Image to Text (OCR)
Upload an image and extract every word inside it — English & Hindi supported, 100% in your browser.
What is the Image to Text (OCR)?
The Image to Text (OCR) tool reads printed or handwritten text from an image and gives you back a plain, editable transcript. It uses an optical-character-recognition (OCR) engine that runs entirely inside your browser, so no scans of documents ever leave your device.
OCR turns unsearchable image files into text you can edit, translate, quote or paste into any other application. This is a game-changer for students digitising notes, researchers copying quotes from books, teams archiving whiteboard photos or professionals extracting data from screenshots.
Support currently includes English and Hindi. You can drop in a JPG, PNG or WebP, wait for the engine to load once, and re-use the recognised text however you like.
How to use the Image to Text (OCR)
- 1Upload a photo or screenshot that contains text.
- 2Choose the language of the text (English or Hindi).
- 3Wait a few seconds for the OCR engine to load (first time only).
- 4Watch the text appear in the results box as it is recognised.
- 5Copy the entire text or download it as a .txt file.
Key features
- Multi-language recognition (English, Hindi)
- Runs 100% in the browser — nothing uploaded
- Handles printed and handwritten text
- Copy or download as .txt
- Preserves basic line breaks
- Works with photos, screenshots and scans
- No account or install required
Examples
Textbook page
Snap a photo of a textbook and get an editable transcript to paste into your notes app.
Whiteboard photo
Convert a meeting whiteboard shot into typed minutes for sharing.
Business card
Extract name, phone and email from a business card photo to save into your contacts.
Why use this tool
- Turns images into editable text in seconds
- Keeps sensitive documents private — nothing uploads
- Great accessibility aid for people with low vision
- Speeds up digitising physical notes
- Works on mobile so you can OCR straight from your camera
Common use cases
- Digitising handwritten class notes
- Copying quotes from a physical book
- Extracting text from screenshots
- Turning whiteboard photos into meeting notes
- Reading a scanned document into an editable format
- Grabbing text from posters or flyers
Frequently asked questions
How accurate is the OCR?
Printed text on clean backgrounds is 95%+ accurate. Handwriting and low-light photos are 60–80% accurate.
Does the tool support other languages?
English and Hindi at the moment. More languages are planned.
Are my images uploaded?
No. Everything happens inside your browser using WebAssembly.
Why is the first recognition slow?
The OCR engine (~2 MB) has to download on first use. Later runs are much faster because it is cached.
Can I OCR a PDF?
Export the PDF pages to images first, then run each through this tool.