Skip to content

Image to text (OCR)

Extract text from photos and screenshots with OCR, without sending the image to third parties.

AvailableIn your browserInput: Image

How to use: Image to text (OCR)

  1. Choose a PNG, JPG or WebP image that contains text (a photo of a document, a screenshot…).
  2. Select the language of the text and press “Extract text”.
  3. Check and correct the recognised text, then copy it or download it as .txt.

What it accepts and what you get

Input
A PNG, JPG or WebP image of up to 15 MB and 40 megapixels, with printed text in Spanish or English.
Output
The recognised text (editable) and a summary with the word count and the engine's average confidence.
Where your data is processed
Your data is processed in your browser and is not sent to our servers.

Limitations and notes

  • Recognition runs in your browser with Tesseract: the image is not sent anywhere. The first time, about 7 MB (engine and language) are downloaded from this same site.
  • It works best with printed, straight, sharp text with good contrast. Handwriting is not recognised well.
  • No OCR is perfect: always check the result, especially figures, names and addresses. Words with low confidence are counted separately.
  • It only works with images; for a scanned PDF use the OCR tab of the PDF Editor, which recognises one page at a time.

Frequently asked questions

Why is the first run slow?

Because the browser has to load the OCR engine and the language data. Later runs are faster.

Related tools