Machine Learning for Rock & Roll

Check out the SmartAmp Check out the SmartAmpPro

Read about GuitarML's story

Update: GuitarML is entering the 2021
KVR Developer Challenge! Look out for
a new plugin and vote for your favorite
starting July 1st.

How It Works


Input/Output samples of the amp or pedal are recorded for creating a digital model.


Machine learning algorithms are used to train a real-time digital model of the tone from the recordings. (see Tools section below for more info)

Make some noise!

Models are easily loaded into the plugin for unlimited tone possibilites on your guitar.

Download our pre-made high-quality tones

You can train models yourself with SmartAmpPro, or download our high-quality community tones and rock on.



The SmartAmpPro guitar plugin has been designed from the ground up to put the world of guitar tones at your fingertips. It uses machine learning to bottle up the essence of real amps and pedals in a sharable tone file. Using the training algorithms developed from the GuitarLSTM tool, you can record, train, and play tones within minutes, all from the SmartAmpPro plugin.

Download the SmartAmp VST3 plugin for Windows, Mac, or Ubuntu Linux

Download View on Github


The SmartAmp is a guitar plugin that uses machine learning to mimic all the nuances of a tube amplifier. It features a clean and lead channel with EQ and gain controls. Load your own tones or use the community-created tones for unlimited potential for your sound. The SmartAmp is free and open source.

Download the SmartAmp VST3 plugin for Windows, Mac, or Ubuntu Linux

Download View on Github


PedalNetRT on GitHub

The training algorithms use PyTorch to analyze .wav recordings of the input/output of the target amp or pedal. Anyone can use this to create their own tone models, but it is a slightly involved process that we are working on simplifying. Until then, put on your developer hat and check out PedalNetRT for using machine learning to create your own tone models. The resulting model will be compatible with the SmartAmp plugin.

Visit the GitHub page for more information on how you can create your own tones and get involved in the GuitarML community.

Go to the PedalNetRT GitHub page

GuitarLSTM on GitHub

This is the next iteration of machine learning for guitar effect/amp emulation. The GuitarLSTM code uses Tensorflow/Keras to train models for processing on wav files. Compared to the WaveNet model, the LSTM provides much faster training time with the potential for higher accuracy. Even on a CPU, training time is reduced to minutes rather than hours. Check out the Github page to try it out!

Go to the GuitarLSTM GitHub page


GuitarML is a community of developers and musicians using machine learning and related technolgies to create high-quality guitar tone. Advances in deep learning (artificial intelligence) have made it possible to play near-perfect tonal matches of real amps and pedals through a plugin. GuitarML is working to make this technology easy and accessible to musicians, developers, and A.I. researchers.

About the author: My name is Keith Bloemer, a software engineer and guitar player whose search for great guitar tone led me to create GuitarML. What started as a passion project has quickly grown into a community of developers and musicians contributing time and brainpower to make a great product. GuitarML is only possible due to the generosity of open source developers and researchers. In that same spirit, I hope this project inspires others to follow their curiosity and push the boundaries of what's possible in music technology.


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. Until recently, this technology was only available in high-end capture hardware costing over a thousand dollars. GuitarML believes that the best way to advance this technology is by releasing it as free and open source software for anyone to use and learn from. Because this software is free, your support is extremely valuable in making sure this work continues to grow and improve. Patreon and Github Sponsorship funds will go directly back into GuitarML, specifically for the following areas:

- website hosting fees and future growth
- Aquiring guitar amps/pedals for creating high end models for the community to jam with
- Improved recording equipment for capturing guitar amps/pedals for machine learning
- Development fees for supporting machine learning research and adding new plugin features

If giving financially is not an option, you can still support GuitarML by using the software, providing feedback, and simply spreading the word about GuitarML.

** All supporters will receive an exclusive amp model for use in SmartAmp and SmartAmpPro plugins. More benefits to come. **

Join our Patreon Become a GitHub Sponsor

Wall of Fame

I'd like to personally thank our patrons and sponsors, without you this work could not continue and grow.

Current Patreon Supporters:

William Edstrom

Current Github Sponsors:

Be the first!


We would love to hear about your experience using GuitarML's plugins! You can also contribute tone models as .json files and they may be included in the next TonePack release.


Send Feedback