GPU Audio have announced that their long-awaited SDK (Software Development Kit) is now available, opening up their GPU-accelerated processing to those developing their own plug-ins and applications.
The GPU Audio SDK offers cross-platform support for Windows (10 or 11) and macOS (13 – 15) systems with integration for NVIDIA and AMD GPUs, as well as Apple Silicon M1 chips and above. As a result, there's no need for developers to write device-specific code for each platform, and both are capable of running buffer sizes as low as 96 samples, resulting in a 1ms buffer time at 96kHz. The company say that the primary goal of the platform is to provide guarantees on backward compatibility, enabling developers, partners and vendors to detach the update cycles of their products from the update cycles of the GPU Audio platform.
The company say that use cases for the SDK are unlimited, but could include low-latency multichannel processing, dynamic spatial reverbs, room simulation, acoustic room correction, multi-channel sound synthesis, real-time inferencing of complex models and machine learning-enabled workflows (such as harmonising multiple instruments) and many more.
Example Use Cases
GPU Audio have supplied some supporting documentation along with some examples that users can get started with, including:
- Gain Processor: A simple example to get familiar with GPU Audio-specific APIs and create first your GPU-powered processor.
- IIR & FIR Processor: Examples of IIR filtering and FIR/convolution. These are integrated into terminal/console tests that can be used to process files and measure performance.
- NAM Plugin: Neural Amp Modeler with GPU acceleration of the real-time inferencing. GPU Audio have provided everything to build a VST3 plug-in on Windows, and VST3/AUv2 plug-ins on macOS.
Availability
The GPU Audio SDK is available now, and is free to download from the company’s website.
