Introduction
Xiaozhi ESP32 is an open-source MCP-based voice AI chatbot project by 78, supporting multimodal interaction, IoT device control, and multilingual capabilities. It is suitable for AI hardware development and smart home scenarios.
Key Features
- Voice wake-up, ASR+LLM+TTS streaming interaction
- Multi-protocol (WebSocket/MQTT/UDP) and MCP control
- Supports various ESP32 chip platforms and 70+ open-source hardware
- Rich display and power management features, OLED/LCD/emotion display
- Open-source MIT license, active community
Use Cases
- Smart home voice control
- AI hardware development and prototyping
- Multimodal IoT device integration
- Education and open-source learning
Technical Highlights
- C++/Python multi-language collaboration, ESP-IDF development environment
- MCP protocol enables multi-end device and cloud extension
- Supports mainstream LLM capabilities and multilingual expansion