Show HN: CPU-only fast OCR for screenshots, images, PDFs, webpages

Category: cli-tool

Tags: ocr, offline, cli-tool, cpu-only, python

Score: 7.0/10 (Innovation: 6, Technical: 7, Documentation: 8, Utility: 7)

Textsnap is a CPU-only OCR tool that extracts text from screenshots, images, PDFs, and webpages using a quantized vision-language model. Its ability to run fully offline, support clipboard in/out, and function as a portable single-file tool makes it interesting for privacy-conscious and GPU-less workflows.

Target audience: backend devs, devops, data engineers

Repository: https://github.com/kouhxp/textsnap · Python · MIT · 23 stars

View on Hacker News