xnx3/translate

AI i18n, Two lines of js realize automatic html translation. No need to change the page, no language configuration file, no API key, SEO friendly!

What it solves

This project provides a way to implement automatic, AI-powered internationalization (i18n) for HTML pages without requiring manual translation files, API keys, or changes to the original page structure. It eliminates the need for developers to create and maintain complex language configuration files for every supported language.

How it works

It is a JavaScript library that scans the DOM of a webpage to automatically identify and translate text content. It supports multiple translation service channels (including a default open-source service and the ability to use private deployments or LLM-based APIs like GiteeAI). To ensure performance, it uses multi-threaded acceleration, a three-layer caching mechanism, and text pre-processing cleaning.

Who it’s for

Web developers and site owners who want to add multi-language support to their websites quickly and automatically, as well as organizations requiring private deployment of translation services for data privacy and security.

Highlights

  • Easy Integration: Add a few lines of JavaScript to a page to enable translation into hundreds of languages.
  • Detailed Control: Ability to specify translation areas, exclude specific IDs/classes/tags, and define custom terminology.
  • Dynamic Content Support: Monitors the DOM for changes (e.g., in Vue or React apps) to translate content rendered via JavaScript in real-time.
  • Private Deployment: Supports self-hosting the translation API service for secure, offline, or internal network environments.
  • SEO Friendly: Does not modify the original source code crawled by search engine bots.
  • Dedicated Model: Includes a distilled Transformer-based model (translate100) optimized for low-end hardware (1-core, 2GB RAM) to ensure translation reliability.

Related

  • Project
    rockbenben/subtitle-translator

    Subtitle Translator is a free, browser‑based (and CLI) tool that batch‑translates subtitle files (.srt, .ass, .vtt, .lrc) into 120+ languages. It strips timecodes locally, sends only dialogue to chosen translation APIs (traditional MT or LLM providers), then re‑inserts the original timing. Features include ~1 s per episode processing, multi‑file upload, bilingual output, context‑aware LLM translation, unlimited local caching, and full client‑side privacy.

  • Project
    alibaba/page-agent

    A client-side JavaScript library that embeds an AI agent into web pages for natural language DOM manipulation and automation without requiring headless browsers.

  • Project
    aymericzip/intlayer

    An AI-powered internationalization solution for web and mobile apps that provides per-component content management, a visual editor, and a CMS.

  • Project
    1c7/Translate-Subtitle-File

    A subtitle translation tool that lets users connect their own translation API keys to translate .srt, .vtt, and .ass files cheaply and efficiently.

  • Project
    browser-use/browser-use

    Browser Use is an open‑source Python/TypeScript library that gives LLM agents full control over a real or cloud‑hosted web browser. It provides 31 browser actions as tools, supports custom functions, works with OpenAI, Anthropic, Google models or its own BU2 model, and offers three usage modes: a fully hosted cloud API, a CLI for existing agents, and a library you embed in your code. Ideal for automating web tasks, building AI assistants that browse, or researching LLM‑driven web navigation.