Skip to content
Kitvoo

Image to text

Extract text from photos (OCR)

Drop an image to extract text from here

You can also paste (Ctrl+V) · Up to 20MB per file

Your image is never sent to a server — it's read inside this browser. Only the recognition program and the language data you choose are downloaded.

How to use

  1. Drop an image here or click Choose files. You can also paste a screenshot with Ctrl+V.
  2. Under Languages in the image, select the languages the image contains.
  3. Press Extract text and wait for the progress to finish.
  4. Fix any mistakes in the Extracted text box, then press Copy.

FAQ

Is my image uploaded to a server?

No. When you press Extract text, only the recognition program (tesseract.js) and the language data you selected are downloaded from jsDelivr. The image itself is read inside this browser, so you do need an internet connection to run it.

What images can I use?

PNG, JPG, WebP, and BMP, one image at a time, up to 20 MB. iPhone photos in HEIC format aren’t supported directly, so convert them with HEIC to JPG first.

Why is the first extraction slow?

During “Getting ready”, the recognition program and language data are being downloaded. Each extra language adds more data, so select only the languages that actually appear in the image.

Can it read images that mix languages?

Yes. Korean and English are both on by default, and you can add Japanese or Chinese (Simplified or Traditional). Your language choice is remembered for next time. At least one language must stay selected.

The text is missing or comes out garbled.

First check that the right languages are selected. Handwriting, tilted photos, blurry or tiny text, and busy backgrounds are hard to recognize. Cropping the image down to just the text with Crop image often helps.

It says it couldn’t extract the text.

This usually means the recognition program or language data couldn’t be downloaded. Check your connection and try again. It can also happen on networks that block cdn.jsdelivr.net.