Beep Locator: Claude Code finds a hidden beep within 40cm
Aktualisiert
Symbolbild
The beep in the box room
Simon Willison had a box room full of unpacked boxes. A couple of weeks ago, something in that room started beeping at intervals. The gaps between beeps were long enough that standing there and listening was frustrating, and he didn't want to dig through every box. So he had Claude Code build Beep Locator, a software system for triangulating the source of a mysterious beep using multiple devices scattered around the room. The setup runs a Python web server for the main interface. You connect spare devices as listeners by scanning a QR code or opening a URL.
How the listeners work together
Willison used two iPads, a phone, a MacBook Pro and a Surface Ultra as listeners. The devices play noises to each other to estimate their locations. That didn't work particularly well, so he added a Rough mode: you drag device icons around the space to give rough positions, which are then adjusted based on the sounds. Each listener records a 60 second buffer of recent audio and runs a simple beep detection algorithm using Fast Fourier Transform and a high-pass filter. When a beep is reported, the server has one device play a short chirp, then asks every listener to upload a clip from about 0.6s before the beep to 0.8s after the chirp.
Testing with claps and confirming the beep
Willison added a clapping mode so he could test the system by clapping in different spots around the room. Those claps show up as diamonds on the map, which helped him gain confidence that it could locate a sound. Beeps appear on the map as an X, plus a line in the “Sounds located” log. You can replay the sounds from each device in turn to confirm they are the mysterious beep, then click “This is the mystery beep” to mark them. Once the frequency is confirmed, the system listens for it, measures the interval between beeps, and uses the triangulated locations to narrow down the most likely spot on the map.
The result: a detector that needed batteries
The system worked as intended. It gave Willison the position of the beep to within about 40cm. He then dug through that specific pile of boxes and found an ancient carbon monoxide detector that wanted its batteries replaced. The build leans on BeepBeep, a 2007 paper by Chunyi Peng, Guobin Shen, Yongguang Zhang, Yanlin Li and Kun Tan on acoustic-based ranging and localization using commodity devices. Willison describes the paper's approach as exactly what the project needed. The paper's method combines two-way sensing, self-recording and sample counting to reach high accuracy.
What it takes to try this yourself
Beep Locator is a Python web application server that does most of the work. Listening devices connect to it over WebSockets and show a UI that requests browser microphone access. You need several spare devices with browsers and microphones to act as listeners, plus a way to run the Python server.
The rough positions you drag onto the map help the system adjust, and the chirp exchange lets it align the uploaded clips. Willison's account doesn't include a public release, pricing or setup instructions beyond the server and listener flow. If you have a beeping box room, the practical takeaway is that the approach needs multiple devices and a little manual placement before it can point you to the right pile.
Affiliate-Links: Für qualifizierte Käufe können wir eine Provision erhalten, sie ändert weder unsere Daten noch die Rankings. Sie öffnen die Suchergebnisse von Amazon: Preise und Verfügbarkeit stehen dort.