Reforge Audio Engine

Most focus and sleep apps ship pre-recorded audio loops downloaded from stock libraries. The same rain sound you hear in one app is the same file sold to dozens of others. It loops. It repeats. It wasn't made for you.

Ebbi is different. We built our own audio engine, called Reforge, specifically for this app. It powers every soundscape you hear. Some sounds are generated entirely on your device from mathematical equations, with no audio files and no internet required. Others are engineered from real-world acoustic analysis, reconstructed from their mathematical structure rather than copied from a recording.

Reforge isn't a feature we bolted on. It's the foundation the app is built on.

1. Researched

Every sound in Ebbi was selected based on peer-reviewed research on ADHD, cognition, and psychoacoustics. White noise has a meta-analysis of 13 ADHD studies behind it. Lo-fi music has direct evidence showing fewer errors during cognitive tasks. Even silence is included because the research shows not every ADHD brain benefits from noise. Nothing is in the app without a reason, and every reason is documented with citations.

See the full research for every sound →

2. Engineered

Reforge analyzes real-world recordings and extracts their complete acoustic structure: every frequency, every amplitude change, every timing relationship. From that analysis, it builds a mathematical blueprint of the sound. That blueprint is what powers the audio you hear, not the original recording.

For core sounds like noise colors and rain, the math runs in real time on your device. Your phone's processor generates every sample from equations. No files. No downloads. No streaming.

3. Verified

This is where Reforge does something no other audio app does.

Every sound is tested using audio classification technology trained on large-scale real-world audio datasets. The system generates a sound, then asks: does this actually sound like what it's supposed to be? A generated rain sound is run through the classifier. If it doesn't pass as rain, it doesn't ship.

This isn't a subjective judgment call. It's a measurable, repeatable verification against real-world acoustic profiles. The generated audio is also compared against reference recordings across multiple frequency bands spanning the full audible spectrum, to ensure the spectral character matches.

Only after passing automated verification AND human listening approval does a sound make it into the app.

• Sounds selected for your brain. Not a generic relaxation playlist. Every sound is chosen because research suggests it helps ADHD focus specifically.
• Sounds that work offline. Core soundscapes are generated on your device. No internet, no streaming, no interruptions during a focus session.
• Sounds that were actually tested. Not just mixed by a sound designer and shipped. Every sound passed automated acoustic verification against real-world references before it reached your phone.
• Built in-house. Not licensed. Reforge was developed by Forge Hut LLC specifically for Ebbi. It's not a third-party plugin or a stock audio library. It's ours, and it's patent pending.

The verification system uses machine learning models originally designed to identify sounds in the real world. We repurposed them as a quality gate for engineered audio: instead of asking "what is this sound?" we ask "does this generated sound match what it's supposed to be?" This approach, using audio classification as a verification step for synthesized output, is novel and is covered by our pending patent.

The spectral comparison system evaluates generated audio across seven frequency bands (sub-bass through air) and measures timbral character, spectral shape, and dynamic behavior against reference recordings. Composite scores above defined thresholds are required before a sound is approved.

For the research behind each individual sound, visit the Science page.