Val Kilmer’s voice was recreated using AI technology for his role in ‘Top Gun: Maverick’.
The 62-year-old actor lost his voice after undergoing a tracheotomy in 2014 as part of his treatment for throat cancer, and so when it came to reprising his role as Iceman in the long-awaited sequel, he worked with tech start-up company Sonantic to create his dialogue.
The firm’s CTO and co-founder, John Flynn, told Fortune: “From the beginning, our aim was to make a voice model that Val would be proud of.
“We were eager to give him his voice back, providing a new tool for whatever creative projects are ahead.”
Sonantic typically create a voice model for an actor by having them record performances they read from a script but Val’s case needed “a bit more manual work”.
After cleaning up old audio recordings of the ‘Paydirt’ star, they used a “voice engine” to teach the model how to speak like the actor, but with around 10 times less data than they usually work with, the company had to come up with new algorithms to produce a higher-quality voice model.
John noted: “In the end, we generated more than 40 different voice models and selected the best, highest-quality, most expressive one.
Those new algorithms are now embedded into our voice engine, so future clients can automatically take advantage of them as well.”
After producing the model, creative teams were able to input specific text and fine-tune the performance, and Val couldn’t have been happier.
He said: “[Sonantic have] masterfully restored my voice in a way I’ve never imagined possible.
“As human beings, the ability to communicate is the core of our existence, and the effects from throat cancer have made it difficult for others to understand me,” he added. “The chance to tell my story, in a voice that feels authentic and familiar, is an incredibly special gift.”