Overall: 209 162 208
30-Day: 1474; 7-Day: 1516; Yesterday: 21337
Chameleon is a guitar plugin/standalone app using neural networks to create three distinct sounds from a vintage style amp head. The core sound comes from a neural net inference engine which allows the plugin to disguise itself as a high end tube amplifier. Advanced machine learning was used to capture three distinct sounds, named Red (high gain), Gold (crunchy), and Green (clean). In the same way a real amp head is used with a cabinet and other effects, this plugin is intended to be used in the signal chain along with IR's (cab sim), reverb, and any number of guitar effects.
Chameleon is free and open source on Github for anyone interested in audio DSP with machine learning and neural networks. The capture technique used here is capable of reproducing the dynamic response of real amps and pedals to near perfection.
***For best results, use with 44.1kHz samplerate, which is the optimum samplerate of these particular neural net models.***.
Check out the source code on GitHub.
Read the tech article published on Towards Data Science.
Visit the website for more from GuitarML.
Think it sounds pretty good after an initial test. There seems to be a GUI bug when resizing, the amp/channel select switch shrinks to almost not visible but re-appears the correct proportional size if you click on it or in the area its supposed to be in (I'm on Windows 7, Ableton 10).Read Review
It does the job for what I need, giving me interesting sonic character.
Thank you so much for the plugin.Read Review
Like almost every neural network based plugin, which I know and have tested up to now, this plugin does not at all fulfill the promises, which the description makes.
It also does not at all sound only similar to the real tube amp, which the GUI - why ever - amateurishly tries to simulate.
For me one of these typical, wrong sounding, dispensable sonic bluff packages.Read Review