{"id":76,"title":"Real-Time Source Separation  is Here ","bg_image":{"url":"https://eap-spaces.fra1.cdn.digitaloceanspaces.com/storage/newsfeed/article/bg_image/76/8896-image.jpg","collage":{"url":"https://eap-spaces.fra1.cdn.digitaloceanspaces.com/storage/newsfeed/article/bg_image/76/collage_8896-image.jpg"}},"type":"Newsfeed::Article","preview":"GPU Audio SDK Updated","views":0,"content":"\u003cp\u003eThe GPU Audio SDK has been updated to support the latest NVIDIA and AMD Graphics Cards and we have more good news! Building on the support we received for Steven Atkinson’s NAM Module, we’re here to announce the second SDK module: Real-Time GPU Based Source Separation!\u0026nbsp;\u003c/p\u003e\u003cp\u003eShowcased at 2025's Audio Developer Conference event in Bristol, we’ve delivered genuine real-time source separation utilizing deep learning for music demixing. Based on the \u003ca href=\"https://github.com/lucidrains/HS-TasNet\" rel=\"noopener noreferrer\" target=\"_blank\"\u003eHS TasNet\u003c/a\u003e which has been researched and investigated by L-Acoustics, this new GPU Audio SDK module provides a neural network adapted for real-time low-latency applications. Opening huge potential for remixing and noise-cancelling audio streams in real time - for live shows and many other applications.\u0026nbsp;\u003c/p\u003e\u003cp\u003e\u003cstrong\u003eWe’ve delivered real time processing, something no one else has achieved.\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\u003cp\u003eThe \u003ca href=\"https://github.com/lucidrains/HS-TasNet\" rel=\"noopener noreferrer\" target=\"_blank\"\u003eHS TasNet (Hybrid Spectrogram Time-domain Audio Separation Network)\u003c/a\u003e utilizes a combination of spectral and waveform domains which L-Acoustics state: “demonstrate the potential of efficient demixing for real-time low-latency music applications”. In their white paper, a latency of 23 ms is suggested, which we have developed to be just 512 samples with the GPU, even in its early stages.\u0026nbsp;\u003c/p\u003e\u003cp\u003e\u003cstrong\u003eTry the updated SDK for FREE by visiting \u003c/strong\u003e\u003cstrong style=\"color: rgb(194, 133, 255);\"\u003ehttps://gpu.audio/sdk\u003c/strong\u003e\u003c/p\u003e\u003cp\u003eSome stats:\u003c/p\u003e\u003cul\u003e\u003cli\u003eCPU version (with Eigen) gives you a 0.18x of RTR\u003c/li\u003e\u003cli\u003eMeta's PyTorch (GPU) gives you only 0.58x of RTR\u003c/li\u003e\u003cli\u003eGPU Audio gives you a 6.95 of RTR\u003c/li\u003e\u003c/ul\u003e\u003cp\u003e\u003cstrong\u003eThis is around a 12x performance boost with our Technology\u003c/strong\u003e\u003c/p\u003e\u003cp\u003eThese numbers are scalable on both single and multiple devices, with just a few milliseconds latency; no historical data (compared with Meta Demucs' v4), and the opportunity to rebuild using our SDK and achieve almost a 7x RT factor. Find out more about HS TasNet in the aforementioned white paper entitled: \u003ca href=\"https://www.l-acoustics.com/wp-content/uploads/2024/04/real_time_demixer_2024_04_19.pdf\" rel=\"noopener noreferrer\" target=\"_blank\"\u003e“Real-time Low-latency Music Source Separation Using Hybrid Spectrogram-TASNET“\u003c/a\u003e.\u0026nbsp;\u003c/p\u003e\u003cp\u003e\u003cstrong\u003eThe updated SDK is available NOW for Windows and Mac on our \u003c/strong\u003e\u003ca href=\"https://github.com/gpuaudio/gpuaudio-sdk\" rel=\"noopener noreferrer\" target=\"_blank\" style=\"color: rgb(194, 133, 255);\"\u003e\u003cstrong\u003eGithub page\u003c/strong\u003e\u003c/a\u003e\u003cstrong style=\"color: rgb(194, 133, 255);\"\u003e.\u003c/strong\u003e\u003c/p\u003e","pathname":"real-time-source-separation-is-here-76","human_date":"04 Feb 2026","read_time":"5 minutes","category":"","related_items":[{"id":1,"title":"ADOBE MAX LOS ANGELES 2022","bg_image":{"url":"https://eap-spaces.fra1.cdn.digitaloceanspaces.com/storage/newsfeed/event/bg_image/1/efa3-image.jpg","collage":{"url":"https://eap-spaces.fra1.cdn.digitaloceanspaces.com/storage/newsfeed/event/bg_image/1/collage_efa3-image.jpg"}},"type":"Newsfeed::Event","preview":"GPU Audio joins our partners, AMD, to demonstrate how GPU Audio plugins can be used to enhance workflows of post production workstations. Find us at the AMD booth, nearby Meta and other great compa...","views":0,"pathname":"adobe-max-los-angeles-2022-1","human_date":"18 Oct 2022","human_time":null,"event_type":null,"registration_link":""},{"id":2,"title":"AES NYC 2022","bg_image":{"url":"https://eap-spaces.fra1.cdn.digitaloceanspaces.com/storage/newsfeed/event/bg_image/2/6528-image.jpg","collage":{"url":"https://eap-spaces.fra1.cdn.digitaloceanspaces.com/storage/newsfeed/event/bg_image/2/collage_6528-image.jpg"}},"type":"Newsfeed::Event","preview":"October 19-20, Time TBA","views":0,"pathname":"aes-nyc-2022-2","human_date":"19 Oct 2022","human_time":null,"event_type":null,"registration_link":""}]}