In this full step-by-step tutorial, we turn the ESP32-S3 into a complete AI Voice Assistant using ChatGPT, Whisper Speech-to-Text, and ElevenLabs Text-to-Speech!
You’ll learn how to:
Record voice using INMP441 microphone
Convert speech to text using OpenAI Whisper API
Send the recognized text to ChatGPT
Convert ChatGPT responses to human-like voice using ElevenLabs TTS
Play audio through MAX98357A I²S DAC
Build a fully working offline + online AI assistant on ESP32-S3
🧩 Hardware Used
ESP32-S3 Camera Board (with SD card)
INMP441 I²S Microphone
MAX98357A I²S DAC / Any compatible DAC
Speaker
Jumper wires
📥 Code & Resources
👉 Upload very soon on our website!
If you find this video useful, don’t forget to Like, Subscribe, and leave a comment!
Let me know if you want a Part 2 with offline AI, wake-word detection, or custom commands.