The SIGINT MiniLab is a compact, modular, and mostly autonomous signal intelligence system designed to monitor, decode, and summarize local RF activity. Housed in a custom-built 8U server rack with a combination of 3D printed and commercial components, the system leverages SDR technology, edge AI inference, and centralized data orchestration to provide real-time situational awareness.
Core modules include:
-
Signal Capture: Raspberry Pi 4 units paired with RTL-SDR dongles for identifying and capturing voice and data transmissions across a range of frequencies.
-
Intelligence Inference: An NVIDIA Jetson Orin Nano Developer Kit for speech-to-text transcription, tone and intention analysis, and contextual tagging of intercepted signals.
-
Central Orchestration: A Dell 7050 Micro PC acting as the central controller, user interface host, and future server for mission-critical apps like ATAK.
This project aims to create a fully deployable system capable of monitoring police/fire dispatch, public safety networks, weather broadcasts, and more — all without requiring constant user supervision. Future goals include AI-driven event summarization, real-time map overlays, and off-grid operational capabilities.
Brett Erickson
Enrico Miglino
Ildar Rakhmatulin
Trond B.
Nice project, I built something very similar but I found whisper to have poor accuracy on noisy comms. Some fine tuning is probably required. Did you end up sticking with whisper?