Image to Text (OCR)
Extract text from screenshots, scans, or photos in 10+ languages. Runs entirely in your browser using Tesseract.
Copying text out of a screenshot, scanned page, or photo of a whiteboard usually means retyping it by hand. This tool runs Tesseract - the open-source OCR engine, compiled to WebAssembly - directly in your browser to recognize printed text in your chosen language and return it as selectable, copyable text. It works well on clean printed text in 10+ languages; for scanned multi-page PDFs that need a searchable output file rather than plain text, use OCR PDF Pro instead.
Loading tool
How it works
- 01
Drop or select the image containing text (screenshot, scan, or photo).
- 02
Choose the language that matches the text.
- 03
Click Extract Text and copy the recognized result.
Details
- Category
- AI
- Runs
- In your browser
- Files uploaded
- No
- Cost per run
- Free
- Sign-in
- Not required
- Works offline
- Yes, once loaded
Last updated 2026-08-03
Common questions
Is my image uploaded?
No. The OCR model is downloaded to your browser and runs on your device.
First run is slow?
The language model (~10 MB) downloads once and gets cached.
Handwriting?
Tesseract works best with printed text. Handwriting accuracy is limited.
Which languages are supported?
10+, including English, Spanish, French, German, Chinese, Japanese, Korean, and Arabic. Pick the one matching your image before extracting.
Can it read text from a multi-page scanned PDF?
Not directly - this tool takes a single image. For a searchable, selectable-text PDF from multiple scanned pages, use OCR PDF Pro instead.