XiaoZhi ESP32
The most-starred open-source ESP32 AI voice bot.
By 78 (Xiage)
- Est. cost
- Cost unknown
- Posted
- Date unknown
- GitHub stars
- 30.9K (GitHub)
- Likes on X
- 322 (X post)
Overview
An MCP-based AI chatbot firmware that turns cheap ESP32 boards into voice assistants. It handles wake word and streaming speech, connects to cloud LLMs such as Qwen and DeepSeek, and controls IoT devices through MCP tools. The seed X post calls it the standout of the ESP32 ecosystem.
How it works
ESP32-S3 handles wake word/audio and streams to a backend running ASR -> LLM -> TTS; MCP lets the LLM call device tools.
Hardware
- ESP32-S3
- I2S mic
- speaker
- optional LCD
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.
More in Voice Assistants & Companions
See all 32esp_ai (fully offline ESP32-S3)
Speech-to-text, a tiny LLM and TTS all on one ESP32-S3.
- Freenove FNK0104B ESP32-S3
AdvancedCost unknown40
Daedalus voice terminal
An ESP32 voice terminal for a home AI running OpenClaw.
- ESP32
- mic
- speaker
- +2 more
IntermediateCost unknownRIO XIAO ESP32 S3 Gemini Live Voice Assistant
Standalone full-duplex Gemini Live assistant on a XIAO.
- XIAO ESP32-S3
IntermediateCost unknown2