Three Body Tech – Deep Vintage (Windows)

Featuring Three-Body Tech’s proprietary Audio Processing Neural Network (APNN), a machine learning technology specializing in modeling analog effects processors, Deep Vintage delivers a listening experience as close to the legendary hardware models as possible, while still providing full real-time processing.

We’ve been exposed to numerous emulation technologies: physical modeling, convolution… and many more. Regardless of which technologies we use, our ultimate goal remains the same: to achieve the highest possible fidelity to the sound of real devices.

APNN has been carefully designed and trained to excel at this task, as its training is based on audio signals from real hardware devices. Deep Vintage plugins are not just “theoretically correct circuit modeling” and are not based solely on harmonic structures or impulse responses; they capture 100% of the 3D sensation in analog audio.

Simply put, APNN is a neural network specifically optimized for audio processing, which consists of a massive combination of audio processing modules (equalizer, compressor, overdrive, etc.).

To capture the essence of the hardware model, APNN will automatically adjust its structure and parameters until the difference between its output and the hardware output gradually decreases.

Ultimately, APNN achieves a phase compensation error signal of approximately -40 dB to -75 dB (depending on the equipment model). With this exceptional level of error control, which even exceeds the variance between different production lots of the same equipment model, we can confidently say that APNN is able to “fool” human ears.