XiaoZhi ESP32
Open-source voice chatbot firmware for ESP32 devices that talks through LLMs like Qwen and DeepSeek and controls hardware and services via MCP.
Updated
✨ Try AgentScout's free AI image generator →Good for: building voice agents, connecting tools with MCP
Use cases
About XiaoZhi ESP32
XiaoZhi ESP32 is listed in our voice category and is aimed at builders. Open-source voice chatbot firmware for ESP32 devices that talks through LLMs like Qwen and DeepSeek and controls hardware and services via MCP. Pricing, as the maker states it: Open source. Maturity: Mature. We last checked the official link on 2026-10-18.
What is XiaoZhi ESP32?
XiaoZhi is an open-source, MCP-based voice chatbot for ESP32 hardware. It uses large models such as Qwen and DeepSeek and controls multiple devices through the MCP protocol.
It supports Wi-Fi, Ethernet and 4G networking, offline wake words with ESP-SR, WebSocket or MQTT plus UDP transports, streaming speech recognition, LLM and text-to-speech pipelines, speaker recognition, and displays and cameras on supported boards. It requires ESP-IDF 6.0.1 or later.
Sources: the official README and our directory listing, checked 2026-10-18. Official site: xiaozhi.me.
Who is XiaoZhi ESP32 for?
Makers and hardware hobbyists who want to build their own AI voice assistant device on ESP32 boards.
XiaoZhi ESP32 at a glance
- Open source: Yes (MIT License)
- GitHub: 78/xiaozhi-esp32 · 31,677 stars (as of Oct 21, 2026)
Key features
- Voice chatbot firmware for ESP32 boards
- MCP-based device control
- Offline wake word with customizable wake words
- Streaming ASR + LLM + TTS and realtime voice models
- Wi-Fi, Ethernet and 4G networking
- Speaker recognition, displays and camera input
XiaoZhi ESP32 FAQ
What is XiaoZhi ESP32?
XiaoZhi is an open-source, MCP-based voice chatbot for ESP32 hardware. It uses large models such as Qwen and DeepSeek and controls multiple devices through the MCP protocol.
Who is XiaoZhi ESP32 for?
Makers and hardware hobbyists who want to build their own AI voice assistant device on ESP32 boards.
Is XiaoZhi ESP32 free?
XiaoZhi ESP32's pricing, as the maker states it: Open source. Open-source tools are free to use, though you may still pay for model API usage or a hosted plan. Check the official site for current plans.
Is XiaoZhi ESP32 open source?
Yes. XiaoZhi ESP32 is released under the MIT License, according to its GitHub repository.
What are alternatives to XiaoZhi ESP32?
Similar tools include Pipecat, TEN Framework, Qwen Audio Agent, Cicero, Goodcall and Dograh.
XiaoZhi ESP32 ratings and reviews
Be the first to rate XiaoZhi ESP32: tap 1 to 5 stars below. A written review is optional.
XiaoZhi ESP32 alternatives
Other voice tools in our directory. See all voice tools →
Pipecat
Open-source framework for voice and multimodal conversational agents.
TEN Framework
Open-source framework for real-time multimodal voice agents, including the TEN Agent demo.
Qwen Audio Agent
Real-time voice runtime from the Qwen Audio team that keeps agents talking while they think and work on tasks.
Cicero
Self-hosted voice interface for coding agents (Claude Code, Codex, ACP); talk from a browser or Telegram call.
Goodcall
AI answering service whose voice agent works as a virtual receptionist for businesses from small shops to contact centers.
Dograh
Self-hostable voice agent platform with a visual call-flow builder, bring-your-own speech and LLM providers and MCP control, pitched as an open alternative to Vapi and Retell.
Popular searches with this tool
🏆 Ranked in: Best AI Voice Agent Platforms
Badge for makers
Built XiaoZhi ESP32? Add this badge to your README or site. It links back to this page. About badges
