LLM Translator

Translate selected text and selected screen regions with OpenAI-compatible or Anthropic models.

LLM Translator helps you translate and understand web pages, PDFs, screenshots, and technical documents directly in your browser. It is designed for users who often read papers, documentation, articles, scanned PDFs, or images containing text. You can translate selected text, capture a screen region, or translate the current visible page. The side panel also lets you ask follow-up questions after a screenshot translation. Key use cases: Translate selected text on web pages and PDFs. Translate screenshots or scanned document regions. Translate the current visible page, useful for PDF readers and scanned pages. Ask follow-up questions in the side panel. Preserve Markdown formatting, tables, lists, code blocks, superscripts, subscripts, and formulas. Configure OpenAI-compatible APIs, Anthropic APIs, or local llama.cpp servers. Customize target language, prompts, model presets, theme color, image compression, cropping, and thinking mode. Why install it: LLM Translator reduces the need to copy text between pages, OCR tools, and chat applications. It keeps translation, OCR, formatting, and follow-up questions inside the browser, making it especially useful for research, technical reading, documentation review, and multilingual study workflows.