping and falling, tripping on paving slabs and things like that.\u201d\u00a0<\/p>\n

He didn\u2019t think too much of it at the time, but Darling\u2019s symptoms continued to worsen. The disease affected his legs first, and in August 2023, he started needing to sit during performances. Then he started to lose the use of his hands. \u201cEventually he couldn\u2019t play the guitar or the banjo anymore,\u201d says Cocking.<\/p>\n

By April 2024, Darling was struggling to talk and breathe at the same time, says Cocking. For that performance, the band carried Darling on stage. \u201cHe called me the day after and said he couldn\u2019t do it anymore,\u201d Cocking says, his voice breaking. \u201cBy June 2024, it was done.\u201d It was the last time the band played together.<\/p>\n

Re-creating a voice<\/h3>\n

Darling was put in touch with a speech therapist, who raised the possibility of \u201cbanking\u201d his voice. People who are losing the ability to speak can opt to record themselves speaking and use those recordings to create speech sounds that can then be activated with typed text, whether by hand or perhaps using a device controlled by eye movements.<\/p>\n

Some users have found these tools to be robotic sounding. But Darling had another issue. \u201cBy that stage, my voice had already changed,\u201d he said at the event. \u201cIt felt like we were saving the wrong voice.\u201d<\/p>\n

Then another speech therapist introduced him to a different technology. Richard Cave is a speech and language therapist and a researcher at University College London. He is also a consultant for ElevenLabs, an AI company that develops agents and audio, speech, video, and music tools. One of these tools can create \u201cvoice clones\u201d\u2014realistic mimics of real voices that can be generated from minutes, or even seconds, of a person\u2019s recorded voice.<\/p>\n

Last year, ElevenLabs launched an impact program<\/a> with a promise to provide free licenses to these tools for people who have lost their voices to ALS or other diseases<\/a>, like head and neck cancer or stroke.\u00a0<\/p>\n

The tool is already helping some of those users. \u201cWe\u2019re not really improving how quickly they\u2019re able to communicate, or all of the difficulties that individuals with MND are going through physically, with eating and breathing,\u201d says Gabi Leibowitz, a speech therapist who leads the program. \u201cBut what we are doing is giving them a way \u2026 to create again, to thrive.\u201d Users are able to stay in their jobs longer and \u201ccontinue to do the things that make them feel like human beings,\u201d she says.<\/p>\n

Cave worked with Darling to use the tool to re-create his lost speaking voice from older recordings.<\/p>\n

\u201cThe first time I heard the voice, I thought it was amazing,\u201d Darling said at the event, using the voice clone. \u201cIt sounded exactly like I had before, and you literally wouldn\u2019t be able to tell the difference,\u201d he said. \u201cI will not say what the first word I made my new voice say, but I can tell you that it began with \u2018f\u2019 and ended in \u2018k.\u2019\u201d<\/p>\n

\n
\"Patrick\n
COURTESY OF PATRICK DARLING<\/div>\n<\/figure>\n<\/div>\n

Re-creating his singing voice wasn\u2019t as easy. The tool typically requires around 10 minutes of clear audio to generate a clone. \u201cI had no high-quality recordings of myself singing,\u201d Darling said. \u201cWe had to use audio from videos on people\u2019s phones, shot in noisy pubs, and a couple of recordings of me singing in my kitchen.\u201d Still, those snippets were enough to create a \u201csynthetic version of [Darling\u2019s] singing voice,\u201d says Cave.<\/p>\n

In the recordings, Darling sounded a little raspy and \u201cwas a bit off\u201d on some of the notes, says Cave. The voice clone has the same qualities. It doesn\u2019t sound perfect, Cave says\u2014it sounds human.<\/p>\n

\u201cThe ElevenLabs voice that we\u2019ve created is wonderful,\u201d Darling said at the event. \u201cIt definitely sounds like me\u2014[it] just kind of feels like a different version of me.\u201d<\/p>\n

ElevenLabs has also developed an AI music generator called Eleven Music<\/a>. The tool allows users to compose tracks, using text prompts to choose the musical style. Several well-known artists have also partnered with the company to license AI clones of their voices, including the actor Michael Caine, whose voice clone is being used to narrate an upcoming ElevenLabs documentary. Last month, the company released an album of 11 tracks<\/a> created using the tool. \u201cThe Liza Minnelli track<\/a> is really a banger,\u201d says Cave.<\/p>\n

Eleven Music can generate a song in a minute, but Darling and Cave spent around six weeks fine-tuning Darling\u2019s song. Using text prompts, any user can \u201ccreate music and add lyrics in any style [they like],\u201d says Cave. Darling likes Irish folk, but Cave has also worked with a man in Colombia who is creating Colombian folk music. (The ElevenLabs tool is currently available in 74 languages<\/a>.)<\/p>\n

Back on stage<\/strong><\/h3>\n

Last month, Cocking got a call from Cave, who sent him Darling\u2019s completed track. \u201cI heard the first two or three words he sang, and I had to turn it off,\u201d he says. \u201cI was just in bits, in tears. It took me a good half a dozen times to make it to the end of the track.\u201d<\/p>\n

Darling and Cave were making plans to perform the track live at the ElevenLabs summit in London on Wednesday, February 11. So Cocking and bandmate Hari Ma each arranged accompanying parts to play on the mandolin and fiddle. They had a couple of weeks to rehearse before they joined Darling on stage, two years after their last performance together.<\/p>\n

\u201cI wheeled him out on stage, and neither of us could believe it was happening,\u201d says Cave. \u201cHe was thrilled.\u201d The song was played as Darling remained on stage, and Cocking and Ma played their instruments live.<\/p>\n

Cocking and Cave say Darling plans to continue to use the tools to make music. Cocking says he hopes to perform with Darling again but acknowledges that, given the nature of ALS, it is difficult to make long-term plans.<\/p>\n

\u201cIt\u2019s so bittersweet,\u201d says Cocking. \u201cBut getting up on stage and seeing Patrick there filled me with absolute joy. I know Patrick really enjoyed it as well. We\u2019ve been talking about it \u2026 He was really, really proud.\u201d<\/p>\n