Using AI, extract text from any image in seconds. Two engines: on-device Tesseract (private) and server-side OCR (accurate) — just like the iOS app.
Select an engine, upload an image, and get your text.
Everything you need to turn images into editable text.
Tesseract.js runs entirely in your browser — no upload, fully private. Like Apple Vision on iOS.
Server-side Tesseract with OpenCV preprocessing for documents, uneven lighting, and complex layouts.
English, Persian, German, French, Japanese, Arabic, Chinese, Russian and more.
Tesseract mode never sends data anywhere. Cloud mode discards images immediately after OCR.
One click copies all extracted text to clipboard, ready to paste anywhere.
No subscriptions, no premium tiers, no hidden costs. Free forever.
Three steps from image to editable text.
Pick Tesseract for private on-device OCR, or OCR Cloud for higher accuracy on complex images.
Drag and drop or click to browse — JPG, PNG, WEBP, TIFF and more.
Review the extracted text and copy it to clipboard instantly.