字幕翻译
字幕翻译 是 AI Skill Hub 本期精选AI工具之一。综合评分 8.0 分，整体质量较高。我们强烈推荐将其纳入你的 AI 工具库，帮助提升工作效率。
📚 深度解析
**为什么要使用开源工具而非商业 SaaS？**
对于个人开发者和有隐私需求的用户，本地部署的开源工具意味着数据不离本机，不受第三方服务商的数据政策约束。同时，开源工具通常没有使用次数限制和月度费用，一次安装即可长期使用，对于高频使用场景的总拥有成本（TCO）远低于订阅制商业工具。
**安装与环境准备**
字幕翻译 依赖 TypeScript 运行环境。建议通过 pyenv（Python）或 nvm（Node.js）管理 TypeScript 版本，避免全局环境污染。对于新手用户，推荐先创建虚拟环境（python -m venv venv && source venv/bin/activate），再安装依赖，这样即使出现问题也可以随时删除虚拟环境重新开始，不影响系统稳定性。
**社区与维护**
GitHub Issue 和 Discussion 是获取帮助的最快渠道。在提问前建议先检查 Closed Issues（已关闭的问题），大多数常见问题都已有解答。遇到 Bug 时，提供 pip list 的输出、完整错误堆栈和最小可复现示例，能显著提高开发者响应速度。AI Skill Hub 将持续追踪 字幕翻译 的版本更新，及时通知重要功能变化。
📋 工具概览
字幕翻译 是一款基于 TypeScript 开发的开源工具，专注于 batch-translation、bilingual-subtitles、srt 等核心功能。作为 GitHub 开源项目，它拥有活跃的社区支持和持续的版本迭代，代码完全透明可审计，支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流，都能提供稳定可靠的解决方案。
📖 中文文档
字幕翻译 是一款基于 TypeScript 开发的开源工具，专注于 batch-translation、bilingual-subtitles、srt 等核心功能。作为 GitHub 开源项目，它拥有活跃的社区支持和持续的版本迭代，代码完全透明可审计，支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流，都能提供稳定可靠的解决方案。
- 开源免费，支持本地部署，数据完全自主可控
- 活跃的 GitHub 开源社区，持续迭代更新
- 提供详细文档和使用示例，新手友好
- 支持自定义配置，灵活适配不同使用环境
- 可作为基础组件集成进现有技术栈或进行二次开发
- 本地部署运行，保护数据隐私，满足合规要求
- 自定义集成到现有系统，扩展技术栈能力
- 作为开源基础组件进行商业化二次开发
# 方式一：npm 全局安装 npm install -g subtitle-translator # 方式二：npx 直接运行（无需安装） npx subtitle-translator --help # 方式三：项目依赖安装 npm install subtitle-translator # 方式四：从源码运行 git clone https://github.com/rockbenben/subtitle-translator cd subtitle-translator npm install npm start
- 访问 GitHub 仓库页面
- 按照 README 文档完成依赖安装
- 根据系统环境完成初始化配置
- 参考官方示例或文档开始使用
- 遇到问题可在 GitHub Issues 中查找解答
# 命令行使用
subtitle-translator --help
# 基本用法
subtitle-translator [options] <input>
# Node.js 代码中使用
const subtitle_translator = require('subtitle-translator');
const result = await subtitle_translator.run(options);
console.log(result);
# subtitle-translator 配置说明 # 查看配置选项 subtitle-translator --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量（覆盖配置文件） export SUBTITLE_TRANSLATOR_CONFIG="/path/to/config.yml"
简介
⚡️ Subtitle Translator
English | 中文
Blazing-fast batch subtitle translation for 120+ languages — powered by AI
<p align="center"> <a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License: MIT"></a> <a href="https://tools.newzone.top/en/subtitle-translator"><img src="https://img.shields.io/badge/Live%20Demo-subtitle--translator-blue" alt="Live Demo"></a> </p>
Subtitle Translator is a free, browser-based batch subtitle translation tool for .srt, .ass, .vtt, and .lrc files. With chunked compression and parallel processing it hits ~1 second per episode. Batch-upload a whole season at once, connect to 7 traditional translation APIs (DeepL, Google, Azure, DeepLX, Qwen-MT, TranslateGemma, GTX) or 17+ LLM providers, and translate into 120+ languages — or into several target languages in a single pass, each exported as its own file. Everything runs locally in your browser; subtitle content and API keys never touch a server.
👉 Try it online: <https://tools.newzone.top/en/subtitle-translator>
Key Features
- Real-Time Translation: Chunked compression + parallel processing → ~1 second per episode (GTX is slightly slower).
- Batch Processing: Drop hundreds of subtitle files at once (a whole season in one go); each file translates and downloads independently with its original filename, and you get an aggregated success/failure summary (e.g. "Exported (3/5)") when the run finishes.
- Multi-Language Output: Translate into multiple target languages in a single pass — each language is exported as its own file with the language code appended (e.g.
movie.zh.srt,movie.fr.srt). - Format Compatibility: Auto-detects
.srt,.ass,.vtt, and.lrc. WebVTT NOTE / STYLE / REGION non-cue blocks are correctly skipped (not translated as dialogue). One-click format conversion (SRT ↔ VTT, SRT/VTT → ASS) during translation. - Bilingual Output: Insert the translation above or below the original; alignment preserved across formats. For SRT / VTT sources you can also export ASS with separate styles for original and translation (Default 70pt white + Secondary 55pt cyan), tweakable in any subtitle editor.
- Context-Aware Translation (LLM only): Sends surrounding lines as context for more coherent dialogue and consistent character voice.
- Structural Separation: Timecodes, cue numbers, ASS headers, and VTT cue IDs are extracted locally — only dialogue text is sent to the engine, so the model can never disrupt your timeline.
- Subtitle Extraction: Strip cues / timing and export clean text (auto-copied to clipboard) for AI summarization, scripts, or content repurposing.
- Unlimited Caching (IndexedDB): All translations cached locally with no browser-storage size limit; refreshing the page doesn't lose translated files.
- 120+ Languages: Translate to/from 120+ languages, with source defaulting to Auto-detect.
- Multi-Locale UI: Powered by next-intl, with full UI translation across 18 languages.
- Private by Design: Fully client-side — subtitle content and API keys stay in your browser; LLM requests go directly from your browser to the API endpoint you configure.
Requirements
- Node.js >= 20.9.0
- Yarn (recommended), npm, or pnpm
Getting Started
Install & Run
git clone https://github.com/rockbenben/subtitle-translator.git
cd subtitle-translator
yarn install
yarn devVisit http://localhost:3000.
Production Build
yarn buildDocumentation & Deployment
For detailed configuration, API setup, and self-hosting instructions, see the Official Documentation.
Quick Deployment: Deploy Guide
Translation APIs
Supports 7 traditional MT APIs and 17+ LLM providers:
Traditional APIs
| API | Quality | Stability | Free Tier |
|---|---|---|---|
| **DeepL** | ★★★★★ | ★★★★☆ | 500K chars/month |
| **Google Translate** | ★★★★☆ | ★★★★★ | 500K chars/month |
| **Azure Translate** | ★★★★☆ | ★★★★★ | 2M chars/month (first 12 months) |
| **DeepLX (Free)** | ★★★★☆ | ★★★☆☆ | Self-host or free public endpoints |
| **Qwen-MT** | ★★★★☆ | ★★★★☆ | Alibaba DashScope quota |
| **TranslateGemma** | ★★★★☆ | ★★★★☆ | Self-host (LM Studio / Ollama / etc.) |
| **GTX API (Free)** | ★★★☆☆ | ★★★☆☆ | Free (rate-limited) |
FAQ
Which formats are supported? SRT, ASS, VTT, and LRC. SRT/VTT suit YouTube and HTML5 players; ASS suits Aegisub / anime fansubs (position tags like \an8 auto-restored); LRC suits music lyrics.
Machine translation or LLM? Machine translation (Google, DeepL, Azure, Qwen-MT) is cheap or free but reads flat. LLMs bill per token but produce far more natural dialogue — DeepSeek is the value pick for whole-season batches, Claude Sonnet / GPT give the most natural dialogue, and Gemini's large context handles book-length subtitles.
How do I keep names and proper nouns consistent? Add a glossary in the System Prompt (e.g. "Keep verbatim: iPhone, OpenAI, John Smith") on any LLM engine; all episodes share the same context, so terminology stays consistent across a season.
Do I need "preserve timecodes / line numbers" prompts? No. Timecodes, cue numbers, and headers are extracted locally and re-inserted after translation — the model never sees them. Keep your prompt focused on style, glossary, and tone.
Is it private? Yes. Everything runs client-side: subtitle parsing, translation requests, and caching all happen in your browser. API keys are stored only in local browser storage, and LLM requests go directly from your browser to your configured endpoint.
See the full FAQ in the docs for more.
快速批量字幕翻译工具，支持多种格式
- 跨境业务、多语言内容运营团队
- 先在测试环境跑通最小用例，再接入生产数据
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
- 云端托管：可放在 Vercel / Railway / Fly.io 等 PaaS 平台
⚡ 核心功能
- 开源免费，支持本地部署，数据完全自主可控
- 活跃的 GitHub 开源社区，持续迭代更新
- 提供详细文档和使用示例，新手友好
- 支持自定义配置，灵活适配不同使用环境
- 可作为基础组件集成进现有技术栈或进行二次开发
- 跨境业务、多语言内容运营团队
- 先在测试环境跑通最小用例，再接入生产数据
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
👥 适合人群
🎯 使用场景
- 本地部署运行，保护数据隐私，满足合规要求
- 自定义集成到现有系统，扩展技术栈能力
- 作为开源基础组件进行商业化二次开发
⚖️ 优点与不足
- +MIT 协议，可免费商用
- +完全开源免费，无授权费用
- +本地部署，数据完全自主可控
- +开发者社区支持，遇问题可查可问
- −安装和初始配置可能需要一定技术基础
- −功能完整性通常不如成熟商业产品
- −技术支持主要依赖开源社区，响应速度不稳定
AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一，可自由商用、修改、分发，仅需保留版权声明。
🔗 相关工具推荐
❓ 常见问题 FAQ
经综合评估，字幕翻译 在AI工具赛道中表现稳健，质量优秀。如果你已有明确的使用需求，可以直接上手体验；如果还在评估阶段，建议对比同类工具后再做决策。
| 原始名称 | subtitle-translator |
| Topics | batch-translationbilingual-subtitlessrtassvttlrc |
| GitHub | https://github.com/rockbenben/subtitle-translator |
| License | MIT |
| 语言 | TypeScript |
收录时间：2026-06-04 · 更新时间：2026-06-04 · License：MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。