AI-Powered Home Automation Using Voice and Face Recognition

🏠 AI-Powered Home Automation Using Voice & Face Recognition (ESP32 + Agentic IoT + n8n + Telegram + Google Sheets + ThingSpeak)

🏠 AI-Powered Home Automation Using Voice & Face Recognition (ESP32 + Agentic IoT + n8n + Telegram + Google Sheets + ThingSpeak) 1. 📌 Project Overview This project builds a smart home automation system using: ESP32 AI-based decision layer (agentic IoT logic) Workflow automation using n8n Real-time alerts via Telegram Cloud logging in Google Sheets IoT visualization in ThingSpeak Voice + Face recognition (AI layer on mobile/cloud/edge) 🎯 Core Idea: Your home devices (lights, fans, door lock, sensors) are controlled by ESP32, while AI + n8n + Telegram act as the brain for automation, alerts, and analytics. 2. 🧩 System Architecture 🔄 Flow: Sensors → ESP32 collects data ESP32 → sends data to ThingSpeak / Webhook n8n workflow → processes data AI Agent → makes decisions Telegram → sends voice/text alerts Google Sheets → logs all activity User → controls system via voice/face commands 3. 🧰 Components List Hardware: ESP32 Dev Board Relay Module (2/4 channel) PIR Motion Sensor DHT11/DHT22 (Temperature & Humidity) LDR (Light Sensor) Camera module (for face recognition) Buzzer / LED indicators Power supply (5V) Software: ESP32 firmware (Arduino IDE / PlatformIO) n8n ThingSpeak Google Sheets Telegram bot Python (AI voice + face recognition) OpenCV / Face Recognition library Google Text-to-Speech (for voice alerts) 4. ⚡ Circuit Schematic (Explanation) ESP32 connections: Component ESP32 Pin Relay IN1 GPIO 26 Relay IN2 GPIO 27 PIR Sensor GPIO 14 DHT11 GPIO 4 LDR (Analog) GPIO 34 Buzzer GPIO 25 Camera Module: Connected via ESP32-CAM or external AI module 5. 🔁 System Flowchart Start ↓ ESP32 reads sensors ↓ Send data to ThingSpeak / Webhook ↓ n8n workflow triggered ↓ AI Agent processes data ↓ Decision: ├── Normal → Log to Google Sheets ├── Alert → Send Telegram message ├── Critical → Voice alert + automation ON/OFF ↓ User feedback received ↓ Action executed on ESP32 6. 💻 ESP32 Source Code (Basic Example) #include #include #include "DHT.h" #define DHTPIN 4 #define DHTTYPE DHT11 DHT dht(DHTPIN, DHTTYPE); const char* ssid = "YOUR_WIFI"; const char* password = "YOUR_PASS"; void setup() { Serial.begin(115200); WiFi.begin(ssid, password); dht.begin(); pinMode(26, OUTPUT); // Relay } void loop() { float temp = dht.readTemperature(); float hum = dht.readHumidity(); Serial.println(temp); if (WiFi.status() == WL_CONNECTED) { HTTPClient http; String url = "https://api.thingspeak.com/update?api_key=YOUR_KEY&field1=" + String(temp); http.begin(url); http.GET(); http.end(); } delay(5000); } 7. ⚙️ n8n Workflow Setup Steps: Open n8n Create new workflow Nodes: 1. Webhook Node Receives ESP32 / ThingSpeak data 2. Function Node (AI Logic) if (items[0].json.temp > 35) { return [{ alert: "HIGH TEMP" }]; } return [{ alert: "NORMAL" }]; 3. Telegram Node Send alert message 4. Google Sheets Node Append row (logs data) 5. HTTP Request Node Send command back to ESP32 8. 🤖 Telegram Bot Setup Steps: Open Telegram Search BotFather Create bot Get API token Use in n8n: Connect bot token Configure chat ID Enable: Text alerts Voice messages (TTS) 9. 📊 Google Sheets Integration Structure: Time Temperature Humidity Status Action n8n does: Append row every event Maintain historical analytics 10. ☁️ ThingSpeak Setup Steps: Create channel Add fields: Temperature Humidity Motion Copy API key ESP32 sends data every 10 sec 11. 🧠 AI Power Consumption Prediction Logic Logic idea: if temp > 30 and motion == 1: power_usage = "HIGH" elif temp < 25: power_usage = "LOW" else: power_usage = "MEDIUM" Advanced AI upgrade: Use regression model: Input: temperature, motion, time Output: predicted energy usage 12. 🔊 Voice Notification System Workflow: Event triggers in n8n Text converted to speech Sent via Telegram voice message Example: “Warning! High temperature detected in living room.” 13. 📷 Face Recognition System Process: ESP32-CAM captures image Python/OpenCV processes face Compare with stored dataset Decision: Known user → Unlock door Unknown → Alert sent 14. 🚨 Automation Logic Examples Condition Action Motion detected Turn ON light Temp > 35°C Fan ON Unknown face Send Telegram alert No motion Turn OFF devices 15. 🔌 ESP32 ↔ n8n Communication Two methods: Method 1: Webhook (Recommended) ESP32 sends HTTP POST to n8n Method 2: ThingSpeak polling n8n fetches data periodically 16. 📈 Dashboard Setup In ThingSpeak: Live graphs: Temperature Humidity Motion Historical trends Export CSV 17. 🚀 Future Enhancements AI upgrades: Full edge AI on ESP32-S3 Voice assistant integration Emotion detection via camera Predictive maintenance AI IoT upgrades: Smart energy billing Solar energy integration MQTT-based scalable architecture Automation upgrades: Multi-room smart control Mobile app dashboard AI chatbot control system 18. 📦 Final Deployment Guide Flash ESP32 code Setup WiFi connection Deploy n8n workflow Connect Telegram bot Configure ThingSpeak API Link Google Sheets Test sensor triggers Enable AI logic Deploy face recognition system 🎯 Final Output You will get: Real-time smart home control AI-based decision automation Telegram alerts (text + voice) Cloud logging dashboard Face + voice recognition security Predictive energy monitoring