“Documentation”

Extracts text and structure from documents using the MinerU document extraction toolkit.

Opens and edits Word, Excel and PowerPoint files and annotates PDFs in the browser, with processing done locally.

Summarizes a pasted or uploaded document and lets you download the summary as text.

Finds and redacts personal data in PDFs, images, Word files and spreadsheets using OCR and entity detection.

Parse digital and photographed documents into Markdown.

Convert PDFs and other documents to Markdown using the Docling library.

Playground for an API that recognizes and reads ID documents from an uploaded image.

Reading view named for semantic zoom, with Claude assistance, for working through a document at varying levels of detail.

Detect text blocks, tables, figures and other layout regions on document page images.

Try Pandoc to convert between Markdown, HTML, LaTeX, Word and many other document formats.

Archive of Sanskrit texts and documents in several scripts.

Italian-language tool: load an accounting document, ask questions or generate reports on IFRS statements with your own Anthropic key.

Small office suite where the whole document is stored inside the shareable link.

Convert document page images to structured text with IBM's compact Granite-Docling model.

Converts a document page image into structured Docling markup using a 258M model run in the browser.

Turns an uploaded document image into structured Markdown using a vision model.

Convert page images into structured document markup with a small vision-language model.

Searchable viewer that combines documentation for many languages and frameworks, with offline support.

Convert documents to Markdown or JSON with metadata using Docling.

In-browser Markdown editor with live preview and publishing to blogs and cloud drives.

Reads text and layout from document images with the dots.ocr model.

Browser word processor that opens and saves docx and odt files with no account and local processing.

Extract text from complex documents and images with a multimodal OCR model.

Detects the layout of a document page with the DocLayout-YOLO model.