#6060th of 81 in VoiceFor voice, speech and music
xiaozhi-esp32-server-java
Java backend and admin console for Xiaozhi ESP32 voice devices
- Stars
- 1.4k
- License
- MIT
- Last commit
- Nov 2026
- Last release
- Apr 2026
- Language
- Java
1,205 on 21 Apr 20261,422 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Java server for Xiaozhi ESP32 hardware, split into two Spring Boot processes: an admin backend (port 8091, REST API, users, devices, OTA) and a dialogue service (port 8092, WebSocket/MQTT audio streams and the STT, LLM, TTS pipeline). It includes a Vue web console and integrates OpenAI, Zhipu, Xunfei, Ollama, Dify and Coze, plus local and cloud speech engines. Data is stored in MySQL, Redis and Qdrant.
Who it is for: Owners of Xiaozhi ESP32 devices who want a self-hosted server and admin UI
Strengths
- Dialogue and admin run as separate processes; dialogue instances register with the server and scale out
- Local STT/TTS via sherpa-onnx and Vosk, plus Edge TTS and several cloud providers
- README includes a 100-device concurrency benchmark on 8 cores / 8 GB
- Covers OTA rollout, MQTT wake-up, voiceprint recognition, RAG, long-term memory and MCP
Weaknesses
- Some features are not open source; a commercial edition exists
- README and docs are mostly in Chinese
- Needs MySQL, Redis and downloaded model/native library files before first run
- No LLM API key is bundled; you must supply your own to chat
What it needs
- Compose
- Needs MySQL 8.0, Redis 7, Qdrant, JDK 21 (source build), Node 22 (source build)
- Models: OpenAI, Zhipu AI, Xunfei Spark, Volcengine Ark, Ollama
- port 8084
Quick answers
Is xiaozhi-esp32-server-java open source?
Yes. Its code is on GitHub under the MIT license.
Can you run xiaozhi-esp32-server-java with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Also in Voice
See all 81| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing, dictation and audiobooks | 98 out of 100 |
| 2 | handyOffline push-to-talk dictation app that pastes transcripts into any text field | 91 out of 100 |
| 3 | whisper.cppC/C++ speech-to-text engine running OpenAI Whisper models locally | 90 out of 100 |
| #4 | xiaozhi-esp32ESP32 firmware for a voice chatbot with MCP device and cloud tool control | 83 out of 100 |
| #5 | buzzOffline desktop app for transcribing and translating audio with Whisper | 83 out of 100 |