ToolsMaxxing
English
EnglishEspañolPortuguêsBahasa Indonesiaहिन्दीবাংলাРусскийTiếng ViệtFrançaisDeutschTürkçeالعربية

Image to text (OCR)

Read the text in a photo, screenshot or scan and copy it or save it as a .txt file. Bangla, English and 25 more languages.

or drag and drop images here

JPG, PNG, WebP, GIF, AVIF or BMP images · Multiple files supported

Your files stay on your device

  1. 1Add files
  2. 2Adjust
  3. 3Download

How it works

  1. 1Choose one or more images, up to 10 at a time.
  2. 2Pick the language of the text. Tick the English box if the page mixes in English words.
  3. 3Select Extract text. The first time, the language data downloads once and is kept by your browser.
  4. 4Copy the text or download it as a .txt file, and check it against the picture.

What the options do

Language
The language the text is written in. It is set to the language of this page when we support it. Reading works best when this matches the picture.
Also recognise English
Adds English to the main language. Use it for pages that mix, for example, Bangla with English names or numbers.
Layout
Text on a page reads a whole page in order, with paragraphs. Scattered text is for screenshots, posters, signs and short lines spread out on the picture, where page reading can skip lines.
Improve contrast
Turns the picture to gray and stretches the contrast before reading. It helps faint scans and photos of paper. Turn it off for clean screenshots if a result looks worse.

Privacy

This tool runs in your browser. Your files are never uploaded to a server.

Questions people ask

Is my image uploaded?

No. The picture is read inside your browser. Only the language data, a file of a few megabytes with no personal information, is downloaded once from a public software repository and then kept in your browser.

How accurate is it for Bangla?

Clean, printed Bangla text at a good size reads well, with the occasional wrong conjunct or matra. Handwriting (this OCR is made for printed text), decorative fonts, low-resolution photos and curved pages give poor results. Always read the output against the picture.

Why is the text full of mistakes?

Usually the picture is blurry, small, tilted or has a busy background. Try a sharper photo, crop to the text, rotate it upright, choose the right language, or switch the contrast option.

Why are some lines missing?

Page reading can skip short or widely spaced lines, for example in a poem, a poster or a screenshot. Choose Scattered text under Layout and run it again.

Does it keep tables and columns?

Not as a table. You get the text in reading order, one line per line of text. Columns can end up mixed together.

Why does the first run take longer?

The engine and the language data are downloaded the first time. After that, your browser reuses them and the next run starts straight away.

Related tools