ESP32 Sound Classification IoT Alert Kit: Detect Glass Break, Alarm & Baby Cry with AI

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

This kit transforms an ESP32-S3 into a smart sound monitor that recognises critical audio events — a window shattering, a smoke alarm, or a baby crying — and sends an instant alert to your phone via MQTT. Powered by Edge Impulse's on-device machine learning, it runs inference locally without cloud delay. In three to four hours, you'll have a working prototype ready for home safety, a hackathon demo, or a school project.

What You'll Build

You'll assemble a compact IoT device that listens for three distinct sound classes. When glass break, alarm, or baby cry is detected, the onboard red LEDs flash and the piezo buzzer sounds locally, while the class is published to an MQTT topic of your choice. Connect it to Node-RED, Home Assistant, or any MQTT dashboard to create push notifications, log events, or trigger other smart devices. The kit includes a pre-trained Edge Impulse model, so you'll see results immediately, then retrain with your own audio samples later.

What You'll Learn

• How to wire an I2S MEMS microphone (INMP441) to an ESP32-S3 for high-quality audio capture.
• Training a sound classification model in Edge Impulse Studio using spectrogram features.
• Deploying an Edge Impulse model to an ESP32-S3 and running continuous inference in Arduino IDE.
• Publishing detection results to an MQTT broker and reading them on a phone or web dashboard.

Kit Contents

Why Buy This Kit Instead of Sourcing Parts Separately

Who This Kit Is For

This kit is ideal for CBSE Class 11–12 students learning AI and IoT, B.Tech ECE/EEE undergraduates preparing for campus hackathons, ATL Tinkering Lab mentors seeking a working sound recognition demo, and anyone participating in Smart India Hackathon who needs a reliable Edge AI prototype with MQTT connectivity. It assumes no prior machine learning experience — Edge Impulse's graphical interface and the AI companion make the full workflow approachable.

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.