OCR It – pull text out of un-copyable documents for your LLM
github.com
August 24, 2026
11 min read
52/100
Summary
OCR It is an unpacked Chrome extension that captures a fixed on-screen region from paginated documents, recognizes its text locally, and builds an editable transcript. Users draw the capture region once, then press Option-Shift-S on each page; screenshots are queued while bundled Tesseract OCR runs in the background. Option-Shift-A can automate capture and page turning until the document ends, while Option-Shift-R redraws the region. Exports preserve page order with page-number separators, and each captured page retains a thumbnail for checking crop alignment or rerunning faulty OCR. The extension makes no outbound network requests and requires no API key. It ships with English, Portuguese, and Spanish Tesseract models; additional models from Tesseract’s roughly 100 supported languages can be bundled before installation. Automatic page turning can target a clicked screen coordinate or dispatch a key such as ArrowRight, including in cross-origin iframes and Shadow DOM when the necessary site permission is granted. Runs stop after two identical pages by default, on OCR failures, failed page turns, a 300-page cap, tab closure, or browser restart. Chrome’s PDF viewer supports manual capture and text extraction, but cannot be auto-advanced because extensions cannot inject into its plugin. OCR accuracy depends on source quality; crisp rendered text is reported to reach more than 90% confidence, while scans and handwriting may need cleanup.
Key Takeaways
- OCR It uses bundled Tesseract to perform OCR entirely on the local machine, without API keys, network requests, or image uploads.
- A fixed capture region can be processed manually with Option-Shift-S or repeatedly through an Option-Shift-A auto-run that captures, turns pages, and detects repeated final pages.
- Automatic page turning can use a clicked control location or a keyboard event, and supports embedded cross-origin frames after a durable site permission is granted.
- The extension ships with English, Portuguese, and Spanish language models; developers can vendor additional Tesseract language models into the extension.
- Chrome’s built-in PDF viewer can be captured manually but cannot be automatically paged by the extension.
What the discussion said
The conversation quickly moved beyond the extension itself to the harder problem it exposes: getting usable text into an LLM when source material is scanned, image-based, or trapped inside a viewer. Readers with piles of handwritten mathematical notes saw real value in avoiding weeks of manual transcription, and several proposed modern vision-language models or specialized OCR systems as far stronger options than legacy OCR. The practical appeal is not merely transcription: semantic models can pull the relevant field from a cluttered image instead of dumping raw text that needs regex cleanup. There was broad agreement that Tesseract is no longer the obvious local default. Suggestions ranged from compact local multimodal models to browser, OS, and dedicated OCR tools, with the recurring advice to benchmark against the actual documents, especially handwriting, formulas, tables, and poor scans. One firsthand account warned that even strong LLM transcription can silently substitute mathematically plausible notation for what was actually written, making it dangerous when fidelity matters. The extension’s region-lock and automatic pagination workflow was considered convenient for long, unselectable documents, and its visible confidence scores and page thumbnails were praised as useful safeguards. Skepticism focused less on the workflow than on its modest tested accuracy, unproven behavior on bad scans, and the project’s AI-generated presentation and apparent lack of mature real-world use.
Where opinion split
The sharpest dispute is whether general-purpose multimodal LLMs are good enough for document transcription or whether specialized OCR should lead. Advocates say current VLMs understand layouts and can extract the exact requested information with far less cleanup; skeptics note that they may invent mathematically sensible substitutions, so a plausible transcript is not necessarily a faithful one.
Community Sentiment
Positives
- Modern vision-language models make OCR materially more useful by extracting intended fields from images, posters, layouts, and tables instead of producing raw text that needs brittle post-processing.
- Specialized OCR systems were reported to handle handwriting, formulas, complex layouts, and tables accurately at substantially lower cost than flagship hosted multimodal models.
- A pinned capture region plus automatic page turning turns hundreds of uncopyable pages into an LLM-ready transcript without the drudgery of manual screenshots.
- Per-page confidence indicators and capture thumbnails make OCR failures inspectable, reducing the risk that bad pages disappear unnoticed into model context.
Concerns
- LLM transcription can replace handwritten mathematical notation with a mathematically plausible alternative, a subtle fidelity failure that is unacceptable when the original wording or symbols matter.
- The extension's reported 93–95% confidence comes from clean rendered text, leaving its performance on degraded scans—the cases where OCR is most needed—largely untested.
- Legacy local OCR is widely viewed as disappointing in real documents, and commenters argue it should not be assumed to remain the local benchmark.
- AI-generated project copy and signs of an extremely new, lightly exercised tool made some readers doubt whether the workflow has survived real-world use.
