AI & ML

A million-tap linear-phase FIR in real time: 7 ms of plumbing, 650 ms of filter

I'm building Sonir Bench, a macOS app that captures everything your Mac plays, runs it through a DSP chain you design, and sends it to your DAC. The…

VASTAdTagURI in a DAAST Wrapper Validates as XML. Audio Players Read DAASTAdTagURI.

The podcast stitcher logs a VAST-style no-fill. Finance sees the deal as delivered in the ad server. The XML attachment in the ticket is a <DAAST…

Building the Capsize Audio Visualizer with C++ and Qt

I keep coming back to the Capsize Audio Visualizer because it is small enough to finish. It is a C++ and Qt desktop application that turns live audi…

WXRQ turned a production kit into a radio station

I started WXRQ as a new repository for an automated radio and television station. Within a few days it had a public player, a schedule and a product…

How Does Call Noise Reduction Work on a Single-Microphone Phone?

On a phone with a single microphone, call noise reduction cannot work the way it does on flagship smartphones. There is no second microphone signal…

Every sound in my browser game is a few lines of Web Audio (no files)

I have been building a browser board game ( Samudra Manthana , an asymmetric strategy game), and when it came time to add sound, the usual route was…

Designing a 5-band parametric EQ from the biquad up, in MATLAB

A build log on a 5-band parametric equalizer written entirely in MATLAB: the filter design in detail, the pole-zero reading that tells you what a fi…

PL Education in the Age of AI: Interview with Shriram Krishnamurthi

How we made a MIDI controller run our browser radio studio

A live radio screen is fine until the host has to do three things at once. The mouse becomes the wrong tool the moment you need to open a mic, pull…

Creating sound with gestural harmony: AethericGeometry

A build log on Aetheric Geometry, a musical instrument you play with your bare hands in front of a webcam. The first half is how hand geometry becom…

Building a 5.1ch Surround Upmixer GUI with Python & FFmpeg

Building a 5.1ch Surround Upmixer GUI with Python & FFmpeg Ever wanted to watch a movie or listen to live music with true surround sound, but on…

Don't Send Every Audio File Straight to the AI Model

An audio file can pass every technical checkpoint and still produce a bad AI result. The upload completes. The decoder opens it. The model returns a…

Designing a Step-Sequencer UI That Survives Real-World Use

Most walkthroughs about browser-based rhythm tools focus on the musician's side: where to click, how to lay down a beat, what tempo sounds good. Thi…

Reverse Audio at Scale: A Debugging Playbook for Engineers Who Hate Surprise Sibilance

Picture the bug report: a track plays fine in the mix bus, but the moment it runs backwards, the vocalist sounds like a kettle whistle. The waveform…

Fixing Low USB-C Audio on Fedora Linux: My Battle with the Razer Leviathan

TL;DR: If you have a Razer Leviathan connected via USB-C on Linux and the volume is incredibly quiet even at 100%, PipeWire is likely crushing your…

Supplier Invoice Speech-to-Text: EU Startup Validation Beyond Per-Minute Pricing

Short answer: the cheapest speech-to-text API for an EU startup is the candidate that passes your invoice-field accuracy gate at the lowest normaliz…

Автоухо ставил «поломку» в 71% случаев. Я грешил на дешёвые телефоны, но проблемой оказалась тишина

Сервис диагностики двигателей автомобилей по звуку ставил «поломку» в 71% случаев. Я грешил на дешёвые телефоны, но проблемой оказалась тишина Если…

How I record system audio on macOS without a virtual driver

Recording your own microphone on a Mac is a solved problem. Recording the other person — the voice coming out of your speakers — is where macOS quie…

Multi-Voice Audiobooks: The Character Attribution Problem

Turning a novel into a multi-voice audiobook sounds like a TTS problem. It is mostly a parsing problem, and the parsing is harder than the synthesis…

Going Below Android's Volume Floor: DynamicsProcessing, LoudnessEnhancer, and Reproducible F-Droid Builds

Android's volume slider has a floor, and on a lot of devices that floor is louder than it should be. The first step above mute is a fixed fraction o…

Can YAMNet Detect Unseen Sudden Sounds in Real Time? A 48-Stream Evaluation

Hello, everyone. There are many situations where we may want to monitor sounds that happen without warning, such as breaking glass or a car horn. Re…

Transcribe Audio to Text Like a Developer: From File to Final Text

You've got a two-hour architecture review sitting in your Downloads folder. Last month, mine was a 94-minute mess where three engineers talked over…

How to Transcribe Audio to Text: A Practical Workflow for Developers

You've got a 45-minute meeting recording sitting on your desktop. Maybe it's a podcast raw file, or an interview you did for a project. You need it…

Half-Time vs Double-Time BPM Detection: How We Fixed Spotify's Known Accuracy Gap

Run Blinding Lights by The Weeknd through Essentia's RhythmExtractor2013 . It returns 85.4 BPM. The track is famously 171 BPM — one of the most-play…

Build a Voice Assistant with Python and Whisper

Build a Voice Assistant with Python and Whisper Imagine hearing your computer whisper back a response to your question, not through a robotic script…

FFmpeg dynaudnorm Filter: Dynamic Audio Normalization Guide

Originally published at ffmpeg-micro.com You're editing together clips from three different recording sessions, and every cut brings a jarring volum…

Emotions on a cloned voice: a 25 MB graft, a steering vector, and a lot of dead ends

Part of qwen3-tts — a pure C inference engine for Qwen3-TTS. TL;DR Qwen3-TTS ships 9 neutral preset speakers. No emotion control, and cloning a voic…

Stegachirp: Hide Messages in Audio Files Using Pure Python (No NumPy, No SciPy)

Hide a Message in a WAV File With Pure Python (No NumPy, No FFT) I built stegachirp because I wanted to send a short secret message inside an audio…

Tagging Environmental Sounds with YAMNet TFLite: An ESC-50 Evaluation over 2,000 Clips

Hello, everyone. Today is Tanabata in Japan. Events like Tanabata, summer dance festivals, and Christmas all seem to have their own sound images. Th…

Classifying Environmental Sounds with CLAP and ONNX Runtime: A 1-NN Evaluation on ESC-50

Hello, everyone. When people hear an animal call or keyboard typing, they can infer something about the source and setting. If we turn those sounds…