AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Voice / Speech/
xiaozhi-esp32-server-java
xiaozhi-esp32-server-java logo

xiaozhi-esp32-server-java

Active·★ 1.4k·MIT·Updated 2026-09-27

Xiaozhi ESP32 Server Java is an enterprise-style backend for the Xiaozhi ESP32 smart-hardware project, with a full management console. The README (in Chinese) says it uses a multi-module, two-process design: the admin platform and the conversation service run separately and share MySQL and Redis, so they can be deployed and scaled independently. Devices connect over WebSocket and MQTT, with server-initiated wake-up and OTA remote upgrades.

The AI side is broad. It integrates OpenAI, Zhipu, iFlytek Spark, Ollama, Dify and Coze for language models, with MCP tool protocol and Function Call extensions. Speech covers local and cloud STT (Vosk, FunASR, Alibaba Cloud, Tencent Cloud, iFlytek) and TTS (local sherpa-onnx, Volcano Engine, Alibaba Cloud, Edge TTS), with voice cloning, real-time interruption and two-way streaming. Other features are voice control of smart-home devices through Function Call, a RAG knowledge base with long-term memory, and dashboards for tokens, latency and device activity.

Deployment options are scripts (`bin/all.sh start`), Docker Compose, or source deployment on Linux and Windows, with Flyway creating tables automatically. Local models are not in the repository, so the first run downloads them with `scripts/download_models.sh`, or `download_base.sh` only if you use third-party STT and TTS. The stack is Spring Boot, MyBatis-Plus, Vue and Ant Design on MySQL 8 and Redis 7, and the README reports about 1.8 GB of memory in its test. The licence is MIT and the last push was 2026-09-27. This review is based on the README and repository data; we have not run it ourselves.

© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-22.

License
MIT
Latest release
v5.1.0 · 2026-04-21
Last commit
2026-09-27
Contributors
18
Forks
505
Open issues and PRs
2
First published
2025-02-27

Source: GitHub, npm and PyPI public APIs.

#esp32#java#mcp#mcp-client#mcp-server#mcp-servers#spring-ai#stt
$ Install
$ git clone https://github.com/joey-zhou/xiaozhi-esp32-server-java && cd xiaozhi-esp32-server-java && ./scripts/download_models.sh && bin/all.sh start
↗ Visit site★ GitHub
01

Features

01Multi-module dual-process architecture
02Multi-AI platform integration (OpenAI, Zhipu, etc.)
03Full voice pipeline with local/cloud STT/TTS
04WebSocket and MQTT real-time communication
05IoT smart home control and device management
06RAG knowledge base with document upload and retrieval
02

Why choose it

+Complete backend plus admin console for Xiaozhi ESP32 devices, with WebSocket, MQTT and OTA
+Many model options: OpenAI, Zhipu, iFlytek, Ollama, Dify, Coze, plus MCP and Function Call
+Voice pipeline with local and cloud STT/TTS, voice cloning and interruption
+Docker Compose or scripts, automatic table creation, MIT license
03

Trade-offs

!Needs MySQL 8, Redis 7 and a JVM, and the README reports about 1.8 GB of memory
!Local speech models are downloaded separately and add disk and memory use
!Tied to the Xiaozhi ESP32 hardware ecosystem, so it is not a general voice assistant
!Documentation is mainly in Chinese
05

Maintenance check

ActiveChecked: 2026-10-20
Last commit
2026-09-27
Commits, last 90 days
100+
Releases, last 90 days
0
Latest release
v5.1.0 (2026-04-21)
Open issues
2
Recent issues with at least one comment
24/30
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 1, 1, 0, 0, 91, 0, 40, 0, 1, 0, 0, 0

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

04

Who it fits

Pick it if
  • You run Xiaozhi ESP32 devices and want a Java backend with a full admin console.
  • You want the admin platform and conversation service to run and scale separately.
  • You need OTA upgrades, server-initiated wake-up, voice cloning and providers such as Zhipu, iFlytek, Ollama, Dify or Coze.
Look elsewhere if
  • You cannot run MySQL 8, Redis 7 and a JVM with about 1.8 GB of memory.
  • You have no Xiaozhi hardware: it is not a general voice assistant.
  • You cannot work from mainly Chinese documentation.
06

How it differs

xiaozhi-esp32-server logovs xiaozhi-esp32-server★ 11.0k

xiaozhi-esp32-server is the larger community backend, with a minimal no-database mode. The Java server is built around a two-process design and admin console.

Full comparison →
07

Compatibility

ESP32
ESP32
Verified via docs
08

Quick start

1
$ git clone https://github.com/joey-zhou/xiaozhi-esp32-server-java
2
$ cd xiaozhi-esp32-server-java
3
$ ./scripts/download_models.sh
4
$ bin/all.sh start
09

Use cases

↳Managing ESP32 devices with a complete backend platform
↳Building intelligent voice assistants with real-time interaction
↳Controlling IoT smart home devices via voice commands
10

Alternatives

⚡Top VS:
VSxiaozhi-esp32-server★11.0k→VSmcp-zap-server★67→VSncp★100→

Featured in these lists

  • Best Open-Source Voice Assistants and Speech Tools

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs05Maintenance check04Who it fits06How it differs

Most discussed open issues

  • #83 用户对话情感识别1 comments · 2025-05-23
  • #172 [BUG] DeepSeek/OpenAI 工具调用后下一轮对话 HTTP 400 (由于 Conversation 缺失工具链校验导致历史被写脏) 还有咱们这个我看好像没有配置式 MCP注册0 comments · 2026-07-01

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

VS
agent
★522
→
xiaozhi-esp32-server logo
xiaozhi-esp32-server★ 11.0k
本项目为xiaozhi-esp32提供后端服务,帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
VSCompare→
mcp-zap-server logo
mcp-zap-server★ 67
A Spring Boot application exposing OWASP ZAP as an MCP (Model Context Protocol) server. It lets any MCP‑compatible AI agent (e.g., Claude Desktop, Cursor) orchestrate ZAP actions—spider, active scan, import OpenAPI specs, and generate reports.
VSCompare→
ncp logo
ncp★ 100
Natural Context Provider (NCP). Your MCPs, supercharged. Find any tool instantly, load on demand, run on schedule, ready for any client. Smart loading saves tokens and energy.
VSCompare→
agent logo
agent★ 522
A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.
VSCompare→
discord-mcp logo
discord-mcp★ 556
A MCP server for the Discord integration. Enable your AI assistants to seamlessly interact with Discord. Enhance your Discord experience with powerful automation capabilities.
VSCompare→
turbomcp logo
turbomcp★ 98
A full featured, enterprise grade rust MCP SDK
VSCompare→
fli logo
fli★ 3.2k
Google Flights MCP and Python Library
VSCompare→
mlb-mcp logo
mlb-mcp★ 34
MCP server for advanced baseball analytics (statcast, fangraphs, baseball reference, mlb stats API) with client demo
VSCompare→
See all alternatives →
07
Compatibility
08Quick start
09Use cases
10Alternatives
joey-zhou /
xiaozhi-esp32-server-java
↗

MIT Java server and admin console for Xiaozhi ESP32 voice devices, with STT/TTS, LLM providers, MCP tools, RAG and OTA updates

1.4k505MIT
Last commit3w ago
StatusActive
CategoryVoice / Speech
Contributors18
Latest releasev5.1.0
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit