AI lets country star Randy Travis sing again in first song released post-stroke
Written by WOM writer on May 8, 2024
“I think he went through every emotion there was, in those three minutes of just hearing his voice again.”
Thanks to artificial intelligence, country star Randy Travis is finally able to ‘sing’ again. The 65-year-old, who’s known for his hits like Forever and Ever, Amen and I Told You So, suffered a stroke in 2013 which left him largely unable to speak or sing.
Now, with the help of AI, Travis has released his first song in over a decade titled Where That Came From.
Backed by Warner Music, the project began with the creation of a proprietary AI model. The result was two models: One with 12 vocal stems, and another with 42 stems collected across Travis’s career, according to Kyle Lehning, Travis’s longtime producer.
Fellow country singer James Dupree was enlisted to lay down the demo vocals, which were then inputted into the AI model.
“I really wish somebody had been here with a camera because I was the first person to hear it. And it was stunning, to me, how good it was sort of right off the bat. It’s hard to put an equation around it, but it was probably 70, 75 per cent what you hear now,” says Lehning.
From there, areas that were deemed “not authentic” to Travis’s performance were edited with the help of recording engineer Casey Wood. Alterations were then made to things like vibrato speed, or slowing and relaxing phrases so as to capture Travis’s unique vocal quality as far as possible.
“Randy, I remember watching him when he first heard the song after it was completed. It was beautiful because at first, he was surprised, and then he was very pensive, and he was listening and studying,” said Travis’s wife Mary Travis.
“And then he put his head down and his eyes were a little watery. I think he went through every emotion there was, in those three minutes of just hearing his voice again.”
The team also hopes that the project can help educate the public on the tangible good AI can do. Cris Lacy, Co-president of Warner Music Nashville, told CBS Sunday Morning that unlike AI voice cloning sites that don’t “sound real because it’s not”, Warner’s latest use of AI to recreate Travis’s voice – with the approval of the man himself – is an example of the technology being used “for good”.
Source: Crystal Koe – musictech.com
