GuitarML: The SmartPedal

GuitarML founder, Keith Bloemer, is an aerospace engineer and guitar player. What started as a passion project has grown into a community of developers and musicians that contribute time and brainpower to make a great product. GuitarML uses machine learning and related technologies to create high-quality guitar tones. Advances in deep learning (artificial intelligence) have made it possible to play near-perfect tonal matches of real amps and pedals through a plugin. While there are many guitar plugins out there, GuitarML’s plugins are unique in that they use advanced machine learning to model the dynamic response of real amps and pedals. GuitarML is working to make this technology easy and accessible to musicians, developers, and AI researchers.

The SmartPedal allows users to recreate the sound of real world hardware, such as a TS9 Tube Screamer or Blues Jr amp, and Drive and Level can adjust the signal gain before and after the WaveNet model processing. The WaveNet model is effective at emulating distortion style effects or tube amplifiers, but cannot capture time based effects such as reverb or delay. 

This plugin uses the same WaveNet model architecture as SmartAmp, and you can load your own trained models from the PedalNetRT code. Capture your own devices and load the models using the SmartPedal. For the easiest way to create your own models download the Capture Utility zip file, which includes a Google Colab script and wav file. 

As of version 1.5, the SmartPedal can run models conditioned on a single parameter, such as a gain control. When conditioned models are loaded, the LED graphic will change colours from red to blue, and the Drive knob will control the conditioned parameter.

Available formats (from installer):

• Windows 10/11 64-bit (VST3, AAX)
• Mac 10.11 and up (AU, VST3, AAX)
• Linux (VST3, AAX)