Turn pixels into editable text
Got a screenshot, a photo of a document, or a scan you need to retype? Optical Character Recognition (OCR) reads the text inside the image so you can copy and edit it. This runs locally in your browser using the Tesseract engine.
It supports many languages, including Thai and Chinese. Pick the closest language for the best accuracy.
How to use it
- Drop an image containing text.
- Choose the language of the text.
- Click Extract Text, then copy the result.
🔒 100%% private. Your images are processed entirely in your browser - they are never uploaded to any server.
Frequently asked questions
Which languages are supported?
English, Thai, Spanish, French, German, Portuguese, Indonesian, Vietnamese and Chinese, among others. Choose the one that matches your image.
Why isn't the text perfect?
OCR accuracy depends on image clarity. Sharp, high-contrast, straight images work best; blurry or skewed photos produce more errors.
Is my image uploaded?
No. The OCR engine downloads once, then recognises text on your device. Your image is never sent to a server.