XiaoZhi ESP32

Active
GitHub C++ MIT

Description

An MCP-based open-source chatbot for ESP32 embedded devices, supporting voice interaction, multi-model integration, and IoT control for building smart hardware agents.

Key Features

  • MCP protocol device control — Device-side MCP controls speaker, LED, servo, GPIO; cloud-side MCP extends to smart home, email, and more
  • Offline voice wake-up & recognition — ESP-SR offline wake-word detection, OPUS audio codec, streaming ASR + LLM + TTS architecture
  • 70+ open-source hardware support — Compatible with ESP32-C3/S3/P4, LiChuang, ESP-BOX3, M5Stack, LILYGO and 70+ dev boards
  • Multi-language & multi-model — Supports Chinese/English/Japanese, connects to Qwen/DeepSeek, Websocket and MQTT+UDP dual protocols
  • Speaker recognition — Identifies current speaker via 3D Speaker model for personalized conversations
  • Online custom resources — Customize wake words, fonts, emojis, and chat backgrounds via web-based editor

Use Cases

💡 Smart home voice control — Voice-interact with smart lights, AC, and IoT devices via ESP32
💡 AI desktop assistant — Run LLM conversations on embedded devices for localized AI Q&A
💡 Education & maker projects — Breadboard DIY AI chatbot, learn embedded AI development
💡 Wearable device development — Build AI wearables with CuiCan AI Pendant and similar hardware
💡 Robot interaction control — Control robotic arms, robot dogs via MCP protocol

Tags

chatbot voice mcp agent api

Categories

💬 Chat UI

Quick Start

# 1. Clone the project
git clone https://github.com/78/xiaozhi-esp32.git
cd xiaozhi-esp32

# 2. Install ESP-IDF SDK (v5.4+)
# See https://docs.espressif.com/projects/esp-idf/en/latest/esp32/get-started/

# 3. Build and flash firmware
idf.py set-target esp32s3
idf.py build
idf.py flash

# 4. Connect device to xiaozhi.me server and start using
Visit GitHub

Related Projects