Spektral lets you

mix realities and tell compelling stories in real-time

Read more

The Tech Behind

Our pioneering and unique technology is based on state-of-the-art machine learning and computer vision techniques. Combining deep neural networks and spectral graph theory with the computing power of modern GPUs, our engine can process images and video from the camera in real-time (60 fps) directly on the device.

Specialized deep neural networks trained on +1 million images

Our core tech derives from spectral graph theory & mathematical image processing

Real-time and high-quality rendering based on efficient GPU implementation

Read more


Through machine learning and spectral graph theory we have created a technology that can cutout people in real-time on a smartphone. Continuously building on our algorithms you will soon have the power to build apps that give totally new possibilities when it comes to video creation.

Create any background to replace in real-time
The background is removed in real-time
Anything can be added anywhere

Real-time on a smartphone

Object and person segmentation

High quality details

Immersive Content

Users want to easily create fun and exclusive video content and with our technology you'll soon have a new way to create unique and immersive content

Wanna be in the loop?

Subscribe and be the first to know about news and updates from us, and don't worry, we hate spam too. We won't share your details with anyone.

Our team

We’re proud to have a world class team of highly educated people in the fields of machine learning, algorithms and marketing.

Go to Our Team