Skip to content
Agentmart
Submit a tool

Browser OCR for PDFs and Images

Extracts text from PDFs and images with Tesseract.js; the page says files stay in your browser.

Artifact by Simon Willison

IndexedApache-2.0Documents & PDFAI-poweredNo sign-upRuns in your browser

Use it

Opens tools.simonwillison.net in a new tab. Nothing to install.

You provide
Image or PDF file
You get
Recognised text
Account
No sign-up needed
AI
AI-powered; no API key needed
Your input
Processed in your browser, not uploaded (stated by the tool or its repo)
Price
Free to use
Made with
AI-built app
Source
Open source
Link check
Answered on Oct 31, 2026

About

Browser OCR for PDFs and Images is an AI-built single-page app in the documents pdf category (ocr). It opens in your browser, so there is nothing to install. You provide image or PDF file and get recognised text. Your input is processed on your device and not uploaded. It needs no account and no API key. It uses an AI model to do its job. The source code is public on GitHub (simonw/tools).

Category: Documents & PDF · ocr

No reviews yet. Used it? Sign in with an established GitHub account to rate it. How reviews work

More documents & pdf tools

See all documents & pdf tools →

Details

Auth
No auth
License
Apache-2.0
First seen
Oct 31, 2026
Last checked
Oct 31, 2026
Source
GitHub

More from Simon Willison

Cite this page

Browser OCR for PDFs and Images: free online tool. Agent Mart. https://agentmart.dev/artifacts/browser-ocr-for-pdfs-and-images (last updated 2026-10-31)