Amp ONE vs Neural Amp Modeler

Amp ONE is a free iPad application for real-time guitar preamp and cabinet simulation with effects. It turns an iPad into a modeled tube-preamp and cabinet setup, using pretrained artificial neural network models for circuit simulation. Listed preamps include Marshall JCM800, Cornford Harlequin, Engl E530, Krank models, an American hi-gain amp, EVH 5150 III and Fender Blues Junior III. Cabinet power-amplifier behavior is modeled through convolution. Effects include an adjustable noise gate, swell-capable fade timing, four stereo chorus models, delay and reverb. Snapshot and preset functions can save all settings or selected sections. Amp ONE supports AudioBus and Inter-App Audio. The stated requirements are an Apple iPad 2 or later and iOS 7.1 or later; an external audio interface is required to connect a guitar. The App Store listing says it is designed for iPad and is not verified for macOS. Apple’s listing provides no developer privacy details.

Neural Amp Modeler (NAM) uses deep learning to create models of guitar amplifiers and pedals. The project is free and open source, with three code repositories under permissive licenses that are open to contributions. Users can train models online in Google Colab or install the Python-based trainer locally from PyPI. The Gateway plugin loads and plays snapshot models of gear, while ParametricOD demonstrates modeling across an overdrive's knobs and switches. The plugin repository produces VST3 and AU plugins as well as a standalone desktop application. Models can be shared through TONE3000, a community-organized online library. NAM runs on Windows, macOS, Linux, Raspberry Pi, embedded systems, and websites. Existing A1 models remain supported in NeuralAmpModelerCore and NeuralAmpModelerPlugin. Builders can incorporate NAM's open-source modeling technology into their own products. The training code depends on PyTorch Lightning; version 0.12.3 excludes compromised Lightning versions 2.6.2 and 2.6.3.