How Randy Travis used AI to help get his voice back after a decade away

Legendary Country artist, Randy Travis , gave fans the ultimate gift ahead of his 65th birthday as he released new music for the first time since suffering a stroke in 2013 that left him with limited speech. So how exactly did he capture the essence of his voice from before the stroke? The answer is Artificial Intelligence (AI).

Listen to 80s Country Classics and more on the free Audacy app

With some help from one of today’s most talked-about topics — AI —  Travis’ team was able to capture the vocals Country fans know and love from his biggest hits like, “Forever and Ever (Amen)” and “I Told You So,” and apply them to new music. All of this with the blessing from Travis and his wife, Mary , of course.

“Well, we were all over that, so we were so excited,” Mary told The Associated Press of she and Travis’ reaction to Warner Music Nashville co-president, Chris Lacy , approaching them with the idea of AI. “All I ever wanted since the day of a stroke was to hear that voice again.”

Lacy reached out to developers in London to start the process by using two AI models. The first used 12 song samples from Travis while the second collected 42 from across his career (1985 to 2013). The collected vocals were applied to the song “Where That Came From,” which was written by Scotty Emerick and John Scott Sherrill and co-produced by Travis’ longtime producer, Kyle Lehning , who had large involvement in the process of applying AI to the song.

“I never even thought about another song,” Lehning told AP before detailing the first time he heard the AI-generated vocals. “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% what you hear now.” To authenticate the track even more, Lehning sought help from engineer Casey Wood , who also worked alongside Travis for decades.

“We were able to just improve on it,” Lehning said of working alongside Wood on the AI recording by adding more vocal characteristics specific to Travis. “It was emotional, and it’s still emotional.”

Travis and his team’s use of AI may seem controversial to some who have followed the music industry’s reaction to its development. Just last month, more than 200 artists called out AI-connected companies by signing a letter submitted by the Artist Rights Alliance non-profit demanding them to stop using AI “to infringe upon and devalue the rights of human artists.” While validating other artist’s concerns, Mary Travis shared she and Travis’ team hope their use of AI in such a respectful way will “set the standard,” as its popularity continues to emerge.

“Randy, I remember watching him when he first heard the song after it was completed,” she shared. “It was beautiful because at first, he was surprised, and then he was very pensive, and he was listening and studying. 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.”

Lacy added, “The motivation behind a musical recording is specific to each individual artist. The genesis of this particular track came from a visceral desire to restore what was taken away from someone we know and love - Randy Travis. It was inspired by his courage to continue as a vital contributor to the music community. In working with him to make new recordings, the byproduct is a gift that goes straight to our hearts.”

He concluded, “AI may have been a tool that helped us along, but it was a group of dedicated and passionate humans, including Randy himself, that brought this beautiful song to life.”