







Copy text out of photos, screenshots and scans with browser-based OCR in English and Hindi, with tips for accurate results from receipts and phone shots.
BabelStone : Tangut Script
These tools allow you to find a particular Tangut character or entry in a photographic image of a page of the text.
OpenAI’s updated image generator can now pull information from the web
ChatGPT Images 2.0 can create more “sophisticated” images, according to OpenAI.

jphastings/dotpostcard
A tool for archiving & converting scans of postcards, and information about them.
Page to Markdown
A scanned page, photo or PDF turned into markdown on your GPU: Datalab's Indra OCR (12M parameters) ported to WebGPU, reproducing the Python package line for line, with 4 MB of fp16 models and per-script recognizers and word models fetched on first need

beatrizalmeidaf/papero-pdf-text-extractor
Fast, open-source PDF text extraction API. Files never stored.
ocrmypdf/OCRmyPDF
OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
Rooms with Text: A Dataset for Overlaying Text Detection
In this paper, we introduce a new dataset of room interior pictures with overlaying and scene text, totalling to 4836 annotated images in 25 product categories. We provide details on the collection and annotation process of our dataset, and analyze its statistics. Furthermore, we propose a baseline method for overlaying text detection, that leverages the character region-aware text detection framework to guide the classification model. We validate our approach and show its efficiency in terms of binary classification metrics, reaching the final performance of 0.95 F1 score, with false positive and false negative rates of 0.02 and 0.06 correspondingly.

alan-turing-institute/ReadabiliPy
A simple HTML content extractor in Python. Can be run as a wrapper for Mozilla's Readability.js package or in pure-python mode.
SOTA OCR with Core ML and dots.ocr
We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Introducing ChatGPT Images 2.0
ChatGPT Images 2.0 introduces a state-of-the-art image generation model with improved text rendering, multilingual support, and advanced visual reasoning.

Becky Isjwara on Twitter / X
I made a Codex-native app that can transfer highlights from my paperbacks to my ebook copies.Osmo Pocket takes photos and sees the highlight. Takes a pic, uses OCR, then uses computer use to highlight my Kindle copy.Everything syncs on @readwise ✨ pic.twitter.com/wTD80t9QpA— Becky Isjwara (@beckyisj) October 12, 2026
LlamaIndex | AI Agents for Document OCR + Workflows
LlamaParse is the world's best agentic OCR for processing complex documents with messy tables, charts, images, and more with human-level accuracy.

ChatGPT Images 2.0 is a breakthrough that could fundamentally reshape graphic generation
OpenAI is adding reasoning and web search to its ChatGPT Images 2.0 image generator. The model can now create up to eight consistent images from a single prompt and handles text in general, and especially in non-Latin scripts, significantly better.

isaqueseneda/shieldfont
A web font that protects written content from AI scraping — humans see the text, scrapers see a plausible decoy.
Oskar 🕊️ (@austegard.com)
OCR a scan, in your browser, on your phone, in about a second: austegard.com/experiments/...