78/xiaozhi-esp32
MCP-based voice AI chatbot firmware for ESP32
- Chart
- Not on a chart right now
- Stars
- 33.4k
What it is
An ESP32 voice chatbot firmware that connects large models such as Qwen and DeepSeek with multi-terminal control over the MCP protocol. It communicates over Wi-Fi, wired Ethernet, or 4G using WebSocket or MQTT+UDP.
Who it is for
Embedded developers and hardware makers building voice-controlled AI devices or IoT assistants on ESP32 boards.
Why it is trending
It gained 2,146 stars today, bringing its total to 33,349, alongside the recent v2.6.0 release. The project supports 138 board directories and 171 release variants, and has migrated to require ESP-IDF v6.0.1 or later.
Main features
- Offline voice wake-up with ESP-SR and speaker recognition
- Opus audio streaming for ASR+LLM+TTS and realtime voice models
- Device-side and cloud-side MCP for hardware and smart home control
- OLED/LCD emoji display, camera vision input, and 39 UI languages
Summarized on November 17, 2026 from the README and repository data. It can be wrong; check the source before relying on it. Report a wrong summary