What is Screenshot OCR?

Screenshot OCR is a tool that captures screenshots and uses Optical Character Recognition (OCR) to extract text from the image. It supports both Japanese and English languages.

What output formats are supported?

The extracted text can be output in various formats, including JSON, Markdown, vertical, and horizontal.

How do I use Screenshot OCR?

You can integrate it with Claude Desktop using the provided configuration. Instruct Claude to take a screenshot and recognize the text. For example: 'Please take a screenshot of the left half of the screen and recognize the text in it.'

Screenshot

Name: Screenshot
Author: kazuph

bykazuph

•

生产力与工作流

开发者工具

其他

Captures screenshots and performs OCR text recognition using two engines, with Japanese and English support.

Screenshot captures areas of the screen and uses OCR to recognize text. It uses yomitoku as its primary OCR engine for high-accuracy Japanese text recognition, and Tesseract.js as a fallback engine for both Japanese and English. The tool provides multiple output formats including JSON, Markdown, vertical, and horizontal. This server can be configured to work with Claude desktop by modifying the `claude_desktop_config.json` file.