Noise Pollution Logger Smart Kit – Build an Offline Wake Word Detector That Controls Real-World Devices

Every part needed, pre-tested for compatibility, with an AI build companion trained on this exact project. Shipped from Bengaluru in 3-5 days.

Imagine a library that self-polices chatter. Your device hears the phrase “Too loud,” triggers a warning light, and logs the event – all without sending a single byte to the cloud. This kit puts Espressif’s WakeNet neural network onto an ESP32-S3 and lets you define the exact wake word that activates a relay. It’s privacy-first voice automation built for school labs, community noise monitoring, and any environment where you need an offline acoustic sentinel.

What You'll Build

You’ll assemble a compact sound-triggered relay station. The I2S MEMS microphone captures ambient speech, the ESP32-S3 runs a custom wake word model locally, and when the recognized phrase is detected, the relay switches on your choice of load – an LED tower, a buzzer, or a data logger. Three onboard LEDs provide instant visual status. You’ll leave with a working prototype you can connect straight into a classroom quiet-time system or a Smart India Hackathon demo.

What You'll Learn

• Train and deploy a custom wake word using ESP-Skainet and the ESP32-S3’s neural network accelerator
• Interface an I2S MEMS microphone and process audio frames in real time
• Control a 5V relay safely with flyback diodes and transistor driver logic
• Design a breadboard layout that keeps analog mic signals and relay switching noise apart

Kit Contents

Why Buy This Kit Instead of Sourcing Parts Separately

Who This Kit Is For

CBSE Class 11–12 students tackling an environmental physics or computer science project will find a ready-to-extend base for noise pollution monitoring. B.Tech ECE/EEE learners at IITs, NITs, VIT, or BITS can use it to explore on-device machine learning and voice interfaces. It’s also ideal for ATL Tinkering Lab mentors and Smart India Hackathon teams that need a reliable, low-latency trigger mechanism without internet dependency.

Built and Backed by Compoden

Every Compoden kit ships with an AI build companion trained on this exact project — accessible via a QR code on the box, with WhatsApp and email backup. We’ve spent 10 years building projects for makers, schools, and institutions across India. If a part fails because of a manufacturing defect, replace it free within 7 days.