Show HN: Local-first fast CPU OCR for images, PDFs, webpages

Category: cli-tool

Tags: ocr, on-device, cli-tool

Score: 6.8/10 (Innovation: 6, Technical: 6, Documentation: 8, Utility: 7)

textsnap is a local-first, CPU-only OCR tool that converts images, screenshots, and webpages to text using a quantized vision-language model. It supports clipboard input/output and offline operation after first model download, making it interesting for privacy-conscious users and those without GPU access.

Target audience: backend devs, devops, data engineers

Repository: https://github.com/kouhxp/textsnap · Python · MIT · 45 stars

View on Hacker News