APIs, MCP servers and models to extract text with OCR
12 tools in the catalog do this, by name.
Amazon TextractAPIAWS API that reads text, forms, tables and invoices from scanned documents
Azure Document IntelligenceAPIAzure API for OCR, layout and prebuilt invoice, receipt and ID extraction
DoclingPackageOpen-source Python library that parses PDFs, Office files and images
Google Cloud VisionAPIGoogle Cloud API for image labels, OCR, faces, logos and SafeSearch
Google Document AIAPIGoogle Cloud API for OCR, form parsing and invoice data extraction
LlamaParseAPIDocument parsing API from LlamaIndex that turns PDFs and scans into markdown
Mistral OCRModelOCR model API that turns PDFs, Office files and images into markdown
OCRmyPDFPackageSelf-hosted CLI that adds a searchable OCR text layer to scanned PDFs- PaddleOCRPackageOpen-source OCR toolkit you self-host, with formula-to-LaTeX and PDF parsing
ReductoAPIDocument parsing and extraction API that turns complex files into LLM-ready JSON
Tesseract OCRPackageOpen-source OCR engine you self-host that reads 100+ languages from images
UnstructuredAPIDocument parsing API and open-source library that turn files into LLM-ready data
More in Documents & files
- Parse documents10 tools
- Extract data from invoices and receipts3 tools
- Generate PDFs4 tools
- Convert file formats3 tools
- Collect e-signatures3 tools
- Read QR codes and barcodes5 tools
- Generate QR codes3 tools
- Format citations1 tool
- Recognize math formulas in images2 tools
- Scan documents with a phone camera2 tools
- Add a rich text or email editor to an app4 tools
- Print labels and receipts2 tools