Wake Word + Cloud LLM Voice Assistant
Arduino UNO Q Wake Word Voice Assistant Kit — Cloud LLM Powered with Gemini
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 device that springs to life when you speak a pre-configured wake word, captures your question, and answers using one of the world's most advanced large language models. This kit teaches you to build exactly that — a compact voice assistant powered by on-device wake word detection and the Gemini API, all on an Arduino UNO Q. Perfect for prototyping intelligent voice interfaces for home automation, accessibility aids, or hackathon demos.
What You'll Build
You'll assemble a standalone unit that listens continuously via an I2S digital microphone. When it hears your custom wake word, it records the following phrase, sends the audio to Google's Gemini cloud LLM, then speaks the response aloud through an amplified speaker. The finished board is a self-contained voice agent with no external computer required — ideal for edge AI experiments.
What You'll Learn
- Configure and wire an INMP441 I2S microphone for low‑latency wake word detection on Arduino
- Integrate the Gemini API to process spoken queries and return intelligent, contextual answers
- Drive a PAM8403 amplifier and 3W speaker to deliver clear text‑to‑speech output
- Solder surface‑mount and through‑hole components onto a PCB prototype board to create a robust final assembly
Kit Contents
| Component | Quantity |
|---|---|
| Arduino UNO Q | x1 |
| INMP441 I2S Mic | x1 |
| PAM8403 Amp | x1 |
| 3W 8Ω Speaker | x1 |
| 4.7kΩ Resistors | x5 |
| 100nF Caps | x5 |
| PCB Prototype Board | x1 |
| USB-C Hub | x1 |
| 5V 3A PSU | 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
B.Tech ECE and EEE students who want a hands‑on project that merges embedded systems with modern cloud AI. Hackathon teams preparing for Smart India Hackathon or similar events will appreciate the ready‑to‑integrate wake‑word pipeline. Makers familiar with Arduino basics ready to push into voice‑first design — this kit bridges the gap between microcontroller projects and AI‑driven interaction.
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?
Scan the QR code to access an AI assistant that knows every connection and code block for this kit. If you need human help, message us on WhatsApp — we respond within a few hours.
Do I need a separate computer like Raspberry Pi to run the language model?
No. All processing happens on the Arduino UNO Q, which connects to Wi‑Fi and calls the Gemini API directly. The cloud handles the heavy LLM inference.
Can I change the wake word later?
Yes. The included WakeNet model can be retrained using a simple script we provide. You can pick any short phrase that suits your application.
What if my Gemini API quota runs out?
You can generate a new API key from Google Cloud Console. The kit instructions guide you through updating the key in the firmware.
WakeNet on STM32 triggers Linux MPU to record and send audio to Gemini API. Response read via TTS speaker.
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