Image to Text

Copy the text out of photos, screenshots and scans in Hindi, English and 12 more languages.

Processed in your browser — files never leave your device

Drop files here

or

Select files

About Image to Text

Copy the text out of photos, screenshots, scanned pages and bills. English, Hindi, Marathi, Bengali, Gujarati, Punjabi, Tamil, Telugu, Kannada, Malayalam, Urdu, Spanish, French and German are supported, and several images can be read at once. The text appears ready to copy, or downloads as .txt or Word — read on your device, never uploaded.

How Image to Text works

Image to Text uses Tesseract, the open-source OCR engine, compiled to run in your browser. Each image is placed on a white background and enlarged when it is small, because Tesseract reads letters best when they are about 30 pixels tall. The text is then recognised line by line in the language you choose.

For a language other than English, English is read alongside it by default, so mixed text such as a Hindi bill with English item names comes out right. Several images are read one after another and their text is put together under each file's name. The language data for each language (1–3 MB) is downloaded from our own server the first time it is used.

When to use Image to Text

  • Copy a phone number, address or paragraph from a screenshot.
  • Get the text of a printed notice, notes or textbook page without retyping it.
  • Pull item names and amounts out of a photographed bill or receipt.
  • Turn a scanned Hindi or regional-language letter into editable text.

How to use Image to Text

  1. Add your images. Drop one or more JPG, PNG or WebP photos, screenshots or scans into the box above.
  2. Choose the language. Pick the language of the text; keep “Also read English words” on for mixed text.
  3. Get the text. Click Get text, then copy it or download it as a .txt or Word file.

Tips for the best result

Straight and sharp
Photograph the page from directly above in good light. Blurry, tilted or curved pages are read less accurately.
Crop first
Text that fills the picture reads better than a small paragraph in a big photo. Crop Image can help.
PDF files
For scanned PDFs, OCR PDF adds a searchable text layer to the PDF itself.

Frequently asked questions

Can it read handwriting?

Only neat, printed-style handwriting, and not reliably. The recogniser is trained on printed text, so typed documents, screenshots and printed forms give the best results.

Which languages can it read?

English, Hindi, Marathi, Bengali, Gujarati, Punjabi, Tamil, Telugu, Kannada, Malayalam, Urdu, Spanish, French and German.

Why are some words wrong?

OCR can confuse similar shapes such as 0 and O or 1 and l, especially in small or blurry print. Always check names, numbers and amounts against the image.

Are my images uploaded?

No. Text recognition runs in your browser; your images never leave your device.

Is Image to Text free?

Yes. Image to Text on DocEpic is free, with no sign-up, no watermark and no limit on how often you use it. The site is supported by ads.

Are my files safe with Image to Text?

Yes. Image to Text runs entirely in your web browser, so your files never leave your device and are never uploaded to us.

Do I need to install any software?

No. Image to Text works in any modern browser on Windows, macOS, Linux, Android and iPhone.

Is there a file size limit?

Files up to 25 MB are accepted. Because the work happens on your device, very large files depend on your device's memory.

Related tools