Image to Text (OCR)

Turn the text in photos, scans and screenshots into editable text you can copy. Supports 9 languages including English, Spanish, German and Japanese – your images never leave your device.

🔒 Files and inputs never leave your device
Choose an image Drop a photo, scan or screenshot here or paste it with Ctrl+V · Images never leave your device

Text language

iPhone app · Free to downloadScanner - Scan to PDF, DocsScan paper documents into clean PDFs with your iPhone.View on the App Store

About the Image to Text (OCR)

This image to text converter uses OCR (optical character recognition) to read printed text in a picture and turn it into plain text. Instead of retyping a paper document or a quote from a screenshot, just drop in the image and copy the result.

It runs the open-source Tesseract OCR engine inside your browser, so your images are never uploaded. Only the first run downloads the engine and the language data (1–3 MB per language); after that they are loaded from your browser’s storage.

How to use

  1. Click Choose an image to pick a photo or scan, or paste a screenshot with Ctrl+V.
  2. Select the language(s) of the text. Choosing only the languages that actually appear makes OCR faster and more accurate.
  3. When the progress bar reaches 100%, the text appears in the box below. You can fix any mistakes right there.
  4. Click Copy text or Save .txt to take the result with you.

Worked examples

Copying the details from an invoice screenshot

Input
A screenshot invoice.png (1100×390) with three lines of 60px text, language English (the default on this page), Grayscale & contrast boost on
Result
On the first run the hint says about 4.15 MB will be downloaded. The box then shows Invoice No. 10482 / Total due: $1,249.50 / Due date: November 14, 2026 with the original line breaks, plus 56 characters · estimated accuracy 95%. Save .txt gives invoice.txt.

The character count leaves out spaces and line breaks. Even at 95%, double-check amounts and reference numbers before pasting them anywhere important.

Tiny text needs zooming in first

Input
An 1100px-wide screenshot with one line in 13px type: “Meeting moved to Room 4B at 3:30 PM”
Result
The status shows “No text found” and the box stays empty. The same sentence captured at 20px is read perfectly, with 28 characters · estimated accuracy 95%.

Small images are upscaled automatically, but text that is too small to begin with has blurred strokes. Zoom in on screen and capture only the part you need, or trim it with the Image Cropper.

Common mistake: reading German with English selected

Input
An image saying “Rechnung über 49,90 € / Fälligkeit: 15. März 2026”, languages English only, then English + German, then German only
Result
With English only – and even with English + German – the umlauts are lost: Rechnung uber … Falligkeit … Marz. With German alone the text comes back exactly, at 95% estimated accuracy.

For accented languages, select only the language of the document. The estimated accuracy can stay high even when accents are dropped, so check names and words with special letters by eye.

Tips for better OCR results

  • Shoot the page straight on and well lit. Skewed or shadowed photos lose a lot of accuracy.
  • Text with a cap height of 20 pixels or more reads well. For tiny print, zoom in and capture just that part (small images are upscaled automatically).
  • Keep Grayscale & contrast boost on for colored backgrounds and blurry photos.
  • Select only the languages in the document – extra languages can turn letters into similar-looking characters from another script.
  • Tables, handwriting, vertical text and decorative fonts are less accurate.

Download size per language

LanguageDownload
OCR engine (shared, once)about 1.4 MB
Englishabout 3.0 MB
Spanishabout 2.1 MB
Japaneseabout 2.0 MB
Chinese (Traditional)about 1.7 MB
German, French, Portuguese, Italian, Korean0.7–1.7 MB each

Downloaded data stays in your browser’s storage, so next time recognition starts right away. If you’re on mobile data, consider doing the first run on Wi-Fi.

FAQ

Are my images uploaded to a server?

No. Text recognition runs entirely in your browser on your own device. Only the OCR engine and language data are downloaded – your images and the extracted text are never sent anywhere.

Does it read handwriting?

Neat block letters sometimes work, but the engine is trained for printed text, so handwriting accuracy is low.

Can I extract text from a PDF?

Only image files are supported. For a scanned PDF, convert the pages to JPG with PDF to Image first. If the PDF has selectable text, copying it directly in a PDF viewer is more accurate.

Why does the first run take longer?

The first time, the OCR engine and language data have to be downloaded. After that the stored copy is used and recognition usually finishes in a few seconds; very large photos take longer.

Can I use iPhone HEIC photos?

Yes. HEIC/HEIF photos are read directly. In browsers that can’t open HEIC themselves, such as Chrome and Edge, a small decoder (about 0.7 MB) is downloaded the first time, so the first photo takes a little longer. The photo still never leaves your device.