We would like to leave stealth mode with a research project and share some exciting results.
With the core team, we could not afford to work on anything really future related since I joined MOD two years ago. Delivering against crowdfunding promises and retailer requests took absolute priority. Still I wanted to make a tiny moonshot on the side somehow happen.
We were lucky enough to have @itskais join us for his end of master study internship, starting in March and finishing this week. As several attempts for investment failed, it was truly not the ideal time for an ambitious research project. I’m glad @itskais did not bother and the company survived his internship just about.
His target was to research various potential AI applications on the MOD platform, develop a concept for the most promising one and show its technical feasibility.
Results are very promising - see below. I’m curious about everyone’s feedback.
Thank you @itskais for the great collaboration! Would love to have you onboard the MOD reboot to bring this project to market and drive AI based plugins forward together with the developer community.
Building electric guitar pedal-boards is usually a manual process that involves technical knowledge, musical knowledge, and an artistic vision. This project consists of designing an intelligent tool that assists guitar players when building their pedal-boards on MOD units.
The project is still in a technical POC phase, and for now we are focusing on two main parts of an electric guitarist’s rig: the AMP and the CAB. We have chosen a set of 10 amp configurations and 10 cabs that, in combination, we believe covers a wide range of electric guitar sounds out there. Based on an input guitar tone, our models are now able to predict (or suggest) with high accuracy which amp and cab you can use to get as close as possible to the input sound.
We also just started incorporating some reverbs along with the AMP and CAB sets, and in the future we’re hoping to add a multitude of plugins and effects, so that YOU can just upload a guitar sound that you heard online and quickly get a close (potentially identical) tone using your MOD unit.
Here’s a video that demonstrates what we already have at the moment, and hoping to continue improving it in the near future!
Video link:
The research project finished with a technical proof-of-concept, which is an AI model you cannot access at the moment. To make it a usable for you, a user frontend needs to be designed and the overall pedalboard assistant needs to be implemented in a scalable way.
This requires a funded company and the hiring of @itskais. It’s part of the MOD reboot plan to launch a minimum-viable-product next year. Curious minds here in the forum would for sure get early acces in order to improve the model with their feedback.
Would love to see that come to live. Let’s cross fingers for the reboot!
One of my greatest interests in getting a MOD was the capability of being able to chain pedals and amps in orfer to replicate whatever sound I wanted for my guitar.
One of the greatest disappointments was how hard it is, expecially for relatively simple things.
Lots of amps. Lots of delays. Lots of choruses. If I need to try every one of them I’d spend weeks only to make one pedalboard.
I think a great obstacle that prevented MOD devices to be much more widespread is the learning curve to put them to good use. That think would be a game changer.
This is an innovation in the leage of kemper amps with their profilers. I think this feature could be of huge interest for investors…
Hope to see this come to life!
