A series of plugins for modeling equipment based on artificial intelligence.
The Deep Vintage series is a collection of plugins that emulate real hardware. Using the power of AI, each Deep Vintage plugin faithfully captures the true “soul” of vintage gear.
Featuring Three-Body Tech’s proprietary Audio Processing Neural Network (APNN), a machine learning technology specialized in modeling analog effects processors, Deep Vintage guarantees you a listening experience as close as possible to legendary hardware models, while providing full real-time processing.
What’s the difference?
We’ve been exposed to numerous emulation technologies: physical modeling, convolution… and many more. No matter what technologies we use, our ultimate goal remains the same: to achieve the highest possible sound fidelity to real devices. APNN has been carefully designed and trained to succeed in 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 are also designed to simulate real-world hardware. They capture 100% of the 3D sensation in analog audio.
How does it work?
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.). In order 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 hardware model). With this exceptional level of error control, which even surpasses the variance between different production batches of the same hardware model, we can confidently say that APNN is able to “fool” the human ear.
- Brit 73 AI
- US Rack AI
- Thick Pre AI
- Green AD AI
- Tape S AI
- Tape M AI
