On-Device Sound Event Logger Kit with ESP32 + LED
On-Device Sound Event Logger Kit with ESP32: Detect Glass Breaks, Barks, Sirens, and Speech with Edge 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.
From detecting a window shattering at 2 AM to monitoring urban soundscapes, this kit teaches you how to deploy a fully independent AI sound classifier on an ESP32-S3. It listens through an INMP441 I2S microphone, runs a custom Edge Impulse model to distinguish glass breaks, dog barks, sirens, and human speech, then logs each event with a precise timestamp onto an SD card—no cloud required. The included buzzer can trigger immediate local alerts.
What You'll Build
You'll assemble a self-contained weatherproof sound logging unit with an OLED display showing live classification results. The device runs on rechargeable 18650 batteries, stores events indefinitely on a removable microSD card, and alerts you with an onboard buzzer whenever a sound of interest is detected. Students and researchers can adapt this platform for wildlife monitoring, smart city noise pollution mapping, or home intrusion detection.
What You'll Learn
- Train a custom sound classification model in Edge Impulse and deploy it to an ESP32-S3 as a standalone application.
- Integrate an I2S digital microphone (INMP441) and handle real-time audio inference at the edge.
- Use an RTC (DS3231) to timestamp logged events and structure CSV data on an SD card.
- Manage power with a buck converter and 18650 cells for field-deployable battery-operated systems.
Kit Contents
| Component | Quantity |
|---|---|
| ESP32-S3 Dev Board | x1 |
| INMP441 I2S Mic | x1 |
| DS3231 RTC | x1 |
| MicroSD Module | x1 |
| 0.96in OLED | x1 |
| Active Buzzer | x1 |
| LM2596 Buck Converter | x1 |
| 18650 Cell | x2 |
| TP4056 Module | x1 |
| 100nF Caps | x10 |
| PCB Prototype Board | x2 |
| Waterproof Enclosure | x1 |
| Soldering Iron | x1 |
| Solder Wire | x1 |
Why Buy This Kit Instead of Sourcing Parts Separately
| Factor | Sourcing Separately | Compoden Kit |
|---|---|---|
| Compatibility checks | You verify every part | Pre-tested as a system |
| Build support | Forums and scattered tutorials | AI companion trained on this exact project |
| Time to first working build | Days of debugging | Hours, with step-by-step guidance |
| Shipping coordination | Multiple sellers, multiple delays | One shipment from Bengaluru in 3-5 days |
Who This Kit Is For
This kit is perfect for B.Tech ECE, EEE, and CSE students tackling final-year projects on edge AI, as well as Smart India Hackathon teams prototyping sound-based alert systems. It's also built for advanced hobbyists who want a deployable wildlife or urban noise monitor, and aligns with project requirements at IIT, NIT, VIT, and BITS Pilani. If you have prior Arduino experience and are ready to integrate ML model training with microcontroller programming, this kit bridges the gap with a real-world application.
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.
What if I get stuck during the build?
Your AI build companion, accessible via the QR code on the box, can walk you through wiring, code upload, and model integration. If you still need help, message us on WhatsApp — our engineers will reply within 4-6 hours.
Do I need to know Edge Impulse to use this kit?
Not beforehand. The companion provides a guided workflow to capture audio samples, train the model, and export the Arduino library. You'll learn the platform as you build.
Can I add more sound classes like baby crying or car alarm?
Absolutely. The ESP32-S3 has enough processing headroom to classify 5–7 sound categories. You can collect additional samples using the same INMP441 mic, retrain in Edge Impulse, and update the firmware via USB.
How long does the battery last in the field?
With two 18650 cells and the LM2596 buck converter set to 5V, the system runs for approximately 12–14 hours of continuous inference. You can extend this by enabling deep sleep between sound triggers, which we cover in the companion guide.
INMP441 mic + Edge Impulse sound classifier detects glass break, dog bark, siren, speech. Logs events to SD.
What's in this kit
Choose your assembly option:
- Soldering Kit — 25W soldering iron, 60/40 solder wire, flux, and small perfboard for permanent assembly.
- Breadboard Combo — 800-point full-size breadboard with 65-piece jumper wire pack for solderless prototyping.
Shipping Information
- Prepaid Orders: ₹75 for orders up to ₹999, FREE shipping above ₹999
- COD Orders: ₹125 shipping + ₹50 COD fee = ₹175 total
- Delivery Timeline: Dispatch in 1-2 days, delivery in 2-7 days depending on location
Returns & Warranty
- 7-Day Return: Manufacturing defects only (approval required)
- Warranty: 7 days from delivery
- Non-Returnable: Batteries, consumables, cut wires, clearance items