Neuphonic & Rapport Bring Real-Time, Photorealistic Digital Human System to Everyday CPU

High-quality characters are not exclusive to big companies anymore.

AI voice company Neuphonic has partnered with Speech Graphics' Rapport division to produce "what they believe is among the first fully real-time, photorealistic digital human systems running entirely on standard CPU hardware."

Rapport’s character animations were used in Call of Duty, The Last of Us Part II, and Hogwarts Legacy, and with Neuphonic’s sub-100ms, CPU-only text-to-speech, they will create "fully on-device avatars that speak and react with no perceptible delay."

"Running on everyday CPUs rather than specialised GPUs or the cloud, the system makes responsive, privacy-preserving digital characters practical at scale for games, film/virtual production, advertising and training - and potentially across billions of devices," the companies said in a press release, adding that this should unlock a new generation of interactive content and help overcome the uncanny valley.

“We’re making real-time digital humans practical,” said Sohaib Ahmad, CEO and co-founder of Neuphonic. “For the first time, you can run a fully interactive, lifelike avatar instantly on everyday hardware. It shifts this from something that required high-end infrastructure to something that can run anywhere, and will unlock entirely new use cases across games, media and AI. It will move us closer to AI that feels like a natural, seamless extension of human interaction.”

“Neuphonic was a natural partner because the technologies are highly complementary,” said Gregor Hofer, CEO and Co-founder of Rapport, a division of Speech Graphics Ltd. “They bring ultra-low latency, on-device voice that runs efficiently on CPU, and we bring production-proven, real-time facial animation. Together, this enables fully local digital humans that can speak, animate and respond instantly, without relying on the cloud, opening up new possibilities for performance, cost and deployment at scale. It’s a complete, real-time conversational experience.”

For gaming, it means NPCs that speak and react dynamically. The system runs on-device, so user data never leaves the environment, "reducing latency, cost, and infrastructure complexity while making real-time avatars deployable across billions of devices."

Don't forget to subscribe to our Newsletter and join our 80 Level Talent platform, follow us on Twitter, LinkedIn, Telegram, and Instagram, where we share breakdowns, the latest news, awesome artworks, and more.

Are you a fan of what we do here at 80 Level? Then make sure to set us as a Preferred Source on Google to see more of our content in your feed.