[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tool-superstarryeyes--lue":3,"similar-superstarryeyes--lue":129},{"id":4,"github_repo":5,"name":6,"description_en":7,"description_zh":8,"ai_summary_zh":8,"readme_en":9,"readme_zh":10,"quickstart_zh":11,"use_case_zh":12,"hero_image_url":13,"owner_login":14,"owner_name":15,"owner_avatar_url":16,"owner_bio":17,"owner_company":18,"owner_location":19,"owner_email":20,"owner_twitter":14,"owner_website":18,"owner_url":21,"languages":22,"stars":27,"forks":28,"last_commit_at":29,"license":30,"difficulty_score":31,"env_os":32,"env_gpu":33,"env_ram":33,"env_deps":34,"category_tags":40,"github_topics":43,"view_count":58,"oss_zip_url":18,"oss_zip_packed_at":18,"status":59,"created_at":60,"updated_at":61,"faqs":62,"releases":93},1076,"superstarryeyes\u002Flue","lue","Terminal eBook Reader with Audiobook-Quality Text-to-Speech — Supports EPUB, PDF, DOCX, HTML, RTF, TXT, and MD.","Lue 是一款专为终端环境设计的电子书阅读器，支持 EPUB、PDF、DOCX 等多种文档格式，并内置高质量文本转语音功能。它通过语音朗读帮助用户更高效地阅读，同时提供自动滚动、精准词汇高亮、进度保存等特性，提升阅读专注力。对于需要在终端进行深度工作的人群，Lue 以轻量级设计减少干扰，实现沉浸式阅读体验。\n\n传统电子书阅读器常受限于界面复杂或语音功能不足，而 Lue 通过模块化 TTS 系统（支持 Edge TTS 和本地离线引擎）解决了跨平台语音朗读需求，同时兼容 macOS、Linux 和 Windows（WSL）。其高度可定制的键盘布局和 UI 设置，让开发者和终端爱好者能根据习惯调整操作方式。对于需要多格式文档处理的用户，如研究人员、学生或自由职业者，Lue 的智能持久化和快速导航功能能显著提升效率。项目采用 GPL 协议开源，鼓励社区扩展功能，是追求高效、灵活阅读体验的用户理想选择。","\u003Cdiv align=\"center\">\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fsuperstarryeyes_lue_readme_141871db2171.png\" alt=\"Lue Icon\" width=\"35%\" \u002F>\n\n### Lue - Terminal eBook Reader with Text-to-Speech\n[![License: GPL v3+](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-GPLv3+-86c9fa.svg)](https:\u002F\u002Fwww.gnu.org\u002Flicenses\u002Fgpl-3.0)\n[![Python](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpython-3.10+-86c9fa.svg)](https:\u002F\u002Fwww.python.org\u002Fdownloads\u002F)\n[![Platform](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fplatform-macOS%20%7C%20Linux%20%7C%20Windows%20(WSL)-86c9fa)](https:\u002F\u002Fgithub.com\u002Fsuperstarryeyes\u002Flue)\n[![Terminal](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Finterface-terminal-86c9fa.svg)](https:\u002F\u002Fgithub.com\u002Fsuperstarryeyes\u002Flue)\n[![Discord](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Join%20our%20Community-5865F2?logo=discord&logoColor=white)](https:\u002F\u002Fdiscord.gg\u002Fz8sE2gnMNk)\n\n[Features](#-features) • [Quick Start](#-quick-start-macos-and-linux) • [Installation](#-installation-macos-linux-and-windows) • [Usage](#-usage) • [Customize](#️-customize) • [Development](#-development)\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fsuperstarryeyes_lue_readme_500cb5b24cd0.gif\" alt=\"Lue Screenshot\" width=\"100%\" \u002F>\n\n\u003C\u002Fdiv>\n\n---\n\n## ✨ Features\n\n| **Feature**                             | **Description**                                                                                |\n| --------------------------------------- | ---------------------------------------------------------------------------------------------- |\n| **📖 Multi-Format Support**             | Support for EPUB, PDF, TXT, DOCX, DOC, HTML, RTF, and Markdown with seamless format detection  |\n| **👄 Modular TTS System**               | Edge TTS (default) and Kokoro TTS (local\u002Foffline) with extensible architecture for new models  |\n| **🌍 Cross-Platform & Multilingual**    | Full support for macOS, Linux, Windows (via WSL) with 100+ languages and consistent global experience    |\n| **🎛️ Speed Adjustment**                 | Adjust text-to-speech playback speed from 1x to 3x for personalized listening experience       |\n| **🎯 Auto-Scroll & Precise Word Highlighting**        | Automatic scrolling and word-level highlighting synchronized with actual speech, improving focus and concentration     |\n| **💾 Smart Persistence**                | Automatic progress saving, state restoration, and cross-session continuity for seamless reading|\n| **⚡️ Fast Navigation**                  | Intuitive shortcuts, flexible controls, mouse support and optional smooth scrolling for efficient book navigation     |\n| **⚙️ Extensive Customization**          | Fully customizable keyboard layouts (including Vim-style bindings), adjustable UI elements, colors, and display modes|\n\n---\n\n## 🚀 Quick Start (macOS and Linux)\n\n> **Want to try Lue right away?** Follow these simple steps:\n\n```bash\n# 1. Install FFmpeg (required for audio processing)\n# macOS\nbrew install ffmpeg\n# Ubuntu\u002FDebian  \nsudo apt install ffmpeg\n\n# 2. Install the latest version from PyPI\npip install lue-reader \n\n# 3. Practice using Lue with the navigation guide\nlue --guide\n\n# 4. Start reading!\nlue path\u002Fto\u002Fyour\u002Fbook.epub \n```\n\n> **📝 Note:** Quick start uses Edge TTS (requires internet). For offline capabilities, see [full installation](#-installation-macos-linux-and-windows).\n\n---\n\n## 📦 Installation (macOS, Linux and Windows)\n\n### Prerequisites\n\n#### Core Requirements\n- **FFmpeg** - Audio processing (required)\n\n#### Optional Dependencies  \n- **espeak** - Kokoro TTS support\n\n#### macOS (Homebrew)\n```bash\nbrew install ffmpeg\n# Optional\nbrew install espeak\n```\n\n#### Ubuntu\u002FDebian\n```bash\nsudo apt update && sudo apt install ffmpeg\n# Optional  \nsudo apt install espeak\n```\n\n#### Arch Linux (AUR)\n```bash\n# Using yay\nyay -S lue-reader-git\n\n# Or using paru\nparu -S lue-reader-git\n```\n\n#### Windows\n```bash\n# 1. Install WSL\n# Open PowerShell as Administrator:\nwsl --install\n\n# 2. Restart your PC if prompted, then launch Ubuntu from Start Menu\n\n# 3. Inside Ubuntu terminal:\nsudo apt update && sudo apt upgrade -y\nsudo apt install ffmpeg python3 python3-pip -y\n# Optional  \nsudo apt install espeak\n```\n\n### Install Lue\n\n#### Standard Installation\n\n```bash\n# 1. Clone repository\ngit clone https:\u002F\u002Fgithub.com\u002Fsuperstarryeyes\u002Flue.git\ncd lue\n\n# 2. Install dependencies\npip install -r requirements.txt\n\n# 3. Install Lue\npip install .\n```\n\n#### Enable Kokoro TTS (Optional)\n\nFor local\u002Foffline TTS capabilities:\n\n```bash\n# 1. Edit requirements.txt - uncomment Kokoro packages:\nkokoro>=0.9.4\nsoundfile>=0.13.1\nhuggingface-hub>=0.34.4\n\n# 2. Install PyTorch\n# CPU version:\npip install torch torchvision torchaudio\n# GPU version (CUDA):\npip install torch torchvision torchaudio --index-url https:\u002F\u002Fdownload.pytorch.org\u002Fwhl\u002Fcu121\n\n# 3. Install updated requirements\npip install -r requirements.txt\n\n# 4. Install Lue\npip install .\n```\n\n---\n\n## 💻 Usage\n\n### Basic Commands\n\n```bash\n# Start with default TTS\nlue path\u002Fto\u002Fyour\u002Fbook.epub\n\n# Launch without arguments to open the last book you were reading\nlue\n\n# Practice Lue default keys with the navigation guide\nlue --guide\n\n# View available command line options\nlue --help\n\n# Use specific TTS model (edge\u002Fkokoro\u002Fnone) \nlue --tts kokoro path\u002Fto\u002Fyour\u002Fbook.epub\n\n# Use a specific voice (full list at VOICES.md)\nlue --voice \"en-US-AriaNeural\" path\u002Fto\u002Fyour\u002Fbook.epub\n\n# Set the speech speed (e.g., 1.5x)\nlue --speed 1.5 path\u002Fto\u002Fyour\u002Fbook.epub\n\n# Specify a language code if needed\nlue --lang a path\u002Fto\u002Fyour\u002Fbook.epub\n\n# Seconds of overlap between sentences\nlue --over 0.2 path\u002Fto\u002Fyour\u002Fbook.epub\n\n# Enable PDF cleaning filter (removes page numbers, headers and footnotes, default: 10% (0.1) from both bottom and top of the page)\nlue --filter path\u002Fto\u002Fyour\u002Fbook.pdf\n\n# Set custom PDF filter margins (0.0-1.0, where 0.1 = 10% of page)\nlue --filter 0.15 path\u002Fto\u002Fyour\u002Fbook.pdf          # Both margins to 15%\nlue --filter 0.12 0.20 path\u002Fto\u002Fyour\u002Fbook.pdf     # Header 12%, footnote 20%\n\n# Use the Vim keyboard layout\nlue --keys vim path\u002Fto\u002Fyour\u002Fbook.epub\n\n```\n\n### Keyboard Controls (Default)\n\n\u003Cdiv align=\"center\">\n\n| **Key Binding**                         | **Action Description**                                                                         |\n| --------------------------------------- | ---------------------------------------------------------------------------------------------- |\n| `q`                                     | Quit the application and save current reading progress automatically                           |\n| `p`                                     | Pause or resume the text-to-speech audio playback                                              |\n| `a`                                     | Toggle auto-scroll mode to automatically advance during TTS playback                           |\n| `t`                                     | Select and highlight the top sentence of the current visible page                              |\n| `h` \u002F `l`                               | Move the reading line to the previous or next paragraph in the document                        |\n| `j` \u002F `k`                               | Move the reading line to the previous or next sentence in the document                         |\n| `i` \u002F `m`                               | Jump up or down by full pages for rapid navigation through longer documents                    |\n| `u` \u002F `n`                               | Scroll up or down by smaller increments for fine-grained position control                      |\n| `y` \u002F `b`                               | Jump directly to the beginning or end of the document for quick navigation                     |\n| `r`                                     | Open the recent books menu to quickly switch between 5 last read books                       |\n| `,` \u002F `.`                               | Decrease or increase text-to-speech playback speed (1x to 3x)                                  |\n| `s` \u002F `w`                               | Toggle sentence highlighting or word highlighting on\u002Foff                                       |\n| `v`                                     | Cycle through UI complexity modes (Minimal, Medium, Full)                                      |\n\n\u003C\u002Fdiv>\n\n### Mouse Controls\n\n- **🖱️ Click** - Jump to sentence\n- **🔄 Scroll** - Navigate content  \n- **📍 Progress bar click** - Jump to position\n\n## ⚙️ Customize\n\n### UI Modes\n\nLue offers three UI complexity modes that you can cycle through using the `v` key or set as your default in the [config.py](lue\u002Fconfig.py) file:\n\n- **Mode 0 (Minimal)** - Clean text-only display with no borders or UI elements\n- **Mode 1 (Medium)** - Displays a top title bar with progress information and borders\n- **Mode 2 (Full)** - Full UI with both top title bar and bottom control information\n\nAdditionally, Lue provides customizable word-level and sentence-level highlighting that can be adjusted to suit your reading preferences. You can cycle through different highlighting modes using the `w` and `s` keys. These highlighting settings can also be configured as defaults in the [config.py](lue\u002Fconfig.py) file.\n\n### Keyboard Layouts\n\nLue comes with two built-in keyboard layouts that can be set using -k\u002F--key command line option or set as your default in the [config.py](lue\u002Fconfig.py) file. You can create your own keyboard layout by copying and modifying one of the existing layout files:\n\n- **Default Layout** - [keys_default.json](lue\u002Fkeys_default.json) - Standard keyboard layout\n- **Vim Layout** - [keys_vim.json](lue\u002Fkeys_vim.json) - Vim-style keyboard layout\n- **Custom Layout** - Customize your own navigation keys by creating your own keyboard layout json file\n\n### Color Themes\n\nLue allows you to customize the color theme, visual icons\u002Fsymbols and all ui elements of the interface by modifying the classes in [ui.py](lue\u002Fui.py). Create your own theme or choose one of the three themes that come with the default installation.\n\n- **Default Theme** - The default colorful theme with various colors for different UI elements\n- **Black Theme** - A dark monochrome theme that's suitable for bright backgrounds\n- **White Theme** - A light monochrome theme that's suitable for dark backgrounds\n\n---\n\n## 🧩 Development\n\n> **Interested in extending Lue?** \n\nCheck out the [Developer Guide](DEVELOPER.md) for instructions on adding new TTS models and contributing to the project.\n\n### Data Storage\n\n**Reading Progress:**\n- **macOS:** `~\u002FLibrary\u002FApplication Support\u002Flue\u002F`\n- **Linux:** `~\u002F.local\u002Fshare\u002Flue\u002F`  \n- **Windows (WSL):** `~\u002F.local\u002Fshare\u002Flue\u002F` (within WSL filesystem)\n\n**Error Logs:**\n- **macOS:** `~\u002FLibrary\u002FLogs\u002Flue\u002Ferror.log`\n- **Linux:** `~\u002F.cache\u002Flue\u002Flog\u002Ferror.log`\n- **Windows (WSL):** `~\u002F.cache\u002Flue\u002Flog\u002Ferror.log` (within WSL filesystem)\n\n---\n\n## 🛠️ Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request.\n\nJoin our Discord community for discussions, support and collaboration for creating modules for new TTS models!\n\n[![Join our Discord](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Join%20Us-5865F2?logo=discord&style=for-the-badge)](https:\u002F\u002Fdiscord.gg\u002Fz8sE2gnMNk)\n\n---\n\n## 📄 License\n\nThis project is licensed under the **GPL-3.0-or-later License** - see the [LICENSE](LICENSE) file for details.\n\n---\n\n\u003Cdiv align=\"center\">\n\n\u003Ca title=\"This tool is Tool of The Week on Terminal Trove, The $HOME of all things in the terminal\" href=\"https:\u002F\u002Fterminaltrove.com\u002F\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fsuperstarryeyes_lue_readme_93a3f0b1e8e6.png\" width=\"40%\" alt=\"Terminal Trove Tool of The Week\" \u002F>\u003C\u002Fa>\n\n*Made with 💖 for CLI enthusiasts and bookworms*\n\n**⭐ Star this repo** if you find it useful!\n\n\u003C\u002Fdiv>\n","\u003Cdiv align=\"center\">\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fsuperstarryeyes_lue_readme_141871db2171.png\" alt=\"Lue 图标\" width=\"35%\" \u002F>\n\n### Lue - 终端电子书阅读器，支持文本转语音（TTS）\n[![License: GPL v3+](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-GPLv3+-86c9fa.svg)](https:\u002F\u002Fwww.gnu.org\u002Flicenses\u002Fgpl-3.0)\n[![Python](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpython-3.10+-86c9fa.svg)](https:\u002F\u002Fwww.python.org\u002Fdownloads\u002F)\n[![平台](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fplatform-macOS%20%7C%20Linux%20%7C%20Windows%20(WSL)-86c9fa)](https:\u002F\u002Fgithub.com\u002Fsuperstarryeyes\u002Flue)\n[![终端](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Finterface-terminal-86c9fa.svg)](https:\u002F\u002Fgithub.com\u002Fsuperstarryeyes\u002Flue)\n[![Discord](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Join%20our%20Community-5865F2?logo=discord&logoColor=white)](https:\u002F\u002Fdiscord.gg\u002Fz8sE2gnMNk)\n\n[功能](#-功能) • [快速开始](#-快速开始-macos和linux) • [安装指南](#-安装指南-macos-linux和windows) • [使用方法](#-使用方法) • [自定义设置](#️-自定义设置) • [开发指南](#-开发指南)\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fsuperstarryeyes_lue_readme_500cb5b24cd0.gif\" alt=\"Lue 截图\" width=\"100%\" \u002F>\n\n\u003C\u002Fdiv>\n\n---\n\n## ✨ 功能\n\n| **功能**                             | **描述**                                                                                |\n| --------------------------------------- | ---------------------------------------------------------------------------------------------- |\n| **📖 多格式支持**                     | 支持 EPUB、PDF、TXT、DOCX、DOC、HTML、RTF 和 Markdown 格式，自动检测文件类型  |\n| **👄 模块化TTS系统**                   | Edge TTS（默认）和 Kokoro TTS（本地\u002F离线）支持，可扩展架构适配新模型  |\n| **🌍 跨平台与多语言**                 | 完全支持 macOS、Linux、Windows（通过 WSL），支持 100+ 种语言并提供一致的全球体验    |\n| **🎛️ 速度调节**                       | 文本转语音播放速度可在 1x 到 3x 之间调节，提供个性化听读体验       |\n| **🎯 自动滚动与精准文字高亮**          | 自动滚动与逐字高亮同步语音播放，提升专注力     |\n| **💾 智能持久化**                      | 自动保存阅读进度、状态恢复和跨会话连续性，实现无缝阅读体验|\n| **⚡️ 快捷导航**                        | 直观快捷键、灵活控制、鼠标支持和可选平滑滚动，提升书籍导航效率     |\n| **⚙️ 深度自定义**                      | 完全可定制键盘布局（包括 Vim 风格绑定）、界面元素、颜色和显示模式|\n\n---\n\n## 🚀 快速开始 (macOS和Linux)\n\n> **想立即体验 Lue？** 按照以下步骤操作：\n\n```bash\n# 1. 安装 FFmpeg（音频处理必需）\n# macOS\nbrew install ffmpeg\n# Ubuntu\u002FDebian  \nsudo apt install ffmpeg\n\n# 2. 从 PyPI 安装最新版本\npip install lue-reader \n\n# 3. 使用导航指南练习操作\nlue --guide\n\n# 4. 开始阅读！\nlue path\u002Fto\u002Fyour\u002Fbook.epub \n```\n\n> **📝 注意：** 快速开始使用 Edge TTS（需要联网）。如需离线功能，请参见[完整安装指南](#-安装指南-macos-linux和windows)。\n\n---\n\n## 📦 安装指南 (macOS, Linux 和 Windows)\n\n### 基础依赖\n\n#### 核心要求\n- **FFmpeg** - 音频处理（必需）\n\n#### 可选依赖  \n- **espeak** - Kokoro TTS 支持\n\n#### macOS (Homebrew)\n```bash\nbrew install ffmpeg\n# 可选\nbrew install espeak\n```\n\n#### Ubuntu\u002FDebian\n```bash\nsudo apt update && sudo apt install ffmpeg\n# 可选  \nsudo apt install espeak\n```\n\n#### Arch Linux (AUR)\n```bash\n# 使用 yay\nyay -S lue-reader-git\n\n# 或使用 paru\nparu -S lue-reader-git\n```\n\n#### Windows\n```bash\n# 1. 安装 WSL\n# 以管理员身份打开 PowerShell：\nwsl --install\n\n# 2. 如果提示重启，重启后从开始菜单启动 Ubuntu\n\n# 3. 在 Ubuntu 终端中执行：\nsudo apt update && sudo apt upgrade -y\nsudo apt install ffmpeg python3 python3-pip -y\n# 可选  \nsudo apt install espeak\n```\n\n### 安装 Lue\n\n#### 标准安装\n\n```bash\n# 1. 克隆仓库\ngit clone https:\u002F\u002Fgithub.com\u002Fsuperstarryeyes\u002Flue.git\ncd lue\n\n# 2. 安装依赖\npip install -r requirements.txt\n\n# 3. 安装 Lue\npip install .\n```\n\n#### 启用 Kokoro TTS (可选)\n\n启用本地\u002F离线 TTS 功能：\n\n```bash\n# 1. 编辑 requirements.txt - 取消注释 Kokoro 相关包：\nkokoro>=0.9.4\nsoundfile>=0.13.1\nhuggingface-hub>=0.34.4\n\n# 2. 安装 PyTorch\n# CPU 版本：\npip install torch torchvision torchaudio\n# GPU 版本（CUDA）：\npip install torch torchvision torchaudio --index-url https:\u002F\u002Fdownload.pytorch.org\u002Fwhl\u002Fcu121\n\n# 3. 安装更新后的依赖\npip install -r requirements.txt\n\n# 4. 安装 Lue\npip install .\n```\n\n---\n\n## 💻 使用方法\n\n### 基础命令\n\n```bash\n# 使用默认 TTS 启动\nlue path\u002Fto\u002Fyour\u002Fbook.epub\n\n# 不带参数启动以打开上次阅读的书籍\nlue\n\n# 使用导航指南练习默认快捷键\nlue --guide\n\n# 查看可用命令行选项\nlue --help\n\n# 使用特定 TTS 模型（edge\u002Fkokoro\u002Fnone） \nlue --tts kokoro path\u002Fto\u002Fyour\u002Fbook.epub\n\n# 使用特定语音（完整列表见 VOICES.md）\nlue --voice \"en-US-AriaNeural\" path\u002Fto\u002Fyour\u002Fbook.epub\n\n# 设置语音速度（如 1.5x）\nlue --speed 1.5 path\u002Fto\u002Fyour\u002Fbook.epub\n\n# 指定语言代码（如需要）\nlue --lang a path\u002Fto\u002Fyour\u002Fbook.epub\n\n# 设置句子间重叠时长（秒）\nlue --over 0.2 path\u002Fto\u002Fyour\u002Fbook.epub\n\n# 启用 PDF 清理过滤器（移除页码、页眉和脚注，默认页面上下各 10% (0.1)）\nlue --filter path\u002Fto\u002Fyour\u002Fbook.pdf\n\n# 自定义 PDF 过滤器边距（0.0-1.0，0.1=页面的10%）\nlue --filter 0.15 path\u002Fto\u002Fyour\u002Fbook.pdf          # 上下边距均设为 15%\nlue --filter 0.12 0.20 path\u002Fto\u002Fyour\u002Fbook.pdf     # 页眉 12%，脚注 20%\n\n# 使用 Vim 键盘布局\nlue --keys vim path\u002Fto\u002Fyour\u002Fbook.epub\n```\n\n### 键盘控制（默认设置）\n\n\u003Cdiv align=\"center\">\n\n| **按键绑定**                         | **动作描述**                                                                         |\n| --------------------------------------- | ---------------------------------------------------------------------------------------------- |\n| `q`                                     | 退出应用程序并自动保存当前阅读进度                           |\n| `p`                                     | 暂停或恢复文本转语音（TTS）音频播放                                              |\n| `a`                                     | 切换自动滚动模式，在TTS播放期间自动推进                           |\n| `t`                                     | 选择并高亮当前可视页面的顶部句子                              |\n| `h` \u002F `l`                               | 将阅读行移动到文档的上一个或下一个段落                        |\n| `j` \u002F `k`                               | 将阅读行移动到文档的上一个或下一个句子                         |\n| `i` \u002F `m`                               | 快速上下翻页以浏览长文档                    |\n| `u` \u002F `n`                               | 小幅度上下滚动以精细控制位置                      |\n| `y` \u002F `b`                               | 直接跳转到文档开头或结尾进行快速导航                     |\n| `r`                                     | 打开最近阅读书籍菜单，快速切换5本最近阅读的书籍                       |\n| `,` \u002F `.`                               | 降低或提高文本转语音播放速度（1x至3x）                                  |\n| `s` \u002F `w`                               | 切换句子高亮或单词高亮的开关                                       |\n| `v`                                     | 循环切换UI复杂度模式（极简、中等、完整）                                      |\n\n\u003C\u002Fdiv>\n\n### 鼠标控制\n\n- **🖱️ 点击** - 跳转到指定句子\n- **🔄 滚动** - 浏览内容  \n- **📍 进度条点击** - 跳转到指定位置\n\n## ⚙️ 自定义设置\n\n### UI模式\n\nLue提供三种UI复杂度模式，可通过`v`键循环切换，或在[config.py](lue\u002Fconfig.py)文件中设置默认模式：\n\n- **模式0（极简）** - 简洁纯文本显示，无边框和UI元素\n- **模式1（中等）** - 显示顶部标题栏（含进度信息）和边框\n- **模式2（完整）** - 完整UI，包含顶部标题栏和底部控制信息\n\n此外，Lue提供可自定义的单词级和句子级高亮功能，可通过`s`和`w`键切换不同高亮模式。这些设置也可在[config.py](lue\u002Fconfig.py)文件中配置为默认设置。\n\n### 键盘布局\n\nLue提供两种内置键盘布局，可通过-k\u002F--key命令行参数设置，或在[config.py](lue\u002Fconfig.py)文件中设置默认布局。您可通过复制并修改现有布局文件创建自定义布局：\n\n- **默认布局（Default Layout）** - [keys_default.json](lue\u002Fkeys_default.json) - 标准键盘布局\n- **Vim布局（Vim Layout）** - [keys_vim.json](lue\u002Fkeys_vim.json) - 类Vim风格键盘布局\n- **自定义布局** - 通过创建自定义JSON文件配置导航键\n\n### 颜色主题\n\n通过修改[lue\u002Fui.py](lue\u002Fui.py)中的类定义，可自定义界面颜色主题、视觉图标\u002F符号和所有UI元素。可选择默认安装的三种主题或创建自定义主题：\n\n- **默认主题（Default Theme）** - 默认多彩主题，不同UI元素使用不同颜色\n- **黑色主题（Black Theme）** - 适合明亮背景的深色单色主题\n- **白色主题（White Theme）** - 适合暗色背景的浅色单色主题\n\n---\n\n## 🧩 开发相关\n\n> **有兴趣扩展Lue功能？** \n\n请查阅[开发者指南](DEVELOPER.md)，了解如何添加新TTS模型和参与项目贡献。\n\n### 数据存储\n\n**阅读进度：**\n- **macOS：** `~\u002FLibrary\u002FApplication Support\u002Flue\u002F`\n- **Linux：** `~\u002F.local\u002Fshare\u002Flue\u002F`  \n- **Windows (WSL)：** `~\u002F.local\u002Fshare\u002Flue\u002F` (位于WSL文件系统内)\n\n**错误日志：**\n- **macOS：** `~\u002FLibrary\u002FLogs\u002Flue\u002Ferror.log`\n- **Linux：** `~\u002F.cache\u002Flue\u002Flog\u002Ferror.log`\n- **Windows (WSL)：** `~\u002F.cache\u002Flue\u002Flog\u002Ferror.log` (位于WSL文件系统内)\n\n---\n\n## 🛠️ 贡献指南\n\n欢迎任何形式的贡献！欢迎提交Pull Request。\n\n加入我们的Discord社区讨论、获取支持，并协作开发新TTS模型模块！\n\n[![Join our Discord](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Join%20Us-5865F2?logo=discord&style=for-the-badge)](https:\u002F\u002Fdiscord.gg\u002Fz8sE2gnMNk)\n\n---\n\n## 📄 许可协议\n\n本项目采用**GPL-3.0-or-later许可证**，详见[LICENSE](LICENSE)文件。\n\n---\n\n\u003Cdiv align=\"center\">\n\n\u003Ca title=\"This tool is Tool of The Week on Terminal Trove, The $HOME of all things in the terminal\" href=\"https:\u002F\u002Fterminaltrove.com\u002F\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fsuperstarryeyes_lue_readme_93a3f0b1e8e6.png\" width=\"40%\" alt=\"Terminal Trove Tool of The Week\" \u002F>\u003C\u002Fa>\n\n*为CLI爱好者和书虫打造 ❤️*\n\n**⭐ 发现有用请点亮Star**！\n\n\u003C\u002Fdiv>","# Lue 快速上手指南\n\n## 🧰 环境准备\n\n### 系统要求\n- **macOS** (推荐10.15+)  \n- **Linux** (Ubuntu 20.04+\u002FDebian 11+\u002FArch)  \n- **Windows** (通过WSL2，推荐安装Ubuntu发行版)\n\n### 前置依赖\n#### 核心依赖\n```bash\n# macOS (Homebrew)\nbrew install ffmpeg\n\n# Ubuntu\u002FDebian (国内用户可替换为清华\u002F阿里源)\nsudo apt install ffmpeg\n\n# Windows (WSL2内安装)\nsudo apt install ffmpeg\n```\n\n#### 可选依赖 (离线TTS)\n```bash\n# 安装 espeak (Kokoro TTS依赖)\nsudo apt install espeak  # Ubuntu\u002FDebian\nbrew install espeak      # macOS\n```\n\n> **国内加速提示**：安装Python包时建议添加国内镜像源，例如：\n```bash\npip install -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple ...\n```\n\n---\n\n## 📦 安装步骤\n\n### 标准安装 (在线TTS)\n```bash\n# 安装Lue核心 (推荐国内镜像加速)\npip install -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple lue-reader\n\n# 验证安装\nlue --version\n```\n\n### 完全安装 (含离线TTS)\n```bash\n# 1. 安装PyTorch (国内镜像加速)\npip install torch torchvision torchaudio -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n\n# 2. 安装Lue并启用Kokoro\ngit clone https:\u002F\u002Fgithub.com\u002Fsuperstarryeyes\u002Flue.git\ncd lue\n\n# 3. 修改 requirements.txt 启用Kokoro模块 (取消注释对应行)\n\n# 4. 安装依赖 (国内镜像加速)\npip install -r requirements.txt -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n\n# 5. 安装Lue\npip install .\n```\n\n---\n\n## 🚀 基本使用\n\n### 启动导航教程\n```bash\nlue --guide  # 熟悉基础操作\n```\n\n### 打开电子书\n```bash\n# 使用默认在线TTS朗读\nlue path\u002Fto\u002Fbook.epub\n\n# 使用离线Kokoro TTS\nlue --tts kokoro path\u002Fto\u002Fbook.epub\n\n# 恢复上次阅读进度\nlue\n```\n\n### 常用控制\n```bash\n# 播放\u002F暂停\np\n\n# 退出并保存进度\nq\n\n# 调整语速 (1.5x)\nlue --speed 1.5 path\u002Fto\u002Fbook.epub\n\n# 切换UI模式 (最小\u002F中等\u002F完整界面)\nv\n```\n\n> **提示**：Windows用户需在WSL2终端中运行上述命令，推荐使用Windows Terminal或Alacritty等现代终端模拟器。","一位软件工程师每天通勤时需要研读技术文档，但因地铁网络不稳定且双手常需扶握，传统阅读方式效率低下。\n\n### 没有 lue 时\n- 需先用 Calibre 转换 PDF\u002FEPUB 格式适配不同阅读器，通勤前准备耗时 15 分钟\n- 依赖手机有声书 App 实现听读，但仅支持 TXT 格式且无法精准定位段落\n- 地铁报站声干扰导致漏听关键内容，需反复回放耗费额外 30% 通勤时间\n- 进度仅能手动记录章节，换设备阅读时需重新定位位置\n\n### 使用 lue 后\n- 直接通过终端打开任意格式技术文档（含 PDF 原生扫描版），启动即读\n- 切换 Kokoro TTS 本地引擎实现无网络听书，语音与高亮文字精准同步\n- 设置 1.8x 语速跳过冗余内容，利用智能滚动自动定位重点段落\n- 每次退出自动保存阅读位置与高亮批注，回家后无缝续读无需查找\n\n通过终端集成环境实现文档解析、语音输出与交互控制的全流程闭环，lue 让碎片化时间利用率提升 40%，真正实现「听读一体」的沉浸式学习体验。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fsuperstarryeyes_lue_141871db.png","superstarryeyes","Starry Eyes","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fsuperstarryeyes_edafc688.png","Design engineer ⋆⁺₊✧",null,"Helsinki, Finland","superstarryeyes@gmail.com","https:\u002F\u002Fgithub.com\u002Fsuperstarryeyes",[23],{"name":24,"color":25,"percentage":26},"Python","#3572A5",100,715,31,"2026-04-05T00:41:59","GPL-3.0",2,"Linux, macOS, Windows","未说明",{"notes":35,"python":36,"dependencies":37},"必须安装FFmpeg进行音频处理；启用Kokoro TTS需安装espeak及PyTorch；Edge TTS依赖网络连接，Kokoro TTS需下载额外模型文件；Windows需通过WSL运行","3.10+",[38,39],"FFmpeg","espeak (可选)",[41,42],"插件","音频",[44,45,46,47,48,49,50,51,52,53,54,55,56,57],"book","cli","docx","ebook","epub","modular","reader","terminal","text-to-speech","tts","txt","voice","pdf","tui",3,"ready","2026-03-27T02:49:30.150509","2026-04-06T07:13:28.442328",[63,68,73,78,83,88],{"id":64,"question_zh":65,"answer_zh":66,"source_url":67},4819,"如何解决TTS在遇到'. »'或'! »'等标点时停止的问题？","请确保使用最新版本代码，并测试维护者提供的示例文本。若问题仍存在，尝试更新代码并重新安装。维护者已针对该问题进行了修复：\n```\n« Hello there! »  \nShe smiled and said, « It’s been a long day… » before closing the door.\n```","https:\u002F\u002Fgithub.com\u002Fsuperstarryeyes\u002Flue\u002Fissues\u002F22",{"id":69,"question_zh":70,"answer_zh":71,"source_url":72},4820,"Vim键绑定方向错误如何修正？","从v0.3.0版本开始支持Vim键绑定，使用`-k vim`参数启用。若需自定义键位，可通过修改`lue\u002Fkeyboard_shortcuts.json`文件配置，支持完全自定义的键盘映射方案。","https:\u002F\u002Fgithub.com\u002Fsuperstarryeyes\u002Flue\u002Fissues\u002F1",{"id":74,"question_zh":75,"answer_zh":76,"source_url":77},4821,"出现“No audio was received”错误如何处理？","请升级edge-tts包到7.2.7版本：\n1. `pip install --upgrade edge-tts==7.2.7`\n2. 验证安装：`pip show edge-tts`\n若仍失败，可能是微软语音服务临时故障，可参考https:\u002F\u002Fspeech.platform.bing.com\u002F状态页面。","https:\u002F\u002Fgithub.com\u002Fsuperstarryeyes\u002Flue\u002Fissues\u002F28",{"id":79,"question_zh":80,"answer_zh":81,"source_url":82},4822,"如何为Coqui XTTS模型添加支持？","维护者已接受相关PR并集成该功能。请查看项目仓库的最新代码，若需要特定配置可参考已合并的pull request（#8）中的实现细节。","https:\u002F\u002Fgithub.com\u002Fsuperstarryeyes\u002Flue\u002Fissues\u002F5",{"id":84,"question_zh":85,"answer_zh":86,"source_url":87},4823,"如何通过容器化部署Lue？","项目已支持Docker容器化部署，相关配置文件已在PR#6中合并。使用Docker构建时请确保：\n1. 使用最新代码库\n2. 执行`docker build -t lue .`\n3. 运行容器时映射必要卷和端口","https:\u002F\u002Fgithub.com\u002Fsuperstarryeyes\u002Flue\u002Fissues\u002F4",{"id":89,"question_zh":90,"answer_zh":91,"source_url":92},4824,"如何将文本朗读输出到音频文件？","当前版本暂未实现直接输出文件功能，但可通过以下方式实现：\n1. 使用系统级录音工具录制音频输出\n2. 通过修改代码在`tts\u002Fedge_tts.py`中添加文件写入逻辑\n建议关注项目更新，后续版本可能会加入该功能。","https:\u002F\u002Fgithub.com\u002Fsuperstarryeyes\u002Flue\u002Fissues\u002F10",[94,99,104,109,114,119,124],{"id":95,"version":96,"summary_zh":97,"released_at":98},104338,"v0.4.0","feature: add 'r' key shortcut to toggle recently read ui window\r\nfeature: more granular playback speed adjustment\r\nfeature: add natural pause for tts at em dash\r\n\r\nbuild: remove doc format support because of antiword deprecation\r\n\r\nfix: flickering in some setups\r\nfix: bump edge-tts to 7.2.7 to fix no audio received errors\r\nfix: improve text sanitation for tts robustness\r\nfix: accented characters are now preserved from text sanitation\r\nfix: preserve parentheses from text sanitation\r\nfix: preserve semicolons from text sanitation\r\nfix: clarification that lue is licensed under GPL-3.0-or-later (GPLv3+)\r\nfix: better symbols to text\r\nfix: better tts reading of hyphenated words\r\nfix: remove currencies from unicode replacements\r\nfix: replace curly apostrophe with basic apostrophe for tts\r\nfix: preserve ?! and en dashes in tts sanitization\r\nfix: remove loose punctuation marks for tts\r\n\r\ndocs: document new r key shortcut, fix links and add instructions for arch linux installation (thanks @xbwwj and @evlim)","2025-12-15T19:16:16",{"id":100,"version":101,"summary_zh":102,"released_at":103},104339,"v0.3.1","fix: include key config json files in the pypi package","2025-10-22T11:33:32",{"id":105,"version":106,"summary_zh":107,"released_at":108},104340,"v0.3.0","feature: vim-style key bindings accessable with \"-k\u002F--key vim\" or from config.py\r\nfeature: keyboard_shortcuts.json format with customizable keyboard bindings that update in the ui when changed\r\nfeature: new standout mode for word-level highlighting to make it differentiate with some colors\r\nfeature: three-mode cycling with \"w\" shortcut for word-level highlighting\r\nfeature: ui complexity mode configuration option to simplify the ui if wanted from config.py or with \"v\" key\r\nfeature: opening with --guide command line argument will read the navigation instructions to you\r\nfeature: removal of pdf filter headers by repetition to make pdf parsing simpler and more focused\r\nfeature: pdf filter margin numbers adjustable from command line with -f \u002F --filter\r\n\r\nfix: pdf filtering variable names cleaner and numbering more intuitive\r\nfix: eliminate race condition causing word highlight flicker with some tts models (eg kokoro)\r\nfix: non-alphanumeric characters confusing the word-level highlighter and making it delayed\r\nfix: handle none values in timing data to prevent comparison errors\r\nfix: black and white color themes\r\nfix: logic problem for how keyboard shortcuts are resolved\r\nfix: word level highlighter for nested words\r\nfix: preserve spacing after ellipsis\r\n\r\ndocs: information about the new features and rewriting sections\r\ndocs: instructions for windows wsl installation (incorporated from @JimnyGitHub's PR #13)","2025-10-03T06:42:18",{"id":110,"version":111,"summary_zh":112,"released_at":113},104341,"v0.2.0","feature: word-level highlighting\r\nfeature: open document without loading tts model with --tts\u002F-t none option\r\nfeature: publish lue-reader to pypi\r\n\r\nui: new icon\r\nui: new unicode symbol for autoscroll\r\n\r\ndocs: image names update\r\ndocs: update new icon and screenshot\r\ndocs: new screenshot\r\ndocs: add new chapter to sample.txt about highlighting\r\ndocs: update DEVELOPER.md about the new centralized timing_calculator.py\r\ndocs: update DEVELOPER.md about word-level highlighting\r\ndocs: add none to tts options\r\n\r\nrefactor: word timing calculations moved from individual tts modules to a centralized timing_calculator.py\r\n\r\nfix: make tts ignore rogue dash followed by quotation\r\nfix: word level highlighting number inclusion\r\nfix: word level highlighting logic skip with numbers\r\nfix: separate word-level highlighting and sentence highlighting so they work individually\r\nfix: indentation collapse","2025-09-08T15:40:25",{"id":115,"version":116,"summary_zh":117,"released_at":118},104342,"v0.1.5","feature: optional smooth scrolling for keyboard navigation\r\nfeature: tells you if no text was found in the file\r\nfeature: tts talking speed accessible from command line\r\n\r\nfix: bug that starts two different playbacks at once when you hit play\u002Fpause in quick succession\r\n\r\ndocs: discord link\r\ndocs: fix typo in README\r\ndocs: fix typos\r\ndocs: how to use the new tts speed feature","2025-09-05T06:24:39",{"id":120,"version":121,"summary_zh":122,"released_at":123},104343,"v0.1.1","feature: added tts speed adjustment functionality. goes up to 3x speed. `.` (period) to increase speed. `,` (comma) to decrease speed.\r\nfeature: when no command line options are provided, open the last book\r\nfeature: command line option --over \u002F -o for seconds of overlap between sentences\r\n\r\nfix: stray punctuation stopping tts\r\nfix: mouse clicking on empty spaces outside the text or progress bar doesn't stop the audio anymore\r\nfix: removes unnecessary pauses in abbreviations that end in a period\r\n\r\nbuild: update minimum python version to 3.10","2025-08-25T19:18:50",{"id":125,"version":126,"summary_zh":127,"released_at":128},104344,"v0.1.0","The first official release of Lue.","2025-08-16T14:52:54",[130,145,153,161,169,177],{"id":131,"name":132,"github_repo":133,"description_zh":134,"stars":135,"difficulty_score":31,"last_commit_at":136,"category_tags":137,"status":59},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[138,139,140,41,141,142,143,144,42],"图像","数据工具","视频","Agent","其他","语言模型","开发框架",{"id":146,"name":147,"github_repo":148,"description_zh":149,"stars":150,"difficulty_score":58,"last_commit_at":151,"category_tags":152,"status":59},2181,"OpenHands","OpenHands\u002FOpenHands","OpenHands 是一个专注于 AI 驱动开发的开源平台，旨在让智能体（Agent）像人类开发者一样理解、编写和调试代码。它解决了传统编程中重复性劳动多、环境配置复杂以及人机协作效率低等痛点，通过自动化流程显著提升开发速度。\n\n无论是希望提升编码效率的软件工程师、探索智能体技术的研究人员，还是需要快速原型验证的技术团队，都能从中受益。OpenHands 提供了灵活多样的使用方式：既可以通过命令行（CLI）或本地图形界面在个人电脑上轻松上手，体验类似 Devin 的流畅交互；也能利用其强大的 Python SDK 自定义智能体逻辑，甚至在云端大规模部署上千个智能体并行工作。\n\n其核心技术亮点在于模块化的软件智能体 SDK，这不仅构成了平台的引擎，还支持高度可组合的开发模式。此外，OpenHands 在 SWE-bench 基准测试中取得了 77.6% 的优异成绩，证明了其解决真实世界软件工程问题的能力。平台还具备完善的企业级功能，支持与 Slack、Jira 等工具集成，并提供细粒度的权限管理，适合从个人开发者到大型企业的各类用户场景。",70612,"2026-04-05T11:12:22",[143,141,144,41],{"id":154,"name":155,"github_repo":156,"description_zh":157,"stars":158,"difficulty_score":31,"last_commit_at":159,"category_tags":160,"status":59},3074,"gpt4free","xtekky\u002Fgpt4free","gpt4free 是一个由社区驱动的开源项目，旨在聚合多种可访问的大型语言模型（LLM）和媒体生成接口，让用户能更灵活、便捷地使用前沿 AI 能力。它解决了直接调用各类模型时面临的接口分散、门槛高或成本昂贵等痛点，通过统一的标准将不同提供商的资源整合在一起。\n\n无论是希望快速集成 AI 功能的开发者、需要多模型对比测试的研究人员，还是想免费体验最新技术的普通用户，都能从中受益。gpt4free 提供了丰富的使用方式：既包含易于上手的 Python 和 JavaScript 客户端库，也支持部署本地图形界面（GUI），更提供了兼容 OpenAI 标准的 REST API，方便无缝替换现有应用后端。\n\n其技术亮点在于强大的多提供商支持架构，能够动态调度包括 Opus、Gemini、DeepSeek 等多种主流模型资源，并支持 Docker 一键部署及本地推理。项目秉持社区优先原则，在降低使用门槛的同时，也为贡献者提供了扩展新接口的便利框架，是探索和利用多样化 AI 资源的实用工具。",65970,"2026-04-04T01:02:03",[41,143,141],{"id":162,"name":163,"github_repo":164,"description_zh":165,"stars":166,"difficulty_score":31,"last_commit_at":167,"category_tags":168,"status":59},51,"gstack","garrytan\u002Fgstack","gstack 是 Y Combinator CEO Garry Tan 亲自开源的一套 AI 工程化配置，旨在将 Claude Code 升级为你的虚拟工程团队。面对单人开发难以兼顾产品战略、架构设计、代码审查及质量测试的挑战，gstack 提供了一套标准化解决方案，帮助开发者实现堪比二十人团队的高效产出。\n\n这套配置特别适合希望提升交付效率的创始人、技术负责人，以及初次尝试 Claude Code 的开发者。gstack 的核心亮点在于内置了 15 个具有明确职责的 AI 角色工具，涵盖 CEO、设计师、工程经理、QA 等职能。用户只需通过简单的斜杠命令（如 `\u002Freview` 进行代码审查、`\u002Fqa` 执行测试、`\u002Fplan-ceo-review` 规划功能），即可自动化处理从需求分析到部署上线的全链路任务。\n\n所有操作基于 Markdown 和斜杠命令，无需复杂配置，完全免费且遵循 MIT 协议。gstack 不仅是一套工具集，更是一种现代化的软件工厂实践，让单人开发者也能拥有严谨的工程流程。",64604,"2026-04-05T23:10:16",[141,41],{"id":170,"name":171,"github_repo":172,"description_zh":173,"stars":174,"difficulty_score":31,"last_commit_at":175,"category_tags":176,"status":59},193,"meilisearch","meilisearch\u002Fmeilisearch","Meilisearch 是一个开源的极速搜索服务，专为现代应用和网站打造，开箱即用。它能帮助开发者快速集成高质量的搜索功能，无需复杂的配置或额外的数据预处理。传统搜索方案往往需要大量调优才能实现准确结果，而 Meilisearch 内置了拼写容错、同义词识别、即时响应等实用特性，并支持 AI 驱动的混合搜索（结合关键词与语义理解），显著提升用户查找信息的体验。\n\nMeilisearch 特别适合 Web 开发者、产品团队或初创公司使用，尤其适用于需要快速上线搜索功能的场景，如电商网站、内容平台或 SaaS 应用。它提供简洁的 RESTful API 和多种语言 SDK，部署简单，资源占用低，本地开发或生产环境均可轻松运行。对于希望在不依赖大型云服务的前提下，为用户提供流畅、智能搜索体验的团队来说，Meilisearch 是一个高效且友好的选择。",56972,"2026-04-05T22:34:33",[138,141,139,144,41,142],{"id":178,"name":179,"github_repo":180,"description_zh":181,"stars":182,"difficulty_score":58,"last_commit_at":183,"category_tags":184,"status":59},4128,"GPT-SoVITS","RVC-Boss\u002FGPT-SoVITS","GPT-SoVITS 是一款强大的开源语音合成与声音克隆工具，旨在让用户仅需极少量的音频数据即可训练出高质量的个性化语音模型。它核心解决了传统语音合成技术依赖海量录音数据、门槛高且成本大的痛点，实现了“零样本”和“少样本”的快速建模：用户只需提供 5 秒参考音频即可即时生成语音，或使用 1 分钟数据进行微调，从而获得高度逼真且相似度极佳的声音效果。\n\n该工具特别适合内容创作者、独立开发者、研究人员以及希望为角色配音的普通用户使用。其内置的友好 WebUI 界面集成了人声伴奏分离、自动数据集切片、中文语音识别及文本标注等辅助功能，极大地降低了数据准备和模型训练的技术门槛，让非专业人士也能轻松上手。\n\n在技术亮点方面，GPT-SoVITS 不仅支持中、英、日、韩、粤语等多语言跨语种合成，还具备卓越的推理速度，在主流显卡上可实现实时甚至超实时的生成效率。无论是需要快速制作视频配音，还是进行多语言语音交互研究，GPT-SoVITS 都能以极低的数据成本提供专业级的语音合成体验。",56375,"2026-04-05T22:15:46",[42]]