An event powered by
Close this search box.


Advances in voice tech and machine learning helped recreate Val Kilmer’s voice for the blockbuster sequel to the 1986 classic


Spoiler alert: Do not read unless you have watched “Top Gun: Maverick.”

Val Kilmer’s Tom “Iceman” Kazansky makes an unforgettable appearance in Top Gun: Maverick — with a little help from science.

Filmed after the actor, 62, recovered from throat cancer, the newly released follow-up to 1986’s Top Gun sees Kilmer reunite with Tom Cruise onscreen over 35 years after the original movie.  Artificial intelligence previously developed by Sonantic for Kilmer was leveraged for his role in the sequel.

Val Kilmer, ritratto, indossa camicia bianca e giacca blu
Val Kilmer I Credits: Wikipedia

‘Iceman’ had to be in it

The actor lost his ability to speak after going through throat cancer treatment in 2014. However, Val Kilmer’s return as Tom “Iceman” Kazansky was an undeniable highlight for many.

Instead of leaving Iceman and Kilmer out of the long-anticipated sequel, the writers wove Kilmer’s story into the character. In “Top Gun: Maverick,” Iceman also has cancer and, for the majority of his brief time in the film, communicates with Maverick by typing.


Voice technology and machine learning

However, Kilmer does have one emotional line of dialogue, which required a unique partnership between Kilmer and Sonantic, a voice synthesis company. Sonantic, with which Kilmer previously partnered in 2021 for another project, fed hours of Kilmer’s archival recordings through an A.I. to generate a voice model that is a vocal clone of the actor.

The work done by Sonantic back in 2021 blog post, “generated more than 40 different voice models and allowed to select the best, highest-quality, most expressive one” for Kilmer. “From the beginning, our aim was to make a voice model that Val would be proud of”, said Sonantic CEO John Flynn. “We were eager to give him his voice back, providing a new tool for whatever creative projects are ahead.”

Voice technology I credits: Site by Site

Those new algorithms are now embedded into the Sonantic Voice Engine, so future clients can automatically take advantage of them as well. So, what’s been used for Top Gun: Maverick might come useful to other in the future – including Val Kilmer himself, that “he’ll probably use it for something creative and, at the very least, just to communicate with us when he’s feeling tired” according to Jack, 26, actor’s son

Rapid advances in vocal synthesis technology

Sonantic’s work with Kilmer is only possible because of rapid advances in vocal synthesis technology over the last decade. What used to be a time-consuming, expensive process that required hours of recorded or archived audio to create or restore a voice is more streamlined and advanced than ever before.
An Oscar-worthy performance is still human

Kilmer’s appearance in “Top Gun: Maverick” has brought audiences to tears, but audiences shouldn’t expect Oscar-worthy work from an A.I.-assisted voice performance just yet.

“It’s going to be a while, but what we’re seeing today versus even five years ago is a night-and-day difference because machine learning has supercharged this field in a way that we could never imagine,” said professor Patel from Northeastern University, who has extensively reseaching and workin on those topics.

Lights and shadows

However, as with any new technology, professor Patel urged caution when considering its uses––and misuses. 

“It’s going to be really important that companies that are creating voice clones actually have a seat at the table to understand how to prevent this from being misused and abused technology,” Patel said. “Consent is really important. Understanding the use cases is really important.”

“Taking a measured, multi-pronged approach to the future of this technology­­ will pay dividends”, she said, especially as voice synthesis continues to advance.