Alex: ESP32 voice assistant with puppy eyes
A bare ESP32 voice assistant with animated OLED eyes.
By jayesh_nawani
- Posted
Build sheet
- Board
- ESP32-D0WD-V3
- Other parts
- INMP441 I2S mic, MAX98357A amp + 3W speaker, SSD1306 0.96" OLED
- AI model or service
- OpenAI Whisper STT, GPT-4o-mini, OpenAI TTS
- Difficulty
- Beginner
Overview
Bare ESP32 (no PSRAM) + INMP441 mic + MAX98357A speaker + SSD1306 OLED. Records on volume trigger, Whisper+GPT+TTS via OpenAI APIs, streams PCM to the amp, and animates FreeRTOS-pinned puppy eyes (listen/think/speak/error) on core 0. Covered by Adafruit Blog.
How it works
Volume-triggered recording goes to OpenAI Whisper, GPT-4o-mini and TTS; PCM streams to the amp while a FreeRTOS task animates the eyes.
Hardware
- ESP32-D0WD-V3
- INMP441 I2S mic
- MAX98357A amp + 3W speaker
- SSD1306 0.96" OLED
Like this build? Get the weekly builds
Get the best new AI hardware builds every Thursday. One email a week, free.
Built something? Submit a build
This page is a short summary written by HardwareLab. Build steps, code and photos belong to the creator; follow “View original” for the full project.
Featured? Add this badge
Built this? Paste the badge into your README. It links back to this page.
Markdown
[](https://hardwarelab.dev/projects/alex-esp32-puppy-eyes/?utm_source=badge&utm_medium=referral&utm_campaign=launch_2w)HTML
<a href="https://hardwarelab.dev/projects/alex-esp32-puppy-eyes/?utm_source=badge&utm_medium=referral&utm_campaign=launch_2w"><img src="https://hardwarelab.dev/badge.svg" alt="Featured on HardwareLab" width="188" height="20"></a>Related builds
All 43 in Voice Assistants & CompanionsLocal Xiaozhi on a Waveshare ESP32-S3 audio board
A Xiaozhi voice assistant that only talks to your own LAN server.
- Waveshare ESP32-S3-AUDIO-Board (ES8311/ES7210, dual mic AEC, amp, RGB LEDs)
Intermediate

KALO ESP32 Voice Chat AI Friends
Chat with several custom AI friends on an ESP32.
- ESP32
- mic
- speaker
Intermediate75