Show HN: Local-first fast CPU image to text for screenshots, PDFs, webpages

Software Development, AI & Machine Learning, DevOps & Infrastructure(github.com)view on HackerNews
textsnapOCRimage-to-textPythonPaddleOCR-VLONNXCPUvision-language modelofflineportablecustomizable output.

Author: mrkn1

Date: 6/5/2026

Article Summary:
A Python tool named textsnap for converting images, screenshots, and web pages into plaintext using a CPU-based vision-language model, with features like offline operation, portable mode, and customizable output.