American-Built Acoustic Intelligence

Every sound tells a story.
We give operators vision via sound.

A throwable sensor that classifies hundreds of acoustic signatures — vehicles, personnel, weapons, aircraft, machinery, wildlife, weather — and delivers plain-English threat assessments to the operator's tablet in under one second. In total darkness. Through smoke. Under full-spectrum jamming.

See How It Works Operator Use Cases →
500+
Sound Classes
<1s
Alert to Operator
72hr
Persistent Overwatch
Zero
RF Signature
300m
Standoff Range
Acoustic Coverage
500+ sound classes. Every domain covered.

Built on the AudioSet taxonomy and extended with mission-specific signatures. The Puck doesn't listen for a handful of threats — it understands the entire acoustic environment.

500+
Classifiable Sound Types
From a tracked vehicle at 300 meters to a whispered conversation at 50. From a power line arcing before ignition to a bolt being cut on a perimeter fence. If it makes a sound, the Puck classifies it.
🚛

Ground Vehicles

Wheeled, tracked, engine type, speed estimation, approach vs. departure

✈️

Aerial Threats

Fixed-wing, multirotor, jet, propeller, including RF-silent platforms

🚶

Human Activity

Footsteps, speech, tools, digging, fence cutting, glass breaking

💥

Weapons & Ordnance

Gunshots, explosions, mortar launch, ricochet, caliber classification

Infrastructure

Arcing faults, transformer hum, pipe stress, structural cracking

🌧️

Environmental Baseline

Wind, rain, wildlife, machinery — auto-profiled and suppressed from alerts

The PerimeterAI Advantage
Six capabilities no other sensor on Earth combines

Each exists in isolation somewhere. No deployed system delivers all six. That's the gap we close.

01

Fully Passive — Zero Emissions

The Puck emits nothing. No RF, no IR, no acoustic output. It cannot be detected, targeted, jammed, or spoofed. Total electromagnetic silence in contested threat terrain.

02

On-Device AI — Comms-Denied Ready

Two layers of AI run entirely on the sensor. Classification, reasoning, and alerting at the edge. When comms are denied, the Puck doesn't degrade — it was designed for that condition.

03

500+-Class Acoustic Awareness

Not a narrow signature library. Full-spectrum acoustic classification across vehicles, aircraft, personnel, weapons, infrastructure, and environment. One sensor replaces an entire stack.

04

Plain-English Operator Alerts

Not a code. Not a beep. An on-device LLM writes bearing, range, threat class, and confidence in natural language. Operators act on words, not waveforms.

05

Throw-and-Forget Deployment

Hockey-puck form factor. Battery-powered. 72 hours persistent overwatch. A team deploys a dozen across a square mile in minutes — no setup, no calibration, no babysitting.

06

Self-Healing Sensor Mesh

Multiple pucks cross-reference bearings to triangulate threats in 3D. If a node goes down, the mesh adapts. If comms drop, detections cache locally. Resilient by architecture.

The Threat Gap
Current systems fail where operators need them most
Acoustic Towers

Chained to the grid

Permanent power, hardwired comms, remote server processing. No infrastructure, no capability. Useless forward of the wire.

Pattern Matchers

Can't adapt. Can't explain.

Static signature libraries with a handful of preprogrammed sounds. Can't identify novel threats. Output a raw code an operator can't act on without an analyst in the loop.

RF-Based Sensors

Blind to passive threats

Intercept radio signals only. Completely blind to fiber-optic munitions, dismounted personnel, vehicles running silent, gunfire, fence breaches, and every non-emitting threat class.

Cloud AI Systems

Denied when denied

Push data to a remote server. Seconds to minutes of latency. Fail completely under jamming — the exact condition where threat detection is life or death.

Every current approach demands infrastructure, connectivity, or analysts at scale. In contested terrain, operators have none of the above.
How It Works
Distributed mesh detection + 3D triangulation

Each Puck classifies hundreds of sound types independently. When multiple nodes detect the same event, the mesh triangulates and delivers a fused threat picture to the operator.

Live Mesh — 7 Nodes · 3 Threats Tracked
Sector 7 South · 0.8 mi²
PERIMETER BOUNDARY PUCK-01 PUCK-02 PUCK-03 PUCK-04 PUCK-05 PUCK-06 PUCK-07 ⚠ WHEELED VEHICLEBRG 062° · 210m · HIGH ⚠ DISMOUNTED ×2BRG 215° · 95m · MED ⚠ GUNSHOTBRG 118° · 260m · HIGH OPERATOR TABLET ⚠ HIGH — Wheeled vehicle ⚠ HIGH — Gunshot detected ⚠ MED — Dismounted ×2 ✓ 247 other classes: nominal
Puck Node
High Threat
Medium Threat
Gunshot Event
Mesh Healthy
The Platform
The Perimeter AI Puck

Two layers of on-device intelligence. Entirely passive. Entirely autonomous. Hundreds of classifiable sounds. Built for conditions where everything else fails.

Acoustic
Sensor
Array
Hockey Puck
Form Factor
72 Hours
Persistent Overwatch
100–300m
Standoff Range
500+
Sound Classes
Zero RF
Signature
<50ms
Classification
Layer 1 — 90% of Events · <50ms

Neural Classifier — Instant Threat ID

A quantized neural network classifies 500+ sound types on-device in under 50 milliseconds. Vehicles, aircraft, personnel, weapons, machinery, wildlife, weather — the full acoustic environment, profiled and assessed before the echo fades.

Layer 2 — 10% of Events · <2s

On-Device LLM — Tactical Reasoning

When the classifier encounters ambiguity — overlapping sources, novel signatures, environmental masking — a compressed LLM reasons over the full acoustic context and writes a plain-English alert with bearing, range, assessment, and confidence. No analyst. No network.

Multi-Puck · Autonomous Mesh

Self-Healing Listening Web

Multiple pucks cross-reference direction-of-arrival bearings to triangulate sources in 3D. The mesh tracks vehicles, personnel, weapons fire, and aircraft simultaneously. Nodes that lose connectivity cache locally and sync on reconnect.

Built for Operators
From SOF teams to law enforcement — one platform
⚔️

Forward-Deployed & SOF

Detect approaching vehicles, dismounted patrols, weapons fire, and aerial threats — including RF-silent platforms — and push bearing + range to the operator's tablet in under one second. Works in total darkness, through smoke, under jamming.

Full-spectrum acoustic overwatch in comms-denied terrain.
🛡️

Base & Perimeter Security

Replace 24/7 manned observation with 72-hour autonomous acoustic overwatch. Track vehicles, personnel, fence breaches, and gunfire across the perimeter. Only confirmed events reach the operator — zero false-alarm fatigue.

72hr autonomous overwatch. Zero manned observation hours.
🚔

Law Enforcement & Infrastructure

Gunshot detection and localization for urban environments. Perimeter breach detection for critical facilities. Arcing fault detection for power infrastructure — hours before ignition. One mesh covers every acoustic threat domain.

Gunshots, intrusions, infrastructure faults — one sensor mesh.
🇺🇸

Designed, engineered, and manufactured in the United States

PerimeterAI is an American company building American technology for American operators and allied forces. Our AI models are trained on domestically collected data. Our hardware is assembled in the U.S. Zero foreign dependency for critical components. No foreign cloud. No foreign code. No foreign access — ever.

PerimeterAI
The first passive, autonomous acoustic defense layer for contested terrain.

No cameras. No RF. No cloud. No analysts. Just sound — and the intelligence to turn it into operator advantage.

Request a BriefContact Our Team →