Vizrt shows how live video can be produced anywhere, without complex studio setups
Updated
April 20, 2026 1:40 PM
A camera filming a still life on a table. PHOTO: UNSPLASH
Vizrt, a media technology company, has introduced a new AI-powered tool to simplify the creation of virtual scenes in live production. Its latest release, the AI Keyer, is built around a simple idea: remove the need for green screens and make virtual production possible in almost any environment.
Traditionally, creating virtual backgrounds or augmented reality (AR) scenes requires controlled studio setups, green screens, precise lighting and skilled operators. That makes high-end visual production expensive and difficult to scale, especially for smaller teams or live, on-the-ground reporting.
The AI Keyer is designed to address that gap. It uses AI trained on real-world footage to identify people in a frame and separate them from the background in real time. This allows production teams to replace backgrounds, insert AR graphics or place presenters into virtual environments—whether they are indoors, outdoors or on location.
"Creating XR environments typically demands large infrastructure investments and requires specialized skills for daily operations. The Vizrt AI Keyer removes all these constraints, so high-quality virtual scenes and AR graphics become a reality for live productions of every size", says Edouard Griveaud, Senior Product Manager at Vizrt.
In practical terms, this means a presenter can appear in a different location without moving, a remote speaker can be placed inside a virtual event space or branded graphics can be added to live interviews without a complex setup. The system works without chroma keying, reducing both preparation time and production overhead.
This shift also reflects how the company is approaching AI more broadly. Instead of treating it as a background feature, Vizrt is positioning AI as a core part of the content creation and delivery process.
"AI is transforming the world, and the creative industries are no exception. At Vizrt, we have been on this journey for years, embedding intelligence into our solutions, empowering storytellers and delivering real, measurable impact for our customers", says Rohit Nagarajan, CEO of Vizrt. "That is not a vision for tomorrow. That is happening today. The Vizrt AI Keyer is the latest proof point of our relentless commitment to innovation. Putting breakthrough technology in the hands of every creative, at every level, everywhere in the world".
Beyond the product itself, the direction is clear. By removing the need for green screens and complex setups, tools like the AI Keyer make it easier to produce high-quality visual content in more flexible settings. The result is a production model that is less tied to physical studios and more adaptable to real-world environments, where content can be created and adjusted in real time.
Keep Reading
Why investors are backing Applied Brain Research’s on-device voice AI approach.
Updated
January 28, 2026 5:53 PM
Plastic model of a human's brain. PHOTO: UNSPLASH
Applied Brain Research (ABR), a Canada-based startup, has closed its seed funding round to advance its work in “on-device voice AI”. The round was led by Two Small Fish Ventures, with its general partner Eva Lau joining ABR’s board, reflecting investor confidence in the company’s technical direction and market focus.
The round was oversubscribed, meaning more investors wanted to participate than the company had planned for. That response reflects growing interest in technologies that reduce reliance on cloud-based AI systems.
ABR is focused on a clear problem in voice-enabled products today. Most voice features depend on cloud servers to process speech, which can cause delays, increase costs, raise privacy concerns and limit performance on devices with small batteries or limited computing power.
ABR’s approach is built around keeping voice AI fully on-device. Instead of relying on cloud connectivity, its technology allows devices to process speech locally, enabling faster responses and more predictable performance while reducing data exposure.
Central to this approach is the company’s TSP1 chip, a processor designed specifically for handling time-based data such as speech. Built for real-time voice processing at the edge, TSP1 allows tasks like speech recognition and text-to-speech to run on smaller, power-constrained devices.
This specialization is particularly relevant as voice interfaces become more common across emerging products. Many edge devices such as wearables or mobile robotics cannot support traditional voice AI systems without compromising battery life or responsiveness. The TSP1 addresses this limitation by enabling these capabilities at significantly lower power levels than conventional alternatives. According to the company, full speech-to-text and text-to-speech can run at under 30 milliwatts of power, which is roughly 10 to 100 times lower than many existing alternatives. This level of efficiency makes advanced voice interaction feasible on devices where power consumption has long been a limiting factor.
That efficiency makes the technology applicable across a wide range of use cases. In augmented reality glasses, it supports responsive, hands-free voice control. In robotics, it enables real-time voice interaction without cloud latency or ongoing service costs. For wearables, it expands voice functionality without severely impacting battery life. In medical devices, it allows on-device inference while keeping sensitive data local. And in automotive systems, it enables consistent voice experiences regardless of network availability.
For investors, this combination of timing and technology is what stands out. Voice interfaces are becoming more common, while reliance on cloud infrastructure is increasingly seen as a limitation rather than a strength. ABR sits at the intersection of those two shifts.
With fresh funding in place, ABR is now working with partners across AR, robotics, healthcare, automotive and wearables to bring that future closer. For startup watchers, it’s a reminder that some of the most meaningful AI advances aren’t about bigger models but about making intelligence fit where it actually needs to live.