A Czech AI startup claims to be able to detect drones at a cost of €150 per sensor, and wants to install electric grids first.
The TL;DR
Czech startup Neuron Soundware developed Sound Shield, an AI acoustic drone detection system using €100-150 sensors that consume 1W each.
Czech startup Neuron Soundware has built an AI-powered acoustic detection system called Sound Shield that identifies drones by the sound of their engines using microphone sensors that cost between €100 and €150 each. The system is designed as a passive, low-cost radar replacement for low-flying drones over cities, infrastructure, and military installations. The company, which has spent the past ten years using AI to listen to industrial equipment for customers including Airbus, Siemens, and BMW, is now using the same acoustic analysis technology to protect the airspace.
The Sound Shield works by installing tiny sensors called nEdge Minis, each consuming only one watt of power, that continuously listen for the signatures of the drone’s engine. The sensors report to a computing platform powered by Nvidia’s Jetson modules, which use the device’s neural networks to match incoming sound against a known library of drone acoustic profiles. When the system detects a threat, it alerts the central command platform with the drone’s estimated speed, altitude, and direction of travel.
This method exploits the basic limitation of drone construction. Radar-absorbing clothing and a stealthy design can make the drone nearly invisible to conventional detection systems, but no current technology can silence the noise of the rotors and engines. Every drone produces a unique acoustic signature, according to Neuron Soundware, whose AI can pinpoint in real time all the positions of multiple sensors.
TNW City Coworking Space – Where your best work happens
A workplace designed for growth, collaboration, and endless networking opportunities at the heart of technology.
Pavel Konečný, founder and CEO of Neuron Soundware, pitches Sound Shield as a dual-use system that would initially be used in power conversion stations. “Basically, they can continuously monitor the life of the transformer itself and other important parts of the distribution network, to detect internal leakage, oil leakage, or other operational disturbances,” said Konečný.At the same time, their microphones listen to the sky.“
The dual use angle is important for trade. Instead of asking governments to fund an autonomous drone detection network from scratch, Neuron Soundware proposes to retrofit the infrastructure that already requires acoustic deployment. The company says this will reduce the number of sensors needed and provide governments with a deeper layer of air defense with less additional installation and power costs.
European governments are seeking affordable drone adoption after the wars in Ukraine and Iran have shown that cheap UAVs can destroy billions of dollars in military equipment. Ukraine’s Operation Spiderweb in June 2025 used $2,000 worth of drones to destroy an estimated $7 billion worth of Russian strategic bombs, according to Ukrainian officials, although Russia claimed heavy losses. The asymmetry between drone costs and the damage they cause has made counter-drone systems one of the fastest growing segments of defense procurement.
The counter-drone market is expected to more than triple from about $6.6 billion in 2025 to $20 billion in 2030. Startups across Europe are raising money to build strong anti-drone capabilities, and NATO members on Russia’s border have agreed to build a drone detection wall from Norway to Poland. The Sound Shield positions itself as a complementary layer to radar and radio frequency detection rather than a replacement.
The economic case is straightforward. Modern radar systems capable of detecting small drones are orders of magnitude larger than the nEdge Minis network, and actively broadcast their location every time they sweep. Sound Shield sensors are passive, meaning they do not emit signals that can be picked up by an enemy or jammed.
The trade-off is distance and reliability.
Acoustic drone detection has well-documented limitations that the source material does not address. Most acoustic systems work well for about 300-500 meters under favorable conditions, with performance greatly degraded in wind, rain, or noisy urban environments. Ambient noise from traffic, wildlife, and industrial machinery can be misleading.
Newer drone models are also designed with quieter motors that reduce the acoustic signature available for detection. Neuron Soundware claims its nEdge PRO computing module can integrate data from sensors within a 20-kilometer radius, but independent testing of that claim range has not yet been published.
The company has raised approximately 7.4 million euros to date from investors including Inven Capital, J&T Ventures, and Lead Ventures, and received 7 million euros from the European Innovation Council. It has more than 130 industrial installations on all four continents for acoustic monitoring equipment. Whether the jump from eavesdropping on pumps and air engines to tracking hostile drones in contested airspace can be carried over as the company suggests remains to be proven in real-world situations.
