Screen OCR Translator — Alex

Extract and translate text from images, comics, scans, or any area of a web page without leaving your current tab. Free and open source.

Text recognition (OCR) runs locally in your browser. Translation uses Google Translate by default, or you can use DeepL with your own API key or connect your own LLM endpoint.

How to use:

1. Activate the extension from the browser toolbar or context menu, or press Ctrl+Shift+F.
2. Select an area of the page.
3. Click "Translate".

To translate an image directly, right-click it and select "Translate this image".

Use the Live translation for text that keeps changing on screen, such as hardcoded video subtitles.

Features:

• Local OCR powered by PaddleOCR
• Support for Latin, Chinese, Japanese, Cyrillic, Korean, Arabic, and Devanagari scripts
• Automatic source-language detection
• Speech-bubble detection for manga and comics
• Display translations directly over the original content or in a separate panel
• Copy recognized or translated text to the clipboard
• Text-to-speech through Google TTS
• Live translation mode for translating text that keeps changing on screen, such as hardcoded video subtitles
• Connect your own LLM endpoint (llama.cpp, LM Studio, and other compatible providers)

GitHub: https://github.com/OPerepadia/ocr-translator-extension
Chrome version: https://chromewebstore.google.com/detail/screen-ocr-translator/legljemohhhablgapleoakcepoofloae