Neural Amp Modeler

Welcome to the definitive guide on Neural Amp Modeler (NAM) – the open-source AI technology that lets anyone capture and share hyper-realistic digital models of amps, pedals, cabs, rigs and outboard gear.

Neural Amp Modeler Plugin

What is NAM?

Neural Amp Modeler (NAM) is free, open-source technology that uses AI to create digital models of analog music equipment like guitar amplifiers, bass amps, effects pedals, preamps, outboard gear and complete signal chains. Unlike traditional amp simulators that attempt to recreate what gear should sound like using circuit modeling, NAM actually listens to real audio recordings from physical gear and trains a neural network to behave exactly like the original.

The result is a NAM capture (also called a NAM profile, NAM model or NAM file) that delivers tone and dynamic response so authentic it's virtually indistinguishable from the real thing. NAM represents a breakthrough in digital amp modeling, combining machine learning with audio processing to capture the complex nonlinear behavior that makes analog gear sound so good.

Who is NAM for?

Neural Amp Modeler is for guitarists, bassists, producers, and audio engineers who demand authentic analog tone without compromise. Whether you're a bedroom guitarist recording at home, a touring musician who needs reliable stage tone, or an engineer archiving rare vintage equipment, NAM gives you unlimited access to iconic amplifiers and gear. If you care about tone quality and want the flexibility of digital with the authenticity of analog, NAM is for you.

What are the benefits of NAM?

Neural Amp Modeler delivers the true character and feel of real amplifiers with stunning accuracy that surpasses traditional amp modeling. You get authentic tube amp response, natural compression, and dynamic touch sensitivity – all the qualities that make playing through a real amp inspiring – without the volume, weight, maintenance, or expense. NAM lets you record silently at any hour, swap between dozens of amps instantly, and access rare vintage gear you'd never afford or find.

The growing TONE3000 community shares thousands of free NAM profiles capturing everything from pristine Fender cleans to saturated Marshall stacks to boutique high-gain monsters. NAM profiles work across multiple plugins and hardware platforms, so you're never locked into a single product. For live performance, NAM provides consistent, reliable tone night after night without worrying about tube wear or amplifier failures.

How can I use NAM?

Here are some popular uses, though there are probably way more:

  • Create studio-quality recordings without expensive studio sessions
  • Play live without lugging around expensive and heavy gear that's prone to damage
  • Create an organized library of your favorite tones that you can use anywhere
  • Experiment with tones without retracking, reamping or setting up gear
  • Recreate tones (e.g. tone match) even if you forgot your signal chain or settings
  • Share your favorite tones with friends, family or lovers
  • Play models of your gear through headphones/monitors instead of blasting through a wall of 4x12s and having your neighbors call the police

How does NAM work?

Neural Amp Modeler works by training an neural network to learn the input-output relationship of an amplifier as a mathematical function. Instead of simulating the physics of tubes, transformers, capacitors, and circuits, NAM analyzes the actual behavior of real gear by studying what audio comes out when specific signals go in. Here's the NAM capture process:

  • Sweep Signal: A specially designed training signal called a "sweep signal" is sent through the gear you want to model
  • Recording: Both the input signal (DI) and the output from the mic'd amp are recorded simultaneously at high quality
  • Training: A neural network is trained on these paired recordings, learning to predict the output for any given input. This typically takes 5-20 minutes depending on model complexity.
  • Validation: The trained model is tested against held-out audio to verify accuracy
NAM Flow Chart

Diagram of Neural Amp Modeler capture process.

The key advantage of NAM is its ability to capture complex nonlinear distortion, compression, and saturation characteristics that make amplifiers sound unique and respond naturally to playing dynamics.

Are you interested in capturing your gear?

You can capture your gear for free using Neural Amp Modeler on TONE3000. Create NAM captures to use privately or share with the community.

Why is NAM open source?

Neural Amp Modeler is open source to ensure the technology remains accessible, transparent, and continuously improving. Anyone can examine the code, contribute improvements, and build compatible products without licensing restrictions. This openness has created a thriving community of developers worldwide who collaborate to improve NAM's algorithms, optimize performance, and expand compatibility.

This open approach has also fostered a growing ecosystem of hardware and software companies that support NAM profiles. You're not trapped in a proprietary system or forced to pay subscription fees to access your own captures – you can load your favorite NAM profiles into a wide variety of plugins and hardware devices. The community can freely share profiles, and manufacturers can implement NAM support without negotiating licensing deals.

Perhaps most importantly, NAM will never disappear if one company goes out of business. The technology belongs to everyone, ensuring Neural Amp Modeler continues evolving for years to come through community innovation and collaboration.

How does NAM compare to traditional amp sims?

Neural Amp Modeler and traditional amp simulators take fundamentally different approaches to digital tone. Traditional amp modeling relies on hand-coded circuit simulations where engineering teams manually program the behavior of tubes, transformers, tone stacks, and power supplies based on electrical schematics. These component-level models require extensive development time and expertise to capture a single amplifier. NAM uses deep temporal convolutional networks to learn from recordings of real amplifiers, pedals and other gear rather than manual programming. This deep learning approach captures subtle nonlinear interactions and complex harmonic content that circuit modeling often misses.

The result is that NAM profiles often sound and feel more authentic, with better dynamic response and natural compression. Previously, you needed a team of DSP engineers and months of development to model one amplifier accurately. With Neural Amp Modeler, anyone can capture their gear in a few minutes and share it with the world, democratizing access to studio-quality tones.

What's the difference between NAM and IR's?

Neural Amp Modeler and Impulse Responses (IR's) capture different stages of your signal chain and work together to create complete authentic tone. NAM models the amplifier, preamp, and effects pedals – the nonlinear components that add distortion, compression, and tonal coloration. NAM captures how an amp responds dynamically to your playing, including gain staging, EQ curves, and touch sensitivity. Impulse Responses capture the speaker cabinet, microphone placement, and room acoustics – the linear acoustic environment that shapes your final sound. IR's handle the frequency response and spatial characteristics of cabinets and spaces.

For realistic guitar tone, you can chain both technologies to work in tandem: load a NAM profile to get the amp's character, then load an IR to get the cabinet's voice. For example, pair a NAM capture of a Marshall JCM800 head with a Greenback 4x12 IR, or combine a Fender Deluxe Reverb NAM profile with a Fender Spring Reverb Tank IR.

NAM Captures
Full Rigs (Amp Head + Cab) and Combos
Amp Heads
Pedals and Outboard Gear
IR Captures
Speaker Cabinets
Reverb
Room Acoustics

Important: If you're using a NAM capture of just an "Amp Head," you'll need to pair it with an IR to add the speaker cabinet. Without an IR, your tone will sound thin and harsh. NAM captures labeled "Full Rig / Combo" already include the speaker cabinet, so no separate IR is needed.

Beginner Tip: Start with "Full Rig / Combo" captures – they already include the speaker cabinet, so there's nothing else to configure.

What hardware and software supports NAM?

Neural Amp Modeler is supported by a rapidly expanding ecosystem of software developers and hardware manufacturers. This means you can load NAM captures into a wide variety of plugins, pedals, and even apps. Here's a complete list:

Why use TONE3000 for Neural Amp Modeler?

TONE3000 is the world's largest community for discovering, sharing, and creating Neural Amp Modeler profiles and impulse responses (IR's).

How do I get started playing with NAM?

Getting started with Neural Amp Modeler is easy and free. You can start by playing one of the thousands of free NAM profiles on TONE3000 and immediately hear how realistic and inspiring these tones sound.

First time? We created a helpful guide.

How do I capture my gear with NAM?

It’s easy and free to capture your gear on TONE3000. You can create NAM profiles directly on TONE3000 to use privately or share with the community.

TONE3000 Digital Models

NEW TO TONE3000?

Discover hyper-realistic digital models of iconic gear, including the Fender Twin Reverb, Vox AC30, Marshall JCM 800, and thousands more. Getting started is easy—and free!