TOM88812/xiaozhi-android-client

一个基于小智、xiaozhi-server的Android、IOS语音对话应用,支持实时语音交互和文字对话。现在是flutter版本，打通IOS、Android端。请同志们动动小手，点点小星星，予以鼓励。

What it solves

This project provides a comprehensive set of clients for the Xiaozhi AI assistant, enabling real-time voice and text interaction across a wide variety of platforms and hardware. It bridges the gap between AI backends and end-user devices, specifically targeting AI hardware terminals, smart home hubs, and cross-platform mobile/desktop applications.

How it works

The project is split into two primary product lines:

  • V1 Native Clients: Developed natively for Android and HarmonyOS NEXT. These are optimized for low power consumption and fast startup, specifically designed for AI hardware, foldable screens, and secondary screens.
  • V3 Commercial Version: A cross-platform client built with Flutter, supporting Android, iOS, HarmonyOS, Web, Windows, macOS, and Linux. It integrates deeply with a proprietary server-side backend to provide a full-featured experience.

Both versions support real-time voice interaction with the ability to interrupt the AI, and they can synchronize memory and data across different hardware devices.

Who it’s for

  • AI Hardware Developers: Those building AI desktop terminals, smart speakers, or companion devices.
  • End Users: People wanting a cross-platform AI assistant with voice capabilities on their phones or computers.
  • Companies: Businesses looking for a professional, integrated AI agent client with commercial-grade server support.

Highlights

  • Multi-Platform Support: Covers almost every major OS including mobile, desktop, and HarmonyOS.
  • Real-Time Voice Interaction: Supports low-latency voice dialogue with real-time interruption capabilities.
  • Advanced Visuals: Integration of Live2D and 3D models that can express emotions, sing, and dance based on AI triggers.
  • Extensible AI Capabilities: Supports OpenAI's thinking mode, web search, HTML code preview, and MCP (Model Context Protocol) for custom tool calling.
  • Hardware Integration: Specifically designed to work with AI hardware and IoT control, allowing the client to act as a central hub.

Related

  • Project
    MeetKai/functionary

    Functionary is a language model specialized in interpreting and executing functions and plugins, supporting parallel tool calls and a built-in code interpreter.

  • Project
    supermemoryai/opencode-supermemory

    An OpenCode plugin that integrates Supermemory to give AI agents persistent, cross-session memory of user preferences and project knowledge.

  • Project
    datagouv/datagouv-mcp

    An MCP server that enables AI chatbots to search, explore, and analyze French national open data from data.gouv.fr through natural language conversations.

  • Project
    actionbook/actionbook

    An AI browser agent that uses a Chrome extension and MCP connector to operate websites concurrently and access data behind logins to deliver finished work.