- Created README_de.md with German translation
- Maintains same structure and links as original
- Provides German-speaking users access to project documentation
Add detailed technical overview documentation (Chinese)
This document provides a comprehensive technical overview of the xiaozhi-esp32-server project in Chinese, including:
- Overall architecture
- In-depth analysis of xiaozhi-server, manager-api, and manager-web components, covering their purpose, core technologies, and key implementation aspects.
- Data flow and interaction mechanisms.
- Summary of key features.
- Deployment and configuration overview.
- The overall architecture.
- Deep dives into the xiaozhi-server, manager-api, and manager-web components, covering their purpose, core technologies, and key implementation aspects.
- How data flows and how different parts of the system interact.
- A summary of the key features.
- An overview of how to deploy and configure it.
Let me know if this is what you had in mind!
Dieses Projekt basiert auf der Theorie und Technologie der Mensch-Maschine-symbiotischen Intelligenz zur Entwicklung intelligenter Terminal-Hardware- und Software-Systeme<br/>und bietet Backend-Dienste für das Open-Source-Hardware-Projekt
Implementiert mit Python, Java und Vue gemäß dem <a href="https://ccnphfhqs21z.feishu.cn/wiki/M0XiwldO9iJwHikpXD5cEx71nKh">Xiaozhi-Kommunikationsprotokoll</a><br/>
Unterstützt MQTT+UDP-Protokoll, Websocket-Protokoll, MCP-Endpunkte und Stimmabdruckerkennung
Geleitet vom Team von Professor Siyuan Liu (South China University of Technology)
</br>
刘思源教授团队主导研发(华南理工大学)
</br>
<img src="./docs/images/hnlg.jpg" alt="South China University of Technology" width="50%">
</p>
---
## Zielgruppe 👥
Dieses Projekt erfordert ESP32-Hardware-Geräte zum Betrieb. Wenn Sie ESP32-bezogene Hardware erworben haben, erfolgreich eine Verbindung zu Brother Xias bereitgestelltem Backend-Service hergestellt haben und Ihren eigenen `xiaozhi-esp32`-Backend-Service unabhängig aufbauen möchten, dann ist dieses Projekt perfekt für Sie.
Möchten Sie die Nutzungseffekte sehen? Klicken Sie auf die Videos unten 🎥
1. Dieses Projekt ist Open-Source-Software. Diese Software hat keine kommerzielle Partnerschaft mit Drittanbieter-API-Dienstleistern (einschließlich, aber nicht beschränkt auf Spracherkennung, große Modelle, Sprachsynthese und andere Plattformen), mit denen sie sich verbindet, und bietet keine Garantie für deren Servicequalität oder finanzielle Sicherheit. Es wird empfohlen, dass Benutzer Dienstleister mit entsprechenden Geschäftslizenzen bevorzugen und deren Servicevereinbarungen und Datenschutzrichtlinien sorgfältig lesen. Diese Software hostet keine Kontoschlüssel, nimmt nicht an Geldströmen teil und trägt nicht das Risiko von Verlusten bei Guthaben-Aufladungen.
2. Die Funktionalität dieses Projekts ist nicht vollständig und hat keine Netzwerksicherheitsbewertung bestanden. Bitte verwenden Sie es nicht in Produktionsumgebungen. Wenn Sie dieses Projekt zu Lernzwecken in einer öffentlichen Netzwerkumgebung bereitstellen, stellen Sie bitte sicher, dass notwendige Schutzmaßnahmen vorhanden sind.
---
## Deployment-Dokumentation

Dieses Projekt bietet zwei Bereitstellungsmethoden. Bitte wählen Sie basierend auf Ihren spezifischen Anforderungen:
| **Vereinfachte Installation** | Intelligenter Dialog, Einzel-Agenten-Verwaltung | Umgebungen mit geringer Konfiguration, Daten in Konfigurationsdateien gespeichert, keine Datenbank erforderlich | [①Docker-Version](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②Quellcode-Deployment](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E5%8F%AA%E8%BF%90%E8%A1%8Cserver)| 2 Kerne 4GB bei Verwendung von `FunASR`, 2 Kerne 2GB bei allen APIs | - |
| **Vollständige Modulinstallation** | Intelligenter Dialog, Mehrbenutzerverwaltung, Mehr-Agenten-Verwaltung, Intelligente Steuerkonsole-Bedienung | Vollständige Funktionserfahrung, Daten in Datenbank gespeichert |[①Docker-Version](./docs/Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) / [②Quellcode-Deployment](./docs/Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) / [③Quellcode-Deployment Auto-Update-Tutorial](./docs/dev-ops-integration.md) | 4 Kerne 8GB bei Verwendung von `FunASR`, 2 Kerne 4GB bei allen APIs| [Video-Tutorial für lokalen Quellcode-Start](https://www.bilibili.com/video/BV1wBJhz4Ewe) |
Häufige Fragen und entsprechende Tutorials finden Sie unter [diesem Link](./docs/FAQ.md)
> 💡 Hinweis: Unten ist eine Testplattform, die mit dem neuesten Code bereitgestellt wurde. Sie können bei Bedarf brennen und testen. Gleichzeitige Benutzer: 6, Daten werden täglich gelöscht.
```
Adresse der intelligenten Steuerkonsole: https://2662r3426b.vicp.fun
Adresse der intelligenten Steuerkonsole (H5): https://2662r3426b.vicp.fun/h5/index.html
#### 🚩 Konfigurationsbeschreibung und Empfehlungen
> [!Note]
> Dieses Projekt bietet zwei Konfigurationsschemata:
>
> 1. `Einstiegslevel Kostenlose Einstellungen`: Geeignet für den persönlichen und privaten Gebrauch, alle Komponenten verwenden kostenlose Lösungen, keine zusätzliche Zahlung erforderlich.
>
> 2. `Streaming-Konfiguration`: Geeignet für Demonstrationen, Schulungen, Szenarien mit mehr als 2 gleichzeitigen Benutzern usw. Verwendet Streaming-Verarbeitungstechnologie für schnellere Reaktionsgeschwindigkeit und bessere Erfahrung.
>
> Ab Version `0.5.2` unterstützt das Projekt Streaming-Konfiguration. Im Vergleich zu früheren Versionen ist die Reaktionsgeschwindigkeit um ca. `2,5 Sekunden` verbessert, was die Benutzererfahrung erheblich verbessert.
Wenn Sie sich um die Latenz jeder Komponente kümmern, lesen Sie bitte den [Xiaozhi-Komponenten-Leistungstestbericht](https://github.com/xinnan-tech/xiaozhi-performance-research). Sie können gemäß den Testmethoden im Bericht in Ihrer Umgebung tatsächlich testen.
#### 🔧 Testwerkzeuge
Dieses Projekt bietet die folgenden Testwerkzeuge, um Ihnen bei der Überprüfung des Systems und der Auswahl geeigneter Modelle zu helfen:
| Audio-Interaktionstesttool | main》xiaozhi-server》test》test_page.html | Direkt mit Google Chrome öffnen | Testet Audio-Wiedergabe- und Empfangsfunktionen, überprüft, ob die Python-seitige Audioverarbeitung normal ist |
| Modell-Reaktionstesttool | main》xiaozhi-server》performance_tester.py | Ausführen `python performance_tester.py` | Testet die Reaktionsgeschwindigkeit von ASR (Spracherkennung), LLM (großes Modell), VLLM (Vision-Modell), TTS (Sprachsynthese) drei Kernmodulen |
> 💡 Hinweis: Beim Testen der Modellgeschwindigkeit werden nur Modelle mit konfigurierten Schlüsseln getestet.
---
## Funktionsliste ✨
### Implementiert ✅

| Funktionsmodul | Beschreibung |
|:---:|:---|
| Kernarchitektur | Basierend auf [MQTT+UDP-Gateway](https://github.com/xinnan-tech/xiaozhi-esp32-server/blob/main/docs/mqtt-gateway-integration.md), WebSocket und HTTP-Servern, bietet vollständiges Konsolenverwaltungs- und Authentifizierungssystem |
| Sprachinteraktion | Unterstützt Streaming-ASR (Spracherkennung), Streaming-TTS (Sprachsynthese), VAD (Sprachaktivitätserkennung), unterstützt mehrsprachige Erkennung und Sprachverarbeitung |
| Stimmabdruckerkennung | Unterstützt Mehrbenutzer-Stimmabdruckregistrierung, -verwaltung und -erkennung, verarbeitet parallel mit ASR, Echtzeit-Sprecheridentitätserkennung und Weitergabe an LLM für personalisierte Antworten |
| Gedächtnissystem | Unterstützt lokales Kurzzeitgedächtnis, mem0ai-Schnittstellengedächtnis, mit Gedächtniszusammenfassungsfunktion |
| Wissensdatenbank | Unterstützt RAGFlow-Wissensdatenbank, ermöglicht großem Modell die Bewertung, ob Wissensdatenbank benötigt wird, bevor geantwortet wird |
| Befehlsübermittlung | Basierend auf MQTT-Protokoll, unterstützt die Übermittlung von MCP-Befehlen von der intelligenten Steuerkonsole an ESP32-Geräte |
| Verwaltungs-Backend | Bietet Web-Verwaltungsoberfläche, unterstützt Benutzerverwaltung, Systemkonfiguration und Geräteverwaltung; Oberfläche unterstützt vereinfachtes Chinesisch, traditionelles Chinesisch und englische Anzeige |
| Testwerkzeuge | Bietet Leistungstestwerkzeuge, Vision-Modell-Testwerkzeuge und Audio-Interaktionstestwerkzeuge |
Um über spezifische Entwicklungsplanfortschritte zu erfahren, [klicken Sie hier](https://github.com/users/xinnan-tech/projects/3). Häufige Fragen und entsprechende Tutorials finden Sie unter [diesem Link](./docs/FAQ.md)
Wenn Sie ein Softwareentwickler sind, finden Sie hier einen [Offenen Brief an Entwickler](docs/contributor_open_letter.md). Willkommen beim Beitritt!
---
## Produktökosystem 👬
Xiaozhi ist ein Ökosystem. Wenn Sie dieses Produkt verwenden, können Sie sich auch andere [hervorragende Projekte](https://github.com/78/xiaozhi-esp32?tab=readme-ov-file#related-open-source-projects) in diesem Ökosystem ansehen
---
## Liste der von diesem Projekt unterstützten Plattformen/Komponenten 📋
| Rag | ragflow | Schnittstellenaufrufe | Gebühren basierend auf Token-Verbrauch für Segmentierung und Tokenisierung | Nutzt RAGFlow's Retrieval-Augmented-Generation-Funktion für präzisere Dialogantworten |
---
## Danksagungen 🙏
| Logo | Projekt/Unternehmen | Beschreibung |
|:---:|:---:|:---|
| <img src="./docs/images/logo_bailing.png" width="160"> | [Bailing Voice Dialogue Robot](https://github.com/wwbin2017/bailing) | Dieses Projekt wurde von [Bailing Voice Dialogue Robot](https://github.com/wwbin2017/bailing) inspiriert und auf dessen Basis implementiert |
| <img src="./docs/images/logo_tenclass.png" width="160"> | [Tenclass](https://www.tenclass.com/) | Dank an [Tenclass](https://www.tenclass.com/) für die Formulierung von Standardkommunikationsprotokollen, Multi-Geräte-Kompatibilitätslösungen und High-Concurrency-Szenario-Praxisdemonstrationen für das Xiaozhi-Ökosystem; für die Bereitstellung vollständiger technischer Dokumentationsunterstützung für dieses Projekt |
| <img src="./docs/images/logo_xuanfeng.png" width="160"> | [Xuanfeng Technology](https://github.com/Eric0308) | Dank an [Xuanfeng Technology](https://github.com/Eric0308) für den Beitrag des Funktionsaufruf-Frameworks, des MCP-Kommunikationsprotokolls und der plugin-basierten Aufrufmechanismus-Implementierungscode. Durch standardisiertes Befehlsplanungssystem und dynamische Erweiterungsfähigkeiten wird die Interaktionseffizienz und funktionale Erweiterbarkeit von Frontend-Geräten (IoT) erheblich verbessert |
| <img src="./docs/images/logo_junsen.png" width="160"> | [huangjunsen](https://github.com/huangjunsen0406) | Dank an [huangjunsen](https://github.com/huangjunsen0406) für den Beitrag des `Smart Control Console Mobile`-Moduls, das eine effiziente Steuerung und Echtzeit-Interaktion über mobile Geräte ermöglicht und die Betriebsbequemlichkeit und Verwaltungseffizienz des Systems in mobilen Szenarien erheblich verbessert |
| <img src="./docs/images/logo_huiyuan.png" width="160"> | [Huiyuan Design](http://ui.kwd988.net/) | Dank an [Huiyuan Design](http://ui.kwd988.net/) für die Bereitstellung professioneller visueller Lösungen für dieses Projekt, unter Verwendung ihrer Design-Praxiserfahrung im Dienst von über tausend Unternehmen, um die Produktbenutzererfahrung dieses Projekts zu stärken |
| <img src="./docs/images/logo_qinren.png" width="160"> | [Xi'an Qinren Information Technology](https://www.029app.com/) | Dank an [Xi'an Qinren Information Technology](https://www.029app.com/) für die Vertiefung des visuellen Systems dieses Projekts und die Sicherstellung der Konsistenz und Erweiterbarkeit des Gesamtdesignstils in Multi-Szenario-Anwendungen |
| <img src="./docs/images/logo_contributors.png" width="160"> | [Code-Mitwirkende](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors) | Dank an [alle Code-Mitwirkenden](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors), Ihre Bemühungen haben das Projekt robuster und leistungsfähiger gemacht. |
<h1 align="center">Xiaozhi Backend Service xiaozhi-esp32-server</h1>
<p align="center">
This project is based on human-machine symbiotic intelligence theory and technology to develop intelligent terminal hardware and software systems<br/>providing backend services for the open-source intelligent hardware project
Implemented using Python, Java, and Vue according to the <a href="https://ccnphfhqs21z.feishu.cn/wiki/M0XiwldO9iJwHikpXD5cEx71nKh">Xiaozhi Communication Protocol</a><br/>
Support for MQTT+UDP protocol, Websocket protocol, MCP access point, voiceprint recognition, and knowledge base
Spearheaded by Professor Siyuan Liu's Team (South China University of Technology)
</br>
刘思源教授团队主导研发(华南理工大学)
</br>
<img src="./docs/images/hnlg.jpg" alt="South China University of Technology" width="50%">
</p>
---
## Target Users 👥
This project requires ESP32 hardware devices to work. If you have purchased ESP32-related hardware, successfully connected to Brother Xia's deployed backend service, and want to build your own `xiaozhi-esp32` backend service independently, then this project is perfect for you.
Want to see the usage effects? Click the videos below 🎥
1. This project is open-source software. This software has no commercial partnership with any third-party API service providers (including but not limited to speech recognition, large models, speech synthesis, and other platforms) that it interfaces with, and does not provide any form of guarantee for their service quality or financial security. It is recommended that users prioritize service providers with relevant business licenses and carefully read their service agreements and privacy policies. This software does not host any account keys, does not participate in fund flows, and does not bear the risk of recharge fund losses.
2. The functionality of this project is not complete and has not passed network security assessment. Please do not use it in production environments. If you deploy this project for learning purposes in a public network environment, please ensure necessary protection measures are in place.
---
## Deployment Documentation

This project provides two deployment methods. Please choose based on your specific needs:
#### 🚀 Deployment Method Selection
| Deployment Method | Features | Applicable Scenarios | Deployment Docs | Configuration Requirements | Video Tutorials |
#### 🚩 Configuration Description and Recommendations
> [!Note]
> This project provides two configuration schemes:
>
> 1. `Entry Level Free Settings`: Suitable for personal and home use, all components use free solutions, no additional payment required.
>
> 2. `Streaming Configuration`: Suitable for demonstrations, training, scenarios with more than 2 concurrent users, etc. Uses streaming processing technology for faster response speed and better experience.
>
> Starting from version `0.5.2`, the project supports streaming configuration. Compared to earlier versions, response speed is improved by approximately `2.5 seconds`, significantly improving user experience.
This project provides the following testing tools to help you verify the system and choose suitable models:
| Tool Name | Location | Usage Method | Function Description |
|:---:|:---|:---:|:---:|
| Audio Interaction Test Tool | main》xiaozhi-server》test》test_page.html | Open directly with Google Chrome | Tests audio playback and reception functions, verifies if Python-side audio processing is normal |
| Model Response Test Tool 1 | main》xiaozhi-server》performance_tester.py | Execute `python performance_tester.py` | Tests response speed of three core modules: ASR(speech recognition), LLM(large model), TTS(speech synthesis) |
| Model Response Test Tool 2 | main》xiaozhi-server》performance_tester_vllm.py | Execute `python performance_tester_vllm.py` | Tests VLLM(vision model) response speed |
> 💡 Note: When testing model speed, only models with configured keys will be tested.
---
## Feature List ✨
### Implemented ✅

| Feature Module | Description |
|:---:|:---|
| Core Architecture | Based on [MQTT+UDP gateway](https://github.com/xinnan-tech/xiaozhi-esp32-server/blob/main/docs/mqtt-gateway-integration.md), WebSocket and HTTP servers, provides complete console management and authentication system |
| Voiceprint Recognition | Supports multi-user voiceprint registration, management, and recognition, processes in parallel with ASR, real-time speaker identity recognition and passes to LLM for personalized responses |
| Intent Recognition | Supports LLM intent recognition, Function Call function calling, provides plugin-based intent processing mechanism |
| Memory System | Supports local short-term memory, mem0ai interface memory, with memory summarization functionality |
| Knowledge Base | Supports RAGFlow knowledge base, enabling LLM to judge whether to schedule the knowledge base after receiving the user's question, and then answer the question |
| Command Delivery | Supports MCP command delivery to ESP32 devices via MQTT protocol from Smart Console |
| Management Backend | Provides Web management interface, supports user management, system configuration and device management; Supports Simplified Chinese, Traditional Chinese and English display |
| Testing Tools | Provides performance testing tools, vision model testing tools, and audio interaction testing tools |
| Deployment Support | Supports Docker deployment and local deployment, provides complete configuration file management |
| Plugin System | Supports functional plugin extensions, custom plugin development, and plugin hot-loading |
### Under Development 🚧
To learn about specific development plan progress, [click here](https://github.com/users/xinnan-tech/projects/3)
If you are a software developer, here is an [Open Letter to Developers](docs/contributor_open_letter.md). Welcome to join!
---
## Product Ecosystem 👬
Xiaozhi is an ecosystem. When using this product, you can also check out other [excellent projects](https://github.com/78/xiaozhi-esp32?tab=readme-ov-file#related-open-source-projects) in this ecosystem
| Project Name | Project Address | Project Description |
|:---------------------|:--------|:--------|
| Xiaozhi Android Client | [xiaozhi-android-client](https://github.com/TOM88812/xiaozhi-android-client) | An Android and iOS voice dialogue application based on xiaozhi-server, supporting real-time voice interaction and text dialogue.<br/>Currently a Flutter version, connecting iOS and Android platforms. |
| Xiaozhi Desktop Client | [py-xiaozhi](https://github.com/Huang-junsen/py-xiaozhi) | This project provides a Python-based AI client for beginners, allowing users to experience Xiaozhi AI functionality through code even without physical hardware conditions. |
| Xiaozhi Java Server | [xiaozhi-esp32-server-java](https://github.com/joey-zhou/xiaozhi-esp32-server-java) | Xiaozhi open-source backend service Java version is a Java-based open-source project.<br/>It includes frontend and backend services, aiming to provide users with a complete backend service solution. |
| Rag | ragflow | Interface calls | Charged based on tokens consumed for slicing and word segmentation | Utilizes RagFlow's retrieval-augmented generation feature to provide more accurate dialog responses |
---
## Acknowledgments 🙏
| Logo | Project/Company | Description |
|:---:|:---:|:---|
| <img src="./docs/images/logo_bailing.png" width="160"> | [Bailing Voice Dialogue Robot](https://github.com/wwbin2017/bailing) | This project is inspired by [Bailing Voice Dialogue Robot](https://github.com/wwbin2017/bailing) and implemented on its basis |
| <img src="./docs/images/logo_tenclass.png" width="160"> | [Tenclass](https://www.tenclass.com/) | Thanks to [Tenclass](https://www.tenclass.com/) for formulating standard communication protocols, multi-device compatibility solutions, and high-concurrency scenario practice demonstrations for the Xiaozhi ecosystem; providing full-link technical documentation support for this project |
| <img src="./docs/images/logo_xuanfeng.png" width="160"> | [Xuanfeng Technology](https://github.com/Eric0308) | Thanks to [Xuanfeng Technology](https://github.com/Eric0308) for contributing function calling framework, MCP communication protocol, and plugin-based calling mechanism implementation code. Through standardized instruction scheduling system and dynamic expansion capabilities, it significantly improves the interaction efficiency and functional extensibility of frontend devices (IoT) |
| <img src="./docs/images/logo_junsen.png" width="160"> | [huangjunsen](https://github.com/huangjunsen0406) | Thanks to [huangjunsen](https://github.com/huangjunsen0406) for contributing the `Smart Control Console Mobile` module, which enables efficient control and real-time interaction across mobile devices, significantly enhancing the system's operational convenience and management efficiency in mobile scenarios. |
| <img src="./docs/images/logo_huiyuan.png" width="160"> | [Huiyuan Design](http://ui.kwd988.net/) | Thanks to [Huiyuan Design](http://ui.kwd988.net/) for providing professional visual solutions for this project, using their design practical experience serving over a thousand enterprises to empower this project's product user experience |
| <img src="./docs/images/logo_qinren.png" width="160"> | [Xi'an Qinren Information Technology](https://www.029app.com/) | Thanks to [Xi'an Qinren Information Technology](https://www.029app.com/) for deepening this project's visual system, ensuring consistency and extensibility of overall design style in multi-scenario applications |
| <img src="./docs/images/logo_contributors.png" width="160"> | [Code Contributors](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors) | Thanks to [all code contributors](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors), your efforts have made the project more robust and powerful. |
<h1 align="center">Dịch vụ Backend Xiaozhi xiaozhi-esp32-server</h1>
<p align="center">
Dự án này dựa trên lý thuyết và công nghệ trí tuệ cộng sinh người-máy để phát triển hệ thống phần mềm và phần cứng thiết bị đầu cuối thông minh<br/>Cung cấp dịch vụ backend cho dự án phần cứng thông minh mã nguồn mở
Được triển khai bằng Python, Java, Vue theo <a href="https://ccnphfhqs21z.feishu.cn/wiki/M0XiwldO9iJwHikpXD5cEx71nKh">giao thức truyền thông Xiaozhi</a><br/>
Hỗ trợ giao thức MQTT+UDP, giao thức Websocket, điểm truy cập MCP, nhận dạng giọng nói và kho tri thức
Dự án này cần được sử dụng cùng với thiết bị phần cứng ESP32. Nếu bạn đã mua phần cứng liên quan đến ESP32, đã thành công kết nối với dịch vụ backend do anh Xia triển khai, và muốn xây dựng dịch vụ backend `xiaozhi-esp32` riêng của mình, thì dự án này rất phù hợp với bạn.
1. Dự án này là phần mềm mã nguồn mở, phần mềm này không có quan hệ hợp tác thương mại với bất kỳ nhà cung cấp dịch vụ API bên thứ ba nào (bao gồm nhưng không giới hạn ở các nền tảng nhận dạng giọng nói, mô hình lớn, tổng hợp giọng nói, v.v.), và không đảm bảo chất lượng dịch vụ cũng như an toàn tài chính của họ.
Khuyến nghị người dùng ưu tiên lựa chọn nhà cung cấp dịch vụ có giấy phép kinh doanh liên quan và đọc kỹ thỏa thuận dịch vụ và chính sách bảo mật của họ. Phần mềm này không lưu trữ bất kỳ khóa tài khoản nào, không tham gia vào luồng tiền và không chịu rủi ro mất tiền nạp.
2. Chức năng của dự án này chưa hoàn thiện và chưa qua đánh giá bảo mật mạng, vui lòng không sử dụng trong môi trường sản xuất. Nếu bạn triển khai dự án này trong môi trường mạng công cộng để học tập, vui lòng thực hiện các biện pháp bảo vệ cần thiết.
---
## Tài liệu triển khai

Dự án này cung cấp hai phương pháp triển khai, vui lòng chọn theo nhu cầu cụ thể của bạn:
#### 🚀 Lựa chọn phương pháp triển khai
| Phương pháp triển khai | Đặc điểm | Tình huống áp dụng | Tài liệu triển khai | Yêu cầu cấu hình | Video hướng dẫn |
| **Cài đặt tối giản** | Đối thoại thông minh, quản lý đơn tác nhân | Môi trường cấu hình thấp, dữ liệu lưu trong tệp cấu hình, không cần cơ sở dữ liệu | [①Phiên bản Docker](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②Triển khai mã nguồn](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E5%8F%AA%E8%BF%90%E8%A1%8Cserver)| 2 nhân 4GB nếu dùng `FunASR`, 2 nhân 2GB nếu toàn API | - |
| **Cài đặt toàn bộ module** | Đối thoại thông minh, quản lý đa người dùng, quản lý đa tác nhân, bảng điều khiển thông minh | Trải nghiệm đầy đủ tính năng, dữ liệu lưu trong cơ sở dữ liệu |[①Phiên bản Docker](./docs/Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) / [②Triển khai mã nguồn](./docs/Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) / [③Hướng dẫn tự động cập nhật triển khai mã nguồn](./docs/dev-ops-integration.md) | 4 nhân 8GB nếu dùng `FunASR`, 2 nhân 4GB nếu toàn API| [Video hướng dẫn khởi động mã nguồn cục bộ](https://www.bilibili.com/video/BV1wBJhz4Ewe) |
Câu hỏi thường gặp và hướng dẫn liên quan, vui lòng tham khảo [liên kết này](./docs/FAQ.md)
> 💡 Gợi ý: Dưới đây là nền tảng thử nghiệm được triển khai theo mã mới nhất, có thể flash để thử nghiệm nếu cần, đồng thời là 6, dữ liệu sẽ được xóa mỗi ngày,
```
Địa chỉ bảng điều khiển thông minh: https://2662r3426b.vicp.fun
Bảng điều khiển thông minh (phiên bản h5): https://2662r3426b.vicp.fun/h5/index.html
Công cụ kiểm tra dịch vụ: https://2662r3426b.vicp.fun/test/
Địa chỉ giao diện OTA: https://2662r3426b.vicp.fun/xiaozhi/ota/
Địa chỉ giao diện Websocket: wss://2662r3426b.vicp.fun/xiaozhi/v1/
```
#### 🚩 Mô tả và khuyến nghị cấu hình
> [!Note]
> Dự án này cung cấp hai phương án cấu hình:
>
> 1. Cấu hình `Miễn phí hoàn toàn cho người mới`: Phù hợp với sử dụng gia đình cá nhân, tất cả các thành phần đều sử dụng phương án miễn phí, không cần thanh toán thêm.
>
> 2. `Cấu hình streaming`: Phù hợp với demo, đào tạo, hơn 2 đồng thời, v.v., sử dụng công nghệ xử lý streaming, tốc độ phản hồi nhanh hơn, trải nghiệm tốt hơn.
>
> Từ phiên bản `0.5.2`, dự án hỗ trợ cấu hình streaming, so với phiên bản đầu, tốc độ phản hồi cải thiện khoảng `2.5 giây`, cải thiện đáng kể trải nghiệm người dùng.
| Tên module | Cài đặt miễn phí cho người mới | Cấu hình streaming |
| Memory(Chức năng bộ nhớ) | mem_local_short(Bộ nhớ ngắn hạn cục bộ) | mem_local_short(Bộ nhớ ngắn hạn cục bộ) |
Nếu bạn quan tâm đến thời gian của từng thành phần, vui lòng xem [Báo cáo kiểm tra hiệu suất các thành phần Xiaozhi](https://github.com/xinnan-tech/xiaozhi-performance-research), có thể kiểm tra thực tế trong môi trường của bạn theo phương pháp kiểm tra trong báo cáo.
#### 🔧 Công cụ kiểm tra
Dự án này cung cấp các công cụ kiểm tra sau để giúp bạn xác minh hệ thống và chọn mô hình phù hợp:
| Tên công cụ | Vị trí | Phương pháp sử dụng | Mô tả chức năng |
|:---:|:---|:---:|:---:|
| Công cụ kiểm tra tương tác âm thanh | main》xiaozhi-server》test》test_page.html | Mở trực tiếp bằng trình duyệt Google Chrome | Kiểm tra chức năng phát và nhận âm thanh, xác minh xử lý âm thanh phía Python có bình thường không |
| Công cụ kiểm tra phản hồi mô hình | main》xiaozhi-server》performance_tester.py | Thực hiện `python performance_tester.py` | Kiểm tra tốc độ phản hồi của ba module cốt lõi ASR(Nhận dạng giọng nói), LLM(Mô hình lớn), VLLM(Mô hình thị giác), TTS(Tổng hợp giọng nói) |
> 💡 Gợi ý: Khi kiểm tra tốc độ mô hình, chỉ kiểm tra các mô hình đã cấu hình khóa.
---
## Danh sách tính năng ✨
### Đã thực hiện ✅

| Module chức năng | Mô tả |
|:---:|:---|
| Kiến trúc cốt lõi | Dựa trên [cổng MQTT+UDP](https://github.com/xinnan-tech/xiaozhi-esp32-server/blob/main/docs/mqtt-gateway-integration.md), WebSocket, máy chủ HTTP, cung cấp hệ thống quản lý bảng điều khiển và xác thực hoàn chỉnh |
| Tương tác giọng nói | Hỗ trợ ASR streaming(Nhận dạng giọng nói), TTS streaming(Tổng hợp giọng nói), VAD(Phát hiện hoạt động giọng nói), hỗ trợ nhận dạng đa ngôn ngữ và xử lý giọng nói |
| Nhận dạng vân giọng | Hỗ trợ đăng ký, quản lý và nhận dạng vân giọng đa người dùng, xử lý song song với ASR, nhận dạng danh tính người nói theo thời gian thực và truyền cho LLM để phản hồi cá nhân hóa |
| Đối thoại thông minh | Hỗ trợ nhiều LLM(Mô hình ngôn ngữ lớn), thực hiện đối thoại thông minh |
| Cảm nhận thị giác | Hỗ trợ nhiều VLLM(Mô hình lớn thị giác), thực hiện tương tác đa phương thức |
| Nhận dạng ý định | Hỗ trợ nhận dạng ý định mô hình lớn gắn ngoài, gọi hàm tự chủ mô hình lớn, cung cấp cơ chế xử lý ý định dạng plugin |
| Hệ thống bộ nhớ | Hỗ trợ bộ nhớ ngắn hạn cục bộ, bộ nhớ giao diện mem0ai, có chức năng tóm tắt bộ nhớ |
| Kho tri thức | Hỗ trợ kho tri thức RAGFlow, cho phép mô hình lớn đánh giá cần gọi kho tri thức trước khi trả lời |
| Gọi công cụ | Hỗ trợ giao thức IOT phía client, giao thức MCP phía client, giao thức MCP phía server, giao thức điểm truy cập MCP, hàm công cụ tùy chỉnh |
| Gửi lệnh | Dựa vào giao thức MQTT, hỗ trợ gửi lệnh MCP từ bảng điều khiển thông minh xuống thiết bị ESP32 |
| Backend quản lý | Cung cấp giao diện quản lý Web, hỗ trợ quản lý người dùng, cấu hình hệ thống và quản lý thiết bị; giao diện hỗ trợ hiển thị tiếng Trung giản thể, tiếng Trung phồn thể, tiếng Anh |
| Công cụ kiểm tra | Cung cấp công cụ kiểm tra hiệu suất, công cụ kiểm tra mô hình thị giác và công cụ kiểm tra tương tác âm thanh |
| Hỗ trợ triển khai | Hỗ trợ triển khai Docker và triển khai cục bộ, cung cấp quản lý tệp cấu hình hoàn chỉnh |
| Hệ thống plugin | Hỗ trợ mở rộng plugin chức năng, phát triển plugin tùy chỉnh và hot loading plugin |
### Đang phát triển 🚧
Muốn hiểu tiến độ kế hoạch phát triển cụ thể, [vui lòng nhấp vào đây](https://github.com/users/xinnan-tech/projects/3). Câu hỏi thường gặp và hướng dẫn liên quan, vui lòng tham khảo [liên kết này](./docs/FAQ.md)
Nếu bạn là một nhà phát triển phần mềm, đây có một [Lá thư mở gửi các nhà phát triển](docs/contributor_open_letter.md), chào mừng tham gia!
---
## Hệ sinh thái sản phẩm 👬
Xiaozhi là một hệ sinh thái, khi bạn sử dụng sản phẩm này, bạn cũng có thể xem các [dự án xuất sắc](https://github.com/78/xiaozhi-esp32?tab=readme-ov-file#related-open-source-projects) khác trong hệ sinh thái này
---
## Danh sách nền tảng/thành phần được dự án này hỗ trợ 📋
### LLM Mô hình ngôn ngữ
| Phương pháp sử dụng | Nền tảng hỗ trợ | Nền tảng miễn phí |
|:---:|:---:|:---:|
| Gọi giao diện openai | Alibaba Bailian, Volcano Engine, DeepSeek, Zhipu, Gemini, iFlytek | Zhipu, Gemini |
| Gọi giao diện ollama | Ollama | - |
| Gọi giao diện dify | Dify | - |
| Gọi giao diện fastgpt | Fastgpt | - |
| Gọi giao diện coze | Coze | - |
| Gọi giao diện xinference | Xinference | - |
| Gọi giao diện homeassistant | HomeAssistant | - |
Trên thực tế, bất kỳ LLM nào hỗ trợ gọi giao diện openai đều có thể truy cập sử dụng.
---
### VLLM Mô hình thị giác
| Phương pháp sử dụng | Nền tảng hỗ trợ | Nền tảng miễn phí |
|:---:|:---:|:---:|
| Gọi giao diện openai | Alibaba Bailian, Zhipu ChatGLMVLLM | Zhipu ChatGLMVLLM |
Trên thực tế, bất kỳ VLLM nào hỗ trợ gọi giao diện openai đều có thể truy cập sử dụng.
---
### TTS Tổng hợp giọng nói
| Phương pháp sử dụng | Nền tảng hỗ trợ | Nền tảng miễn phí |
| Rag | ragflow | Gọi giao diện | Thu phí theo token tiêu tốn của phân đoạn, phân từ | Sử dụng chức năng tăng cường truy xuất của RagFlow, cung cấp phản hồi đối thoại chính xác hơn |
---
## Lời cảm ơn 🙏
| Logo | Dự án/Công ty | Mô tả |
|:---:|:---:|:---|
| <img src="./docs/images/logo_bailing.png" width="160"> | [Robot đối thoại giọng nói Bailing](https://github.com/wwbin2017/bailing) | Dự án này được lấy cảm hứng từ [Robot đối thoại giọng nói Bailing](https://github.com/wwbin2017/bailing) và được triển khai trên cơ sở đó |
| <img src="./docs/images/logo_tenclass.png" width="160"> | [Shifang Ronghai](https://www.tenclass.com/) | Cảm ơn [Shifang Ronghai](https://www.tenclass.com/) đã xây dựng giao thức truyền thông tiêu chuẩn, phương án tương thích đa thiết bị và mô phạm thực hành tình huống đồng thời cao cho hệ sinh thái Xiaozhi; cung cấp tài liệu hỗ trợ kỹ thuật toàn diện cho dự án này |
| <img src="./docs/images/logo_xuanfeng.png" width="160"> | [Xuanfeng Technology](https://github.com/Eric0308) | Cảm ơn [Xuanfeng Technology](https://github.com/Eric0308) đã đóng góp khung gọi hàm, giao thức truyền thông MCP và mã triển khai cơ chế gọi dạng plugin, thông qua hệ thống điều phối lệnh tiêu chuẩn hóa và khả năng mở rộng động, đã cải thiện đáng kể hiệu suất tương tác và khả năng mở rộng chức năng của thiết bị front-end(IoT) |
| <img src="./docs/images/logo_junsen.png" width="160"> | [huangjunsen](https://github.com/huangjunsen0406) | Cảm ơn [huangjunsen](https://github.com/huangjunsen0406) đã đóng góp module `Bảng điều khiển thông minh di động`, thực hiện điều khiển hiệu quả và tương tác thời gian thực trên thiết bị di động đa nền tảng, cải thiện đáng kể sự tiện lợi vận hành và hiệu quả quản lý của hệ thống trong tình huống di động |
| <img src="./docs/images/logo_huiyuan.png" width="160"> | [Huiyuan Design](http://ui.kwd988.net/) | Cảm ơn [Huiyuan Design](http://ui.kwd988.net/) đã cung cấp giải pháp thị giác chuyên nghiệp cho dự án này, sử dụng kinh nghiệm thực tế thiết kế phục vụ hơn nghìn doanh nghiệp, trao quyền cho trải nghiệm người dùng sản phẩm của dự án này |
| <img src="./docs/images/logo_qinren.png" width="160"> | [Xi'an Qinren Information Technology](https://www.029app.com/) | Cảm ơn [Xi'an Qinren Information Technology](https://www.029app.com/) đã làm sâu sắc hệ thống thị giác của dự án này, đảm bảo tính nhất quán và khả năng mở rộng của phong cách thiết kế tổng thể trong ứng dụng đa tình huống |
| <img src="./docs/images/logo_contributors.png" width="160"> | [Người đóng góp mã](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors) | Cảm ơn [tất cả người đóng góp mã](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors), sự cống hiến của bạn khiến dự án mạnh mẽ và vững chắc hơn. |
[2025-08-07 11:16:33,356] [ INFO] - Other info: front time: 0.06514096260070801 s, first am infer time: 0.008037090301513672 s, first voc infer time: 0.04112648963928223 s,
[2025-08-07 11:16:33,356] [ INFO] - Complete the synthesis of the audio streams
4. [Data Flow and Interaction Mechanisms](#4-data-flow-and-interaction-mechanisms)
5. [Key Features Summary](#5-key-features-summary)
6. [Deployment and Configuration Overview](#6-deployment-and-configuration-overview)
---
## 1. Introduction
The `xiaozhi-esp32-server` project is a **comprehensive backend system** designed to support intelligent hardware based on ESP32. Its core goal is to enable developers to quickly build a robust server infrastructure that can understand natural language commands, interact efficiently with various AI services (for speech recognition, natural language understanding, and speech synthesis), manage IoT devices, and provide a web-based user interface for system configuration and management. By integrating multiple cutting-edge technologies into a cohesive and extensible platform, this project aims to simplify and accelerate the development process of customizable voice assistants and intelligent control systems. It is not just a simple server, but a bridge connecting hardware, AI capabilities, and user management.
---
## 2. Overall Architecture
The `xiaozhi-esp32-server` system adopts a **distributed, multi-component collaborative** architectural design, ensuring modularity, maintainability, and scalability. Each core component has its specific role and works in coordination. The main components include:
1.**ESP32 Hardware (Client Device):**
This is the physical smart hardware device that end-users directly interact with. Its main responsibilities include:
* Capturing user voice commands.
* Securely sending captured raw audio data to `xiaozhi-server` for processing.
* Receiving synthesized voice responses from `xiaozhi-server` and playing them through speakers.
* Controlling other connected peripherals or IoT devices (such as smart bulbs, sensors, etc.) based on instructions received from `xiaozhi-server`.
2.**`xiaozhi-server` (Core AI Engine - Python Implementation):**
This Python-based server is the "brain" of the entire system, responsible for handling all voice-related logic and AI interactions. Its key responsibilities are detailed as follows:
* Establishing **stable, low-latency real-time bidirectional communication links** with ESP32 devices through the WebSocket protocol.
* Receiving audio streams from ESP32 and using Voice Activity Detection (VAD) technology to precisely segment valid speech segments.
* Integrating and calling Automatic Speech Recognition (ASR) services (configurable for local or cloud), converting speech segments to text.
* Interacting with Large Language Models (LLMs) to parse user intent, generate intelligent responses, and support complex natural language understanding tasks.
* Managing context information and user memory in multi-turn dialogues to provide coherent interaction experiences.
* Calling Text-to-Speech (TTS) services to synthesize natural and fluent speech from LLM-generated text responses.
* Executing custom commands through a flexible **plugin system**, including IoT device control logic.
* Obtaining its detailed runtime operation configuration from the `manager-api` service.
3.**`manager-api` (Management Backend - Java Spring Boot Implementation):**
This is an application built using the Java Spring Boot framework, providing a secure RESTful API for system management and configuration. It serves not only as the backend support for the `manager-web` console but also as the configuration data source for `xiaozhi-server`. Its core functions include:
* Providing user authentication (login, permission verification) and user account management functions for the Web console.
* Registration, information management of ESP32 devices, and maintenance of device-specific configurations.
* Persistently storing system configurations in the **MySQL database**, such as user-selected AI service providers, API keys, device parameters, plugin settings, etc.
* Providing specific API endpoints for `xiaozhi-server` to pull its required latest configuration.
* Managing TTS voice options, handling OTA (Over-The-Air) firmware update processes, and related metadata.
* Utilizing **Redis** as a high-speed cache to store hotspot data (such as session information, frequently accessed configurations) to improve API response speed and overall system performance.
4.**`manager-web` (Web Control Panel - Vue.js Implementation):**
This is a Single Page Application (SPA) built with Vue.js, providing system administrators with a graphical, user-friendly operation interface. Its main capabilities include:
* Conveniently configuring various AI services used by `xiaozhi-server` (such as ASR, LLM, TTS provider switching, parameter adjustment).
* Managing platform user accounts, role assignment, and permission control.
* Managing registered ESP32 devices and their related settings.
* (Potential functionality) Monitoring system operation status, viewing logs, troubleshooting, etc.
* Comprehensive interaction with all backend management functions provided by `manager-api`.
**High-Level Interaction Flow Overview:**
***Voice Interaction Main Line:** After the **ESP32 device** captures user voice, it transmits audio data in real-time to **`xiaozhi-server`** through **WebSocket**. After `xiaozhi-server` completes a series of AI processing (VAD, ASR, LLM interaction, TTS), it sends the synthesized voice response back to the ESP32 device for playback through WebSocket. All real-time interactions directly related to voice are completed in this link.
***Management Configuration Main Line:** Administrators access the **`manager-web`** console through a browser. `manager-web` executes various management operations (such as modifying configurations, managing users or devices) by calling **RESTful HTTP interfaces** provided by **`manager-api`**. Data is passed between them in JSON format.
***Configuration Synchronization:****`xiaozhi-server`** actively pulls its latest operation configuration from **`manager-api`** through HTTP requests when starting or when specific update mechanisms are triggered. This ensures that configuration changes made by administrators in the Web interface can be effectively applied to the operation of the core AI engine in a timely manner.
This **frontend-backend separation, core service and management service separation** architectural design allows `xiaozhi-server` to focus on efficient real-time AI processing tasks, while `manager-api` and `manager-web` together provide a powerful and easy-to-use management and configuration platform. Each component has clear responsibilities, facilitating independent development, testing, deployment, and expansion.
```
xiaozhi-esp32-server
├─ xiaozhi-server Port 8000 Python development Responsible for ESP32 communication
├─ manager-web Port 8001 Node.js+Vue development Responsible for providing web interface for console
├─ manager-api Port 8002 Java development Responsible for providing console API
└─ manager-mobile Cross-platform mobile application uni-app+Vue3 development Responsible for providing mobile console management
```
---
## 3. Component Deep Dive
### 3.1. `xiaozhi-server` (Core AI Engine - Python Implementation)
The `xiaozhi-server` is the intelligent core of the system, responsible for processing voice interactions, interfacing with AI services, and managing communication with ESP32 devices.
***Purpose:**
* To provide real-time processing of voice commands from ESP32 devices.
* To integrate with various AI services for Speech-to-Text (ASR), Natural Language Understanding (via Large Language Models - LLMs), Text-to-Speech (TTS), Voice Activity Detection (VAD), Intent Recognition, and Memory.
* To manage dialogue flow and context with users.
* To execute custom functions and control IoT devices based on user commands.
* To be dynamically configurable through the `manager-api`.
***Core Technologies:**
***Python 3:** The primary programming language.
***Asyncio:** Python's asynchronous programming framework, crucial for handling concurrent WebSocket connections and non-blocking I/O for AI service API calls.
***`websockets` Library:** For WebSocket server implementation.
***HTTP Client (e.g., `aiohttp`, `httpx`):** For asynchronous HTTP requests to `manager-api` and external AI services.
***YAML (PyYAML):** For local configuration file parsing.
***Key Implementation Aspects:**
1.**AI Service Provider Pattern (`core/providers/`):**
***Concept:** A flexible design for integrating AI services. Each service type (ASR, TTS, LLM, etc.) has an abstract base class defining a common interface. Concrete classes implement this interface for specific vendors or local models.
***Benefit:** Allows easy switching of AI service backends via configuration and simplifies adding new service integrations.
***Initialization:**`core/utils/modules_initialize.py` acts as a factory to load and instantiate configured providers.
2.**WebSocket Communication & Connection Handling (`core/websocket_server.py`, `core/connection.py`):**
***Server Setup:** Manages WebSocket connections from ESP32 devices.
***Connection Isolation:** Each ESP32 client gets a dedicated `ConnectionHandler` instance, isolating its session state and dialogue.
***Dynamic Configuration Updates:** Can fetch updated configurations from `manager-api` and re-initialize AI service modules live, without a full server restart.
* Employs a modular handler pattern. The `ConnectionHandler` dispatches message processing to specialized modules based on message type or dialogue phase (e.g., `receiveAudioHandle.py` for audio input, `intentHandler.py` for NLU, `functionHandler.py` for plugin execution, `sendAudioHandle.py` for TTS output).
4.**Plugin System for Extensible Functions (`plugins_func/`):**
***Mechanism:** Plugins define functions and schemas. The LLM can request execution of these functions (function calling). `loadplugins.py` and `register.py` manage plugin discovery and registration.
5.**Configuration Management (`config/`):**
* Loads settings from a local `config.yaml` and merges them with configurations fetched from `manager-api` (via `manage_api_client.py`), enabling remote dynamic configuration.
*`logger.py` sets up structured application logging.
*`config/assets/` stores predefined audio files for system notifications.
6.**Auxiliary HTTP Server (`core/http_server.py`):**
* Handles specific HTTP requests, notably for OTA firmware updates (`/xiaozhi/ota/`) and other utility endpoints.
### 3.2. `manager-api` (Management Backend - Java Spring Boot Implementation)
The `manager-api` component is a backend server built using Java and the Spring Boot framework, serving as the administrative hub.
***Purpose:**
* Provide a secure RESTful API for the `manager-web` frontend.
* Act as a centralized configuration provider for `xiaozhi-server`.
* Manage persistent data (users, devices, AI configurations, voice timbres, OTA firmware).
***Core Technologies:**
***Java 21 & Spring Boot 3:** Core language and framework.
***Spring MVC:** For building REST controllers.
***MyBatis-Plus:** ORM for database interaction with MySQL.
***MySQL:** Relational database.
***Druid:** JDBC connection pool.
***Redis (Spring Data Redis):** For caching.
***Apache Shiro:** Security framework for authentication and authorization.
***Liquibase:** Database schema migration.
***Knife4j:** OpenAPI (Swagger) API documentation.
***Maven:** Build and dependency management.
***Key Implementation Aspects:**
1.**Modular Architecture (`modules/` package):**
* Business logic is organized into distinct modules (e.g., `sys` for users/roles, `agent` for assistant configs, `device` for ESP32s, `config` for `xiaozhi-server` settings, `security`, `timbre`, `ota`).
* Each module typically follows a layered pattern: Controller, Service, DAO (Mapper), Entity, DTO.
2.**Layered Architecture:**
***Controller Layer (`@RestController`):** Defines API endpoints, handles HTTP request/response.
***Service Layer (`@Service`):** Contains business logic, transaction management.
***Data Access Layer (MyBatis-Plus Mappers):** Interacts with the MySQL database.
3.**Common Functionalities (`common/` package):**
* Provides shared code: base classes, global configurations (Spring, MyBatis, Redis, Knife4j), custom annotations (e.g., `@LogOperation`), AOP aspects, global exception handling, utility classes, and XSS protection.
4.**Security (Apache Shiro):**
* Manages user authentication and permissions for accessing API endpoints. Configured with Shiro Realms and security filters.
5.**Database Schema Management (Liquibase):**
* Ensures consistent database structure across environments through versioned schema changes.
### 3.3. `manager-web` (Web Control Panel - Vue.js Implementation)
The `manager-web` is a Single Page Application (SPA) providing the administrative user interface.
***Purpose:**
* Offer a web-based control panel for system configuration and management.
* Enable administrators to configure `xiaozhi-server`'s AI services, manage users and devices, customize voice timbres, and handle OTA updates.
***Vue Router:** For client-side routing within the SPA.
***Vuex:** For centralized state management.
***Element UI:** UI component library for a consistent look and feel.
***SCSS:** CSS preprocessor.
***HTTP Client (Flyio or Axios):** For API calls to `manager-api`.
***Workbox:** For PWA features (caching, service worker).
***Opus Libraries:** For potential in-browser audio recording/playback.
***Key Implementation Aspects:**
1.**SPA Structure:** Single HTML page with dynamic view updates.
2.**Component-Based Architecture:** UI built from reusable Vue components (`.vue` files in `src/views/` for pages and `src/components/` for smaller elements).
3.**Client-Side Routing (`src/router/index.js`):** Maps browser URLs to view components, with route guards for authentication.
4.**State Management (`src/store/index.js`):** Vuex manages global state (user info, device lists, etc.) via state, getters, mutations, and actions (often involving API calls).
5.**API Communication (`src/apis/`):** Modularized API service files make asynchronous calls to `manager-api`.
6.**Build Process & PWA Features:** Vue CLI (Webpack) bundles assets. Workbox enables PWA features like caching.
7.**Environment Configuration (`.env` files):**
* The `.env` (and `.env.development`, `.env.production`, etc.) files in the project root directory are used to define environment variables. These variables (such as `VUE_APP_API_BASE_URL` to specify the base URL of `manager-api`) can be accessed in the application code through `process.env.VUE_APP_XXX`, allowing configuration of different parameters for different build environments (development, testing, production).
`manager-web` constructs a powerful, maintainable, and user-friendly management interface through the comprehensive application of these technologies, providing solid frontend support for the configuration and monitoring of the `xiaozhi-esp32-server` system.
The `manager-mobile` component is a cross-platform mobile management application based on uni-app v3 + Vue 3 + Vite, supporting App (Android & iOS) and WeChat Mini Program. It provides system administrators with a mobile management interface, making management operations more convenient.
***Core Objectives:**
* Provide a convenient management interface on mobile devices, similar in functionality to manager-web but optimized for mobile platforms.
* Support core functions such as user login, device management, and AI service configuration.
* Cross-platform adaptation, allowing a single codebase to run on iOS, Android, and WeChat Mini Programs.
* Provide mobile users with a smooth and efficient management experience.
***Platform Compatibility:**
| H5 | iOS | Android | WeChat Mini Program |
| -- | --- | ------- | ------------------ |
| × | √ | √ | √ |
***Core Technologies:**
***uni-app v3:** A framework for developing all frontend applications using Vue.js, supporting iOS, Android, H5, and various mini-programs.
***Vue 3:** A progressive framework for building user interfaces, providing better performance and new features.
***Vite:** The next generation frontend development and build tool, offering an extremely fast development experience.
***pnpm:** A fast, disk space-efficient package manager.
***alova:** A lightweight, flexible request strategy library, paired with @alova/adapter-uniapp to adapt to the uni-app environment.
***pinia:** State management library for Vue, replacing Vuex, providing a simpler API and better TypeScript support.
***UnoCSS:** A high-performance and extremely flexible instant atomic CSS engine.
***TypeScript:** Provides a type-safe development experience.
***Key Implementation Details:**
1.**Cross-Platform Architecture:**
* Based on the uni-app framework, achieving the goal of "write once, run anywhere," significantly reducing development and maintenance costs.
* Handling platform-specific code through conditional compilation to address the characteristics and limitations of different platforms.
2.**Project Structure:**
***`src/App.vue`:** The root component of the application, defining global styles and configurations.
***`src/main.ts`:** The entry file of the application, responsible for initializing the Vue instance, registering plugins, and setting up route interceptors.
***`src/pages/`:** Stores application page components, such as login pages, device management pages, etc.
***`src/layouts/`:** Defines application layout components, such as default layouts, layouts with tabbar, etc.
***`src/api/`:** Encapsulates communication logic with backend APIs.
***`src/store/`:** Uses pinia for state management.
***`src/utils/`:** Provides common utility functions.
3.**Network Requests:**
* Implements network requests based on alova + @alova/adapter-uniapp, unified handling of request headers, authentication, errors, etc.
* Request addresses and environment configurations are managed through .env files, supporting switching between different environments.
4.**Routing and Authentication:**
* Uses uni-app's routing system, combined with route interceptors to implement page login verification and permission control.
* When unlogged users access pages requiring authentication, they are redirected to the login page.
5.**State Management:**
* Uses pinia to manage application state, such as user information, device lists, etc.
* Implements persistent storage of state through the pinia-plugin-persistedstate plugin.
6.**Build and Release:**
* Supports multiple build commands, such as building WeChat Mini Programs, Android, and iOS Apps.
* Uses HBuilderX for cloud packaging of Apps, simplifying the packaging process.
`manager-mobile` provides users with a fully functional, smooth mobile management tool through the application of these technologies, allowing administrators to perform system management and configuration anytime, anywhere.
---
## 4. Data Flow and Interaction Mechanisms
The `xiaozhi-esp32-server` system coordinates work through well-defined data flows and interaction protocols between components. The main communication methods rely on WebSocket protocol optimized for real-time interaction and RESTful API suitable for client-server requests.
This flow is real-time, primarily using WebSocket for low-latency, bidirectional data exchange.
***Communication Protocol Documentation:**
* Detailed communication protocol documentation can be accessed at: https://ccnphfhqs21z.feishu.cn/wiki/M0XiwldO9iJwHikpXD5cEx71nKh
* This document details the WebSocket communication protocol between ESP32 devices and `xiaozhi-server`, including:
* Connection establishment and handshake process
* Audio data transmission format
* Control command format
* Status report format
* Error handling mechanism
***Connection Establishment and Handshake:**
* The ESP32 device, as a client, actively initiates a WebSocket connection request to the specified endpoint of `xiaozhi-server` (e.g., `ws://<server-IP>:<WebSocket-port>/xiaozhi/v1/`).
*`xiaozhi-server` (`core/websocket_server.py`) receives the connection and instantiates an independent `ConnectionHandler` object for each successfully connected ESP32 device to manage the entire lifecycle of that session.
* After the connection is established, an initial handshake process may be executed (handled by `core/handle/helloHandle.py`) to exchange device identification, authentication information, protocol version, or basic status.
***VAD (Voice Activity Detection):**`receiveAudioHandle.py` uses the configured VAD provider (such as SileroVAD) to analyze the audio stream, accurately identifying the start and end points of speech, filtering out silent or noise segments.
***ASR (Automatic Speech Recognition):** Detected valid speech segments are sent to the configured ASR provider (local such as FunASR, or cloud services). The ASR engine converts audio signals into text strings.
***NLU/LLM (Natural Language Understanding/Large Language Model):** The ASR output text, along with the current dialogue context history obtained from the Memory provider, and the description schemas of available functions (tools) loaded from `plugins_func/`, are passed to the configured LLM provider.
***Function Call Execution (if LLM decides needed):** If the LLM analysis determines that an external function needs to be called (e.g., querying weather, controlling home appliances), it generates a structured function call request. `core/handle/functionHandler.py` receives this request, finds and executes the corresponding Python function defined in `plugins_func/`, and returns the function's execution result to the LLM. The LLM then generates the final natural language response based on this result.
***Response Generation:** The LLM synthesizes all information (user input, context, function call results, etc.) to generate the final text response.
***Memory Update:** The current round of interaction (user question, LLM response, possible function calls) is processed by the Memory provider to update the dialogue history for subsequent interactions.
***TTS (Text-to-Speech):** The final text response generated by the LLM is sent to the configured TTS provider, which synthesizes the text into a speech data stream (e.g., MP3 or WAV format).
* The speech data stream synthesized by the TTS provider is sent in real-time as WebSocket **binary messages** back to the ESP32 device through the `core/handle/sendAudioHandle.py` module.
* The ESP32 device receives these audio data chunks and immediately plays them to the user through the speaker.
***Control and Status Messages (Bidirectional):**
* In addition to audio streams, ESP32 and `xiaozhi-server` also exchange **text messages** through WebSocket, these messages are usually encapsulated in JSON format.
***ESP32 -> Server:** The device may send status reports (such as network conditions, microphone status), error codes, or specific control commands (e.g., "stop TTS playback" triggered by user button press).
***Server -> ESP32:** The server may send control instructions to the device (such as "start listening", "stop listening", adjust sensitivity, send specific configuration parameters).
* Modules like `core/handle/abortHandle.py` (handling interrupt requests), `core/handle/reportHandle.py` (handling device reports) are responsible for parsing and responding to these control/status messages.
**4.2. Management and Configuration Flow (`manager-web` <-> `manager-api` <-> `xiaozhi-server`)**
This flow primarily relies on HTTP/HTTPS-based RESTful API for request-response interactions.
* When administrators perform operations in the `manager-web` interface (e.g., saving a configuration, adding a new user, registering an ESP32 device):
* The Vue.js frontend application (`manager-web`) will initiate asynchronous HTTP requests (usually GET, POST, PUT, DELETE) to the corresponding REST API endpoints of `manager-api` through its API encapsulation module (located in `src/apis/module/`).
* Request and response bodies typically use JSON format.
* The `@RestController` classes in `manager-api` receive these requests. The **Apache Shiro** framework will first perform authentication and authorization checks on the requests.
* After verification, the Controller distributes the request to the corresponding Service layer to handle business logic. The Service layer may interact with the MySQL database (through MyBatis-Plus) and may utilize Redis for data caching.
* After processing, `manager-api` returns an HTTP response in JSON format to `manager-web`.
*`manager-web` updates its Vuex state store and user interface display based on the response results.
* The operation of `xiaozhi-server` depends on dynamic configurations obtained from `manager-api` (such as currently selected AI service providers and their API keys).
***Pull Mechanism:** The `config/manage_api_client.py` module within `xiaozhi-server`, when the server starts or through specific update triggers (e.g., when `WebSocketServer.update_config()` is called), will initiate an HTTP GET request to a specified endpoint of `manager-api` (e.g., provided by a Controller in `modules/config/controller/`).
*`manager-api` responds to this request, returning the configuration data required by `xiaozhi-server` (in JSON format).
* After receiving the configuration, `xiaozhi-server` will update its internal state and may reinitialize relevant AI service modules to make the new configuration effective.
* Administrators upload new ESP32 firmware packages to specific endpoints of `manager-api` through the `manager-web` interface.
*`manager-api` stores the firmware files and records related metadata (version number, applicable device models, etc.).
* When administrators trigger OTA updates for specific devices:
*`manager-api` may notify `xiaozhi-server` (the specific notification mechanism may be a polling checkpoint, or `xiaozhi-server` exposes an API to receive update notifications, or more loosely coupled like message queues).
*`xiaozhi-server` can then send an instruction message containing the firmware download URL to the target ESP32 device through WebSocket.
* After receiving the instruction, the ESP32 device downloads the firmware through an HTTP GET request from that URL. This URL may point to a path served by the `SimpleHttpServer` running on `xiaozhi-server` itself (such as `/xiaozhi/ota/`), or in some architectures, it may directly point to `manager-api` or a dedicated file server.
**4.3. Main Protocol Summary:**
***WebSocket:** Selected for the communication link between ESP32 and `xiaozhi-server` because it is very suitable for real-time, low-latency, bidirectional data stream transmission (especially audio), as well as asynchronous control message delivery.
***RESTful APIs (based on HTTP/HTTPS, usually using JSON as the data exchange format):** This is the standard way for web service communication. Used for request-response interactions between `manager-web` (client) and `manager-api` (server), and also for `xiaozhi-server` (as client) to pull configuration information from `manager-api` (as server). Its stateless nature, wide library support, and easy-to-understand semantics make it an ideal choice for such interactions.
This multi-protocol communication strategy ensures that different types of interaction requirements within the system can be handled efficiently and appropriately, balancing real-time performance and standardized request-response patterns.
---
## 5. Key Features Summary
The `xiaozhi-esp32-server` system provides a series of rich features aimed at supporting developers in building advanced voice control applications:
1.**Comprehensive Voice Interaction Backend:** Provides an end-to-end solution from voice capture guidance to response generation and action execution.
2.**Modular and Pluggable AI Services:**
* Supports a wide range of ASR (Automatic Speech Recognition), LLM (Large Language Model), TTS (Text-to-Speech), VAD (Voice Activity Detection), Intent Recognition, and Memory providers.
* Allows dynamic selection and configuration of these services (including cloud-based APIs and local models) to balance cost, performance, privacy, and language requirements.
3.**Advanced Dialogue Management:**
* Supports natural interaction, with wake word to start dialogue, manual (push-to-talk) dialogue, and real-time interruption of system responses.
* Includes contextual memory to maintain coherence in multi-turn dialogues.
* Has automatic sleep mode after a period of inactivity.
4.**Multi-language Capabilities:**
* Supports recognition and synthesis in multiple languages, including Mandarin, Cantonese, English, Japanese, and Korean (specific capabilities depend on the selected ASR/LLM/TTS providers).
5.**Extensible Functions through Plugins:**
* Powerful plugin system allows developers to add custom "skills" or functions (e.g., getting weather, controlling smart home devices, accessing news).
* These functions can be triggered by the LLM using its function calling capability, based on provided schemas.
* Built-in support for Home Assistant integration.
6.**IoT Device Control:**
* Designed to manage and control smart home devices and other IoT hardware through voice commands, utilizing the plugin system.
* Provides a comprehensive graphical interface for:
* System configuration (AI service selection, API keys, operation parameters).
* Role-based access control user management.
* ESP32 device registration and management.
* Voice timbre/TTS voice customization.
* OTA (Over-The-Air) firmware update management for ESP32 devices.
* System parameter and dictionary management.
8.**Flexible Deployment Options:**
* Supports deployment through Docker containers (for simplified server-only or full-stack setup) and directly from source code, adapting to various environments and user expertise.
9.**Dynamic Remote Configuration:**
*`xiaozhi-server` can obtain its configuration from `manager-api`, allowing real-time updates of AI providers and settings without restarting the server.
10.**Open Source and Community-Driven:**
* Licensed under MIT License, encouraging transparency, collaboration, and community contribution.
11.**Cost-Effective Solution:**
* Provides an "Entry Level Free Settings" path, utilizing free tiers of AI services or local models, making it easy to experiment and for personal projects.
12.**Progressive Web Application (PWA) Features:**
* The `manager-web` control panel includes Service Worker integration to enhance caching and potential offline access capabilities.
13.**Detailed API Documentation:**
*`manager-api` provides OpenAPI (Swagger) documentation through Knife4j for clear understanding and testing of its RESTful endpoints.
These features together make `xiaozhi-esp32-server` a powerful, adaptable, and user-friendly platform for building complex voice interaction applications.
---
## 6. Deployment and Configuration Overview
The `xiaozhi-esp32-server` system is designed with flexibility in mind, providing multiple deployment methods and comprehensive configuration options to adapt to different usage scenarios and requirements.
**Deployment Options:**
The project can be deployed in multiple ways, mainly including using Docker to simplify the installation process, or deploying directly from source code for greater control and development.
1.**Docker-based Deployment:**
***Simplified Installation (Only `xiaozhi-server`):** This option only deploys the core Python-based `xiaozhi-server`. It is suitable for users who mainly need voice AI processing capabilities and IoT control, without requiring the complete Web management interface and database support functions (such as OTA). In this mode, configuration is typically managed through local files (`config.yaml`), but if needed, it can still point to an existing `manager-api` instance.
***Full Module Installation (All Components):** This scheme deploys all core components: `xiaozhi-server`, Java-based `manager-api`, and Vue.js-based `manager-web`, along with required database services (MySQL and Redis). This provides a complete system experience, including a Web control panel for comprehensive configuration and management.
* The project provides `Dockerfile` definitions for each service and uses `docker-compose.yml` files (e.g., `docker-compose.yml` for basic version, `docker-compose_all.yml` for full-featured version) to orchestrate and manage multi-container deployment. Additionally, a `docker-setup.sh` script may be provided to assist in automating part of the Docker environment setup work.
2.**Source Code Deployment:**
* This method requires manual setup of the corresponding development environment for each component: Python environment for `xiaozhi-server`, Java/Maven environment for `manager-api`, Node.js/Vue CLI environment for `manager-web`.
* For full module installation, MySQL and Redis database services also need to be manually installed and configured.
* This approach is typically used for project development, deep customization, debugging, or in production scenarios with special environmental requirements.
**Configuration Management:**
Configuration is key to customizing system behavior, especially in selecting AI service providers and managing API keys.
1.**`xiaozhi-server` Configuration:**
***Local `config.yaml`:** A main YAML format configuration file located in the `xiaozhi-server` root directory. It defines server ports, selected AI service providers (ASR, LLM, TTS, VAD, Intent Recognition, Memory modules, etc.), their respective API keys or model paths, plugin configurations, and log levels.
***Remote Configuration through `manager-api`:**`xiaozhi-server` is designed to obtain its operation configuration from `manager-api`. Settings obtained from `manager-api` typically override settings with the same name in the local `config.yaml`. This brings two major benefits:
***Centralized Management:** All configurations can be managed uniformly through the `manager-web` interface.
***Dynamic Updates:**`xiaozhi-server` can refresh its configuration and reinitialize AI modules without completely restarting the service.
*`config/config_loader.py` and `config/manage_api_client.py` in `xiaozhi-server` are responsible for handling configuration loading, merging, and pulling logic from `manager-api`.
2.**`manager-api` Configuration:**
* As a Spring Boot application, its configuration is mainly managed through the `application.properties` or `application.yml` file located in the `src/main/resources` directory.
* Key configuration items include: database connection information (MySQL URL, username, password), Redis server address and port, application service port (default 8002), Apache Shiro security-related settings, and configuration parameters for any integrated third-party services (such as Aliyun SMS).
3.**`manager-web` Configuration:**
* Environment-specific settings for the Vue.js frontend application are managed through `.env` series files (e.g., `.env`, `.env.development`, `.env.production`) in the project root directory.
* The most critical configuration here is usually the API base URL address of the `manager-api` backend (e.g., `VUE_APP_API_BASE_URL`), to which the frontend application will send all API requests.
4.**Predefined Configuration Schemes:**
* The project documentation (usually README) will recommend some common configuration combinations, for example:
***"Entry Level Free Settings":** This scheme aims to utilize free tier quotas of cloud AI services or completely free local models to minimize users' initial usage costs and operating expenses.
***"Full Streaming Configuration":** This scheme prioritizes system response speed and interaction fluency, typically choosing AI services that support streaming processing (possibly paid).
* These predefined schemes provide guidance for users to configure AI service providers in `xiaozhi-server` (through the `manager-web` interface or directly modifying `config.yaml`).
In the case of full module deployment, it is recommended to use the `manager-web` control panel as the main operation interface for most configuration tasks, as it provides a user-friendly way to manage various settings that are persisted by `manager-api` and ultimately used by `xiaozhi-server`.
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.