[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-897":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":15,"forks30d":15,"starsTrendScore":19,"compositeScore":20,"rankGlobal":10,"rankLanguage":10,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":24,"hasPages":24,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":33,"readmeContent":34,"aiSummary":35,"trendingCount":15,"starSnapshotCount":15,"syncStatus":36,"lastSyncTime":37,"discoverSource":38},897,"hi-kid","xiaochong\u002Fhi-kid","xiaochong","HiKid - Your AI English Pal. A desktop app built with React and TypeScript, targeting children in non-English-speaking countries who want to practice English speaking and listening.","https:\u002F\u002Fxiaochong.github.io\u002Fhi-kid",null,"TypeScript",934,108,7,0,25,52,279,75,10.11,"MIT License",false,"main",true,[26,27,28,29,30,31,32],"ai","english-learning","kids-education","local-ai","offline-ai","speaking-practice","voice-chat","2026-06-12 02:00:20","**English** | [简体中文](README-cn.md)\n\n# 🎈 HiKid\n\n> _Hi! I'm your AI English Pal. Let's talk!_\n\n[![Electron](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FElectron-47848F?style=flat-square&logo=electron&logoColor=white)](https:\u002F\u002Fwww.electronjs.org\u002F)\n[![React](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FReact-61DAFB?style=flat-square&logo=react&logoColor=black)](https:\u002F\u002Freact.dev\u002F)\n[![TypeScript](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FTypeScript-3178C6?style=flat-square&logo=typescript&logoColor=white)](https:\u002F\u002Fwww.typescriptlang.org\u002F)\n\n---\n\n## 🌟 What is this?\n\nHiKid is a **completely free, forever free** open-source desktop app designed for **kids in non-English-speaking countries** to practice English speaking and listening.\n\nSay \"Hello\" into the microphone, and it will chat with you in English, tell stories, and play word games — all completely offline. All data and AI run locally on your machine, nothing is uploaded to the cloud.\n\n- 🗣️ **Just start talking** — no typing needed, speak directly and the AI understands\n- 🧠 **Smart and patient** — talk about anything, it doesn't matter if you speak slowly or simply\n- 🎨 **Looks like a cartoon** — cute interface that kids will love\n- 🔒 **Privacy safe** — conversations, voice, and models all run locally\n- 🌏 **Works without internet** — recording, recognition, synthesis, and dialogue all run through a local pipeline\n\n> 🍎 **Currently macOS only.** Windows and Linux versions are planned — contributions welcome!\n\n![](resources\u002Fpreview1.png)\n\n![](resources\u002Fpreview2.png)\n\n## 🚀 Quick Start\n\n### Requirements\n\n- macOS 12.0+ (Apple Silicon \u002F Intel)\n- Node.js >= 20\n- npm\n\n### Install\n\n```bash\n# 1. Clone the repo\ngit clone https:\u002F\u002Fgithub.com\u002Fxiaochong\u002Fhi-kid.git\ncd hi-kid\n\n# 2. Install dependencies\nnpm install\n```\n\n### Development\n\n```bash\n# Start dev server with hot reload\nnpm run dev\n\n# Type check\nnpm run typecheck\n\n# Format code\nnpm run format\n```\n\n### Build\n\n```bash\n# All platforms\nnpm run build\n\n# macOS\nnpm run build:mac\n\n# Unpacked output (no installer)\nnpm run build:unpack\n```\n\n> For detailed external dependency installation (SoX, ASR\u002FTTS servers, model files, etc.), see [INSTALL.md](INSTALL.md).\n\n## 🏗️ Architecture\n\nHiKid's voice conversation runs through a complete **local pipeline**:\n\n```\nUser speaks → SoX(rec) recording + VAD detection ──→ ASR server speech-to-text\n                                                  ↓\nSoX(play) plays PCM audio ←─ TTS server speech synthesis ←─ LLM generates reply\n```\n\n| Component             | Role                                                              |\n| --------------------- | ----------------------------------------------------------------- |\n| **SoX**               | Audio recording, playback, format conversion, and analysis        |\n| **kitten-tts-server** | Local text-to-speech (TTS), streams PCM over SSE                  |\n| **asr-server**        | Local automatic speech recognition (ASR), based on Qwen3-ASR-0.6B |\n| **Ollama**            | Local large language model, default `qwen3:0.6b`                  |\n\nProject structure:\n\n```\nsrc\u002F\n├── main\u002F          # Electron main process\n├── preload\u002F       # Preload scripts (IPC bridge)\n└── renderer\u002F      # React renderer process\n```\n\n## 🤝 Contributing\n\nIssues and PRs are welcome!\n\n- `dev` is the active development branch\n- `main` is the stable branch for merging PRs\n- Please run `npm run lint` and `npm run typecheck` before submitting\n\n## 🙏 Acknowledgments\n\nHiKid stands on the shoulders of giants:\n\n| Project                                                                                  | Purpose                                           |\n| ---------------------------------------------------------------------------------------- | ------------------------------------------------- |\n| [Electron](https:\u002F\u002Fwww.electronjs.org\u002F)                                                  | Cross-platform desktop app framework              |\n| [React](https:\u002F\u002Freact.dev\u002F)                                                              | UI building                                       |\n| [Vite](https:\u002F\u002Fvitejs.dev\u002F)                                                              | Fast build tool                                   |\n| [@mariozechner\u002Fpi-agent-core](https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002F@mariozechner\u002Fpi-agent-core) | Agent orchestration and event streaming framework |\n| [kitten-tts-server](https:\u002F\u002Fgithub.com\u002Fsecond-state\u002Fkitten_tts_rs)                       | Local speech synthesis engine                     |\n| [Qwen3-ASR-0.6B](https:\u002F\u002Fgithub.com\u002FQwenLM\u002FQwen3)                                        | Local speech recognition model                    |\n| [Ollama](https:\u002F\u002Follama.com\u002F)                                                            | Local LLM runtime                                 |\n| [animal-island-ui](https:\u002F\u002Fgithub.com\u002Fguokaigdg\u002Fanimal-island-ui)                        | Cute UI components                                |\n\nAnd to all the developers who indirectly depend on them — thank you for making the open-source world so wonderful!\n\n## ⚠️ Disclaimer\n\n- This project is for personal learning, research, and non-commercial demonstration only. Commercial use, resale, or profit-making in any form is prohibited.\n- The UI component library [animal-island-ui](https:\u002F\u002Fgithub.com\u002Fguokaigdg\u002Fanimal-island-ui) used by this project draws visual design inspiration from classic game styles, but all materials and styles are for design reference only and do not constitute copying or infringement of the original works.\n\n## 📄 License\n\nMIT\n\n---\n\n\u003Cp align=\"center\">\n  Made with  ❤️ for kids around the world\n\u003C\u002Fp>\n","HiKid 是一款专为非英语国家儿童设计的桌面应用，旨在帮助他们练习英语听说能力。该应用使用 React 和 TypeScript 构建，核心功能包括通过麦克风与 AI 互动聊天、讲故事和玩单词游戏，所有操作均在本地完成，无需联网。其界面卡通可爱，易于吸引儿童注意；同时强调隐私保护，所有数据处理都在用户设备上进行，确保安全。适用于希望提高孩子英语交流能力的家庭或教育机构，目前仅支持 macOS 平台，但计划推出 Windows 和 Linux 版本。",2,"2026-06-11 02:40:06","CREATED_QUERY"]