OCR — PDF & Image to Text
Extract text from PDFs and images using AI-powered OCR. Supports scanned documents, photos of text, and native PDFs. Outputs Markdown, plain text, or HTML with preserved formatting.
Drop files here or click to browse
Max 10240.0 MB per file · drop multiple for batch
Processed on our servers — requires a free account
Have feedback? Let us know
How to Use OCR — PDF & Image to Text
- Upload a PDF or image file containing text
- Choose your output format — Markdown, Plain Text, or HTML
- Click Process to extract text with AI OCR
- Download the extracted text file
Features
- AI-powered OCR using Marker — state-of-the-art document understanding
- Supports scanned PDFs, photos of text, native PDFs, and images
- Preserves tables, headings, lists, and document structure
- Output as Markdown, plain text, or HTML
- 90+ languages supported with auto-detection
Frequently Asked Questions
- What types of documents can I OCR?
- Scanned PDFs, photos of documents, screenshots, native PDFs, and images (JPG, PNG, WebP, TIFF, BMP). The AI handles handwriting, tables, equations, and complex layouts.
- Does it preserve formatting?
- Yes. Markdown output preserves headings, tables, lists, bold/italic text, and document structure. Plain text strips all formatting. HTML gives you web-ready formatted output.
- What languages are supported?
- Over 90 languages including English, Spanish, French, German, Chinese, Japanese, Korean, Arabic, Hindi, Russian, and many more. Language is auto-detected.