News
bitHuman launches CPU-based avatar SDK
AI company bitHuman has released a software development kit (SDK) designed to allow developers to run interactive, high-fidelity avatars on devices powered solely by CPUs, including Chromebooks, Mac Minis, and Raspberry Pis.
The SDK supports both Arm and x86 processors, removing the need for graphics processing units, which the company says reduces deployment costs and power consumption. According to bitHuman, the approach makes it easier for developers to create responsive avatars that can run online or offline in environments such as classrooms, kiosks, mobile apps, and edge devices.
The company said the SDK can deliver lifelike interactions with latency under 100 milliseconds. It also includes a plug-in for video and voice platform LiveKit, allowing developers to integrate avatars into existing applications with minimal coding. Users can assign custom voices to avatars by uploading audio samples or selecting from prebuilt voice profiles, with speech streamed in real time over LiveKit’s low-latency infrastructure.
“Now with bitHuman’s SDK, in just a few minutes, anyone can run a virtual Einstein, a cartoon character, or a playful turtle that interacts with kids or becomes a language tutor, virtual companion, or a virtual pet,” said Steve Gu, bitHuman CEO, in a statement. “The ideas are endless, and now you can easily create this. “More importantly, all enterprise data can stay on-prem without worrying about leaking to the outside world.”
Arm executive Parag Beeraka said the SDK benefits from Arm’s energy-efficient CPU architecture and wide adoption, enabling rich, on-device AI experiences without the need for cloud processing.
“Running AI in the cloud can be a challenge in certain scenarios due to privacy, latency or cost,” Beeraka said in a statement. “bitHuman’s SDK takes full advantage of Arm’s CPU performance and widespread adoption to deliver rich, responsive avatars, showing how on-device AI is unlocking new, immersive user experiences.”
The SDK is available through bitHuman’s ImagineX platform, with options for local hosting or via a cloud API that offers similar low-latency performance. Early adopters have used the system in trade show displays, educational applications, and hackathon projects, the company said. One team used it to build an AI-powered dog that placed second in a competition.
About the Author
John K. Waters is the editor in chief of a number of Converge360.com sites, with a focus on high-end development, AI and future tech. He’s been writing about cutting-edge technologies and culture of Silicon Valley for more than two decades, and he’s written more than a dozen books. He also co-scripted the documentary film Silicon Valley: A 100 Year Renaissance, which aired on PBS. He can be reached at [email protected].
Source: adtmag.com
