Czech AI startup detects drones via sound at €150 per sensor, targets power grids

Czech startup Neuron Soundware has developed an AI-driven acoustic detection system called Sound Shield, capable of identifying drones by the sound of their engines using sensors that cost between €100 and €150 each. The system offers a passive, low-cost alternative to radar for detecting low-flying drones over urban areas, critical infrastructure, and military sites. For the past decade, the company has applied artificial intelligence to listen to industrial machinery for clients like Airbus, Siemens, and BMW. Now, it is adapting that same acoustic analysis technology for airspace defense.

Sound Shield relies on small sensors known as nEdge Minis, each consuming just 1 watt of power, which continuously listen for drone engine signatures. These sensors feed data to a computing platform powered by Nvidia’s Jetson modules, where on-device neural networks match incoming audio against a library of known drone acoustic profiles. When a threat is identified, the system alerts a centralized command platform with the drone’s estimated speed, altitude, and direction of movement.

The approach exploits a core weakness in drone design. While radar-absorbing coatings and stealth shaping can make a drone nearly invisible to traditional detection systems, no current technology can silence the mechanical noise of rotors and engines. Every drone produces a distinct acoustic signature that, according to Neuron Soundware, its AI can identify in real time across multiple sensor positions.

Founder and CEO Pavel Konečný is positioning Sound Shield as a dual-use system, with initial deployment planned for electrical transformer stations. “Primarily, they can continuously monitor the health of the transformer itself and other critical components of the distribution network, detecting internal discharges, oil leaks, or other operational anomalies,” Konečný said. “At the same time, their microphones listen to the sky.”

This dual-use strategy has commercial appeal. Instead of asking governments to fund a standalone drone detection network from scratch, Neuron Soundware proposes piggybacking on infrastructure that already requires acoustic monitoring. The company argues this reduces the number of sensors needed and provides governments with a comprehensive air defense layer at minimal extra installation and power costs.

European governments are urgently seeking affordable drone detection solutions, following the wars in Ukraine and Iran, where cheap UAVs destroyed billions of dollars in military hardware. Ukraine’s Operation Spiderweb in June 2025 reportedly used $2,000 drones to destroy an estimated $7 billion worth of Russian strategic bombers, according to Ukrainian officials, although Russia claimed far lower losses. The stark asymmetry between drone cost and the damage they inflict has made counter-drone systems one of the fastest-growing segments of defense procurement.

The counter-drone market is projected to more than triple from roughly $6.6 billion in 2025 to $20 billion by 2030. Startups across Europe are raising capital to build sovereign counter-drone capabilities, and NATO members along Russia’s border have agreed to construct a drone detection wall stretching from Norway to Poland. Sound Shield positions itself as a complementary layer to radar and radio-frequency detection, rather than a replacement.

The economic argument is straightforward. Modern radar systems capable of detecting small drones cost orders of magnitude more than a network of nEdge Minis, and they actively broadcast their position with every sweep. Sound Shield’s sensors are passive, emitting no signal that an adversary could detect or jam.

The trade-off is range and reliability.

Acoustic drone detection has well-documented limitations. Most acoustic systems are effective to roughly 300 to 500 metres under favorable conditions, with performance degrading substantially in wind, rain, or noisy urban environments. Ambient noise from traffic, wildlife, and industrial equipment can generate false positives. Newer drone models are also being designed with quieter motors that reduce the acoustic signature available for detection. Neuron Soundware claims its nEdge PRO computing module can aggregate data from sensors within a 20-kilometre radius, but independent testing of that range claim has not been published.

The company has raised approximately €7.4 million from investors including Inven Capital, J&T Ventures, and Lead Ventures, and received €7 million from the European Innovation Council. It operates more than 130 industrial installations across four continents, monitoring machines acoustically. Whether the jump from listening to pumps and turbines to tracking hostile drones in contested airspace is as transferable as the company suggests remains to be proven in real-world conditions.