Image to Text Converter — Copy Text from Photos & Screenshots, Free

Extract editable text from photos, screenshots and scans on your device — 26 languages, no upload. Free, no sign-up, and your files never leave your device.

Free, with no sign-up and no watermark. The file is processed in your browser and never uploaded.

Pull editable text out of photos, screenshots, scanned pages and receipts. Recognition (OCR) runs on your device with the open-source Tesseract engine, so even private documents never leave your computer or phone.

It reads 26 languages, including Hindi, Bengali, Tamil, Telugu, Marathi, Gujarati, Kannada, Malayalam, Punjabi, Urdu, Arabic, Chinese, Japanese and Korean, and you can combine up to three when an image mixes them. You can drop several images at once, or simply paste a screenshot with Ctrl+V (⌘V on a Mac).

Step by step

Add images: Drop or choose JPG, PNG, WebP, HEIC or TIFF files, click Paste from clipboard, or press Ctrl+V / ⌘V anywhere on the page to add a screenshot.
Pick the language: English is selected; use + Add language for every other language in the image (up to three).
Choose the layout: Tick Join lines into paragraphs for book pages and articles; leave it off to keep the original line breaks (best for receipts, lists and code).
Extract: Click Extract Text. The first run for a language downloads its data (≈2–15 MB) once.
Copy or save: Edit the result if needed, then use Copy text / Copy all text or Download .txt.

Handy for

Screenshots

Copy text from a screenshot of a chat, error message or web page that won’t let you select it.

Printed documents

Turn a photo of a letter, notice or book page into editable text.

Receipts and bills

Grab amounts and item names for expense reports.

Indian languages

Extract Hindi, Marathi, Tamil and other scripts — no typing needed.

Good to know

Shoot straight on, in good light, with the text filling most of the frame — sharp, high-contrast images give the best accuracy.
Small screenshots are enlarged automatically before recognition, which noticeably improves accuracy.
Only add languages that are really in the image — extra languages slow recognition and can add mistakes.
Need a searchable PDF instead of plain text? Use Searchable PDF (OCR).

Questions

How accurate is it?

Clean printed text is usually recognised almost perfectly. Each result shows a confidence score; low scores mean the image was blurry, skewed or low contrast — check those results before using them.

Does it read handwriting?

Not reliably. Tesseract is built for printed text. For handwritten notes, try Handwriting to PDF, which uses a handwriting model (English).

Can I paste a screenshot directly?

Yes — copy a screenshot (for example with the Snipping Tool, or Cmd+Ctrl+Shift+4 on a Mac) and press Ctrl+V / ⌘V on this page, or click Paste from clipboard.

Are my files uploaded?

No. Everything runs in your browser on your own device — nothing is sent to a server. Once a page has loaded it keeps working offline, except that text recognition downloads its language data the first time you use it.