Tagged: transcription

October 29, 2026

FalconSDR: An Open-Source RTL-SDR Scanner and Recorder with Automatic Whisper Transcription

Thank you to Rafał for writing in and sharing his open-source project FalconSDR, a free scanning and recording program he's been working on over the last few months. Rafał notes that after getting into RTL-SDR listening, he found that popular SDR programs didn't have the scanning and recording features he wanted.

FalconSDR can scan multiple bands or channels, even when they are far apart, with separate settings for each band and a blacklist for skipping birdies and unwanted channels. A "recency boost" feature sends the scanner back to channels with recent activity, and it can record multiple transmissions at once. Recordings go into a searchable library and can optionally be transcribed to text with Whisper. In hybrid mode, a server handles recording and a PC handles transcription.

The interface runs in a browser, either locally or on a headless server, so you can reach it from a PC or phone on your network. RTL-SDRs are supported natively, and Rafał has tested the program for months with an RTL-SDR Blog V4. Other SDRs work via SoapySDR. Linux and Windows 11 have been tested, but the macOS builds are marked as experimental. The code is open source under GPLv3 and available on GitHub.

AI Disclaimer: While the author does not disclose it, the repository includes an AGENTS.md file described as "Guidance for AI coding agents working in this repository", so it is our opinion that this software may be coded with the help of AI.

December 29, 2025

RadioTranscriber: Real-Time Public Safety Radio Transcription with Whisper AI

Over in our new forums, user Nite has shared a new open-source project that he's created called RadioTranscriber, a real-time speech-to-text tool for public safety radio feeds using OpenAI’s Whisper large-v3 model. The idea is to take live scanner audio, such as authenticated streams from Broadcastify, and continuously turn it into readable text with minimal babysitting. The project grew out of earlier experiments with Radio Transcriptor, which we posted about back in June, but quickly evolved into a more robust, long-running setup with better audio conditioning and fewer of Whisper’s common hallucinations.

Under the hood, RadioTranscriber is a Python script that pulls in a live stream, cleans it up with filtering, normalization, and WebRTC VAD, then runs Whisper large-v3 with beam search for transcription. A set of custom “hallucination guards” strips out common junk text and replaces alert tones with simple markers, while daily log rotation and basic memory management let it run unattended for long periods, even on a modest CPU-only machine. Although it’s tuned to the author’s local dispatch style, the config and prompt are easy to adapt, and the full code is available on GitHub for anyone who wants to experiment or build on it.