GPU Audio Real-Time Source Separation is here

Showcased at 2025's Audio Developer Conference, GPU Audio have delivered genuine real-time source separation utilizing deep learning for music demixing. Built using the HS TasNet, this latest SDK module provides a neural network adapted for real-time low-latency applications, offering huge potential for remixing and noise-cancelling audio streams in real-time.

It has been described as "AI breakthrough of the hour" by David Frangioni here.

The HS TasNet uses a combination of spectral and waveform domain data, providing accurate and artifact-free processing - utilizing GPU Audio's patented technology for extremely low latencies. If you're interested in integrating the GPU Audio platform into your commercial products, fill out this form and we'll get in touch.

GPU Audio: Soundcore

GPU Audio has changed the face of accelerated audio for all kinds of industries. They've just announced that their Pro Audio division is now Soundcore - with specific brands for each of the fields they're now working in and researching.

Soundcore from GPU Audio will be the technology at the heart of their vision for Pro Audio acceleration and they're proud to share this news with you today.

The GPU Audio SDK is FREE to download and evaluate now, head over to gpu.audio/sdk