tech illustration by sara davidson for use by 360 Magazine

Speech AI Company Sonantic Gives Val Kilmer His Voice Back

Revolutionary advancements in AI voice technology give Kilmer the ability to perform again after suffering side effects from throat cancer.

Sonantic, a UK-based startup leading the charge on emotional text-to-speech technology, has created a voice model for actor Val Kilmer, who was diagnosed with throat cancer in 2015 and has since undergone a tracheotomy procedure. The award-winning actor, whose Hollywood career has spanned nearly four decades, has difficulty communicating in a voice that is easily recognized or understood by fans. The AI-generated voice model, which was developed by utilizing clips of Kilmer’s voice prior to his illness, can be heard in a demo video that was created in close collaboration with the actor.

“I’m grateful to the entire team at Sonantic who masterfully restored my voice in a way I’ve never imagined possible,” said Val Kilmer, adding, “As human beings, the ability to communicate is the core of our existence and the side effects from throat cancer have made it difficult for others to understand me. The chance to narrate my story, in a voice that feels authentic and familiar, is an incredibly special gift.”

Founded in 2018, Sonantic has built a cutting edge platform that creates hyper-realistic, emotionally expressive, and controllable artificial voices. Sonantic has mastered this with its proprietary Voice Engine, which captures the nuances of the human voice such as accents, emotions and delivery styles. This process typically requires actors to record various lines of dialogue in a studio, but only historical footage could be used to create Kilmer’s voice model. After cleaning up the audio samples, Sonantic was left with 10x less data than typically needed. This led to the creation of new algorithms, techniques and models that have since been incorporated back into the Voice Engine, strengthening its ability to handle difficult voice content. These breakthrough advancements in the technology — which allowed for the creation of 40 different options before finalizing Kilmer’s prototype — have further enhanced Sonantic’s capabilities and will benefit all future voice projects.

This announcement comes on the heels of Amazon Studios’ release of Kilmer’s autobiographical documentary, Val, which touches upon the actor’s cancer battle and the physical and emotional toll it has taken on him. During the development of the documentary, Sonantic was introduced to Kilmer’s team which ultimately led to the creation of his voice model. By turning the written word into lifelike audio, Kilmer will be able to use the model  in both his professional and personal life. On the work front, Kilmer can take part in TV or film productions that require voice overs or replacement dialogue that will be created by Sonantic’s easy-to-use computer app. In terms of day-to-day living, Kilmer’s voice model can serve as a personalized replacement to robotic speech generating devices.

Sonantic’s co-founders Zeena Qureshi, CEO and John Flynn, CTO said in a joint statement: “It was an honor to create a voice model for Val Kilmer, whose courage and creativity is truly inspiring. This was an emotional project that demonstrates how Sonantic’s AI generated voice models can have a positive impact on the acting community at large. We’re proud to help Val continue his craft in a way that wasn’t feasible before, and we look forward to seeing what he takes on next.”

This groundbreaking advancement in speech and sound production is revolutionizing the film and gaming industries. Sonantic’s immersive voice acting on-demand allows its top tier B2B clients — including Amazon Studios, XBox Game Studios’ Obsidian Entertainment and Remedy Games — to significantly expedite timelines, streamline processes and lower production costs. Actors play a critical role in crafting voice models, which are scalable assets that generate passive income and create new job opportunities without the commitment of time and travel. Considered the CGI of voice for the industry, actors have embraced this hybrid approach that enables them to take on both traditional, real-life acting jobs as well as innovative, AI voice model work.

Leave a Reply