SlowPunch – Slowdown & Impact Enhancement Tool

SlowPunch is a standalone audio app designed for fast, creative impact and low-end enhancement. It allows you to: Adjust Playback Speed: Slow down or speed up audio with pitch following speed. Punch: Add rich, analogue-style impact and […]


Shine 4 – Harmonic Exciter

Shine 4 is a high-resolution harmonic exciter engineered for controlled spectral enhancement and precise harmonic generation. Featuring targeted excitation via stepped frequency control and four unique Exciter models, it allows you to move beyond broad […]


SlowShade – Slowdown & Tone Transformation Tool

SlowShade is a powerful standalone audio tool for creative sound design and detailed analysis. It allows you to: Adjust Playback Speed: Slow down or speed up audio with pitch following speed. Drive: Add rich, analogue warmth and […]


VelorX – Spatial Reverb

VelorX is a high-fidelity Algorithmic Reverb Processor designed to provide total spatial control through advanced visual feedback. Built around a precision dual-layer FFT engine and a real-time stereo correlation monitor, VelorX eliminates the guesswork of […]


Grav-LF – Bass Enhancement Tool

Grav-LF is a precision Bass Enhancement Processor built around a specialized dual-layer FFT analysis engine that monitors the critical 20 Hz to 1000 Hz frequency range in real time. Instead of adjusting the low-end blindly, […]


Krunx-Q – Digital Bitcrusher

Krunx-Q is a high-precision bitcrusher and sample rate reducer built around a dual-layer FFT analysis engine that monitors both input and output signals in real time. Instead of treating digital degradation as a simple destructive […]


Clipper 7 – Digital Clipper

Clipper 7 is a precision digital clipper built around a dual-layer FFT analysis engine that monitors both input and output signals in real time. Instead of relying solely on waveform-based shaping, Clipper 7 allows users […]


SlowWave – Slowed and Instant Reverb Tool

SlowWave is a creative slow-playback and reverb transformation tool that lets you stretch audio between 0.5x and 1.5x while shaping ambience with size and mix controls. It includes LR peak meters, stereo correlation, and dual-layer […]


Balance 5 – Parametric Equalizer

Balance 5 is a high-precision 5-band parametric equalizer designed for accurate tonal balancing, critical listening, and real-time visual feedback. The standalone version allows you to load and analyse audio files without the need for a […]


Spectra 99 – Spectrum Analyzer

Spectra 99 is designed for modern high-definition audio workflows and is fully optimized for sample rates up to 96 kHz, delivering precise and stable spectral analysis in both standard and high-resolution sessions. The standalone application […]


Audio AI Reading Notes

A curated list of papers and articles I’ve read recently, focused on neural audio, DSP, and music AI. Each entry includes the original source and my key takeaways. This page is being updated regularly. More […]


Transformer For Denoising

Although small datasets make denoising a challenging task, this experiment shows how transformer models can handle audio cleaning in a practical way. The idea is simple: can we teach a transformer — originally built for […]


Composing Without a DAW

Lately, I’ve been exploring ways to handle everything — notation, MIDI tweaks, and VST instruments — without switching to a DAW. Even with the free version of Dorico from Steinberg, I was surprised by how […]


Optimizer Comparision

Choosing the right optimizer is essential when training neural networks, especially for audio tasks like denoising or filter tuning. The optimizer controls how model parameters are updated, affecting convergence speed, stability, and final performance. A […]


SNR Maximization and Wiener Filtering

In digital audio processing, one of the most common tasks is reducing background noise while keeping the original signal as clear as possible. This balance is typically expressed as maximizing the Signal-to-Noise Ratio (SNR) — […]


Supervised Audio Denoising

What is a Supervised Model? A supervised model is a type of machine learning algorithm that learns to map inputs to known outputs using labelled data. The context of audio denoising consists of noisy audio […]


Cosine Similarity

Recently, I experimented with a quick way to measure how similar two audio tracks are — not by comparing raw waveforms, but by looking at their spectral patterns. Using PyTorch and Torchaudio, I load two […]


Denoising with Rectified Flow Models

This project trains a 1D convolutional neural network with time embeddings to remove noise from audio, inspired by Rectified Flow Models (RFM). What is a Rectified Flow Model? An RFM learns a velocity field that […]


HRTF Spatialization: Mono to Stereo

I took a plain mono audio file and transformed it into a stereo track that sounds like it’s coming from a real direction in space — using HRTF data from a SOFA file. HRTF (Head-Related […]


Neural Audio Fingerprinting

This is a basic implementation of neural audio fingerprinting using PyTorch and torchaudio. It serves as a solid foundation for tasks like music identification, audio search, and deep audio retrieval. CNN architecture, sample rate, and […]


1 2 3