Home › All tools › Image to Text (OCR)
Image to Text Converter (OCR)
- Files stay on your device
- No sign-up
- No watermark
- No daily limit
- Full resolution
Pull the text out of a photo, screenshot, scanned page or receipt and copy it or save it as a .txt file. Recognition runs on your own device with the open-source Tesseract OCR engine – your image is never uploaded.

- 1 Upload
- 2 Adjust & process
- 3 Download
How to use
How to use Image to Text (OCR)
- Choose an image, drop it on the box, or paste a screenshot with Ctrl+V (⌘V on a Mac).
- Pick the language the text is written in.
- Press Extract text. The first run downloads the OCR engine and language model (about 3–7 MB); later runs are faster.
- Check the result, fix any mistakes, then copy it or download a .txt file.
Tips for accurate results
- Use a sharp, well-lit photo taken straight on; crop away everything except the text if you can.
- Printed text works best. Handwriting, decorative fonts, very small text and low-contrast images give weaker results.
- OCR is not perfect – always proofread names, numbers and amounts before you rely on them.
- For multi-page scanned PDFs, use PDF to Word; to make a clean scan from a phone photo first, use the Document Scanner.
🔒 Privacy: the image is read only in your browser. The OCR engine and the English and Hindi language models are served by Crop Desk; the Spanish, French, German, Portuguese and Italian models are downloaded from the public jsDelivr CDN. No image or text is sent to any server.
FAQ
Frequently asked questions
Is my image uploaded?
No. Text recognition runs in your browser with Tesseract.js. Only the OCR engine and language model files are downloaded to your device.
Which languages are supported?
English, Spanish, French, German, Portuguese, Italian and Hindi, plus a combined English + Hindi mode. Pick the language that matches your image for the best accuracy.
Can it read handwriting?
Only sometimes. The engine is trained mainly on printed text, so neat block handwriting may work but cursive usually will not.
Why is the first run slow?
The first time, your browser downloads the OCR engine and the language model (a few megabytes). They are cached, so the next images are processed faster.
Is there a size limit?
Images up to 25 MB are accepted. Very large photos are scaled down to 4000 pixels on the long side to keep memory use reasonable on phones.