Image to text, without the detour
Copy text from screenshots, receipts, labels, or scanned notes in a few clicks. Edit each result, copy it all, or save a plain UTF-8 text file.
Private, local OCR
Turn any image into editable text
Drop in a screenshot, scan, or photo. BrowserOCR finds and reads the words on your device—nothing gets sent to a server.
✓ No uploads✓ English + Chinese✓ Works offline after caching
Recognition model
Preparing private OCR…Editable result
Text will appear line by line.
Two sizes, one private engine
Fast mode keeps the first model download compact. High accuracy is an optional recognition upgrade and is downloaded only after you choose it.
Built for multilingual text
The bundled PP-OCRv6 recognition dictionary supports English, simplified and traditional Chinese, and mixed lines.
A useful offline tool
Once the application and models are cached, recognition can run without a connection. Your browser controls and can clear that storage.
Common questions
Frequently asked questions
Does BrowserOCR upload my image?
No. Image decoding, text detection, and recognition run inside a dedicated worker in your browser.
Which image formats work?
The first release accepts one JPEG, PNG, or WebP image, including a photo from your phone camera.
What is High accuracy mode?
It replaces the Tiny recognition model with a larger Small model. It may read detected characters more accurately, but does not change text detection.
Can I use it offline?
Yes, after the app and selected OCR models have been cached during an online visit.