Convert image to text
Extract text from photos, screenshots and scans. JPG, PNG and WebP are supported.
Result
Your Markdown or JSON shows up here.
3 free pages a day, no sign-up.
How it works
- Step 1Upload or paste an image
- Step 2We read the text in it
- Step 3Copy the result
Why use this Image to text converter
Photos, screenshots and scans
Anything with text in it: a whiteboard photo, a screenshot of an error, a scanned letter.
100+ languages
Chinese, Japanese, Korean, Arabic, Hindi and most Latin and Cyrillic scripts, without choosing the language first.
Keeps structure
Tables and lists in the image come back as Markdown tables and lists, not one long line.
What people use it for
- Copying text out of a screenshot or a photo of a slide
- Digitising printed letters, receipts and forms
- Reading text in another script so you can translate it
- Extracting text from product photos and labels
Models that do this well
The free tool picks one for you. With the API you choose, and can set fallbacks so a failed page is retried on the next model.
1Gemini FlashGeneral vision model with strong handwriting and layout understanding at a low price.
google/gemini-flash3 credits / page2Mistral OCRFast document OCR that returns clean Markdown with tables and embedded images.mistral/mistral-ocr6 credits / page3PaddleOCR-VLOpen-source document model from Baidu. Excellent on Chinese, Japanese and Korean.paddle/paddleocr-vl2 credits / page4TesseractThe classic open-source OCR engine. Plain text from clean printed scans.tesseract/tesseractFreeDo it with the API
Converting more than a few files? The same conversion is one request. Pick any model, or let auto choose.
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "auto",
"file_url": "https://example.com/invoice.pdf",
"format": "markdown"
}'