Docs & Files

Read, merge, split, fill and create PDF files, including OCR for scanned pages

Create, edit and extract text from PowerPoint .pptx files with speaker notes

Read, edit, format and chart .xlsx and .csv spreadsheets and clean messy data

Process PDFs and Office files with Nutrient API for OCR, redaction and signing

Convert paper formatting between DOCX, LaTeX and Markdown to fit a journal template

Unify fonts and sizes in Word tables and charts across a thesis or report

Summarize track changes and reviewer feedback across DOCX versions as Markdown

Convert HTML files or web pages to PDF with right-to-left support for Hebrew and Arabic

Convert Office files and PDFs to clean Markdown for summaries and RAG ingestion

Extract PDF text and page images with tables into Markdown with per-page headings

Merge, split and extract pages, text and tables from PDFs offline

Create, edit and extract content from PowerPoint files and export slide previews

Write GCP-compliant SOPs with roles, steps and control points for lab or clinical work

Repair garbled text in PDF and SVG files caused by font encoding issues

Create Word documents for reports and letters and read text from existing DOCX files

Create, edit and validate Word DOCX files, including LaTeX to Word conversion

Convert academic PDFs to Markdown while keeping equations and structure

Read and edit PDF documents page by page with the PyMuPDF library

Read Excel workbooks with multiple sheets, merged cells and messy headers

Merge, split, extract text from and convert local PDFs on the command line

Draft Word documents with formatting, templates, tables of contents and batch edits

Merge saved diagnosis snapshots into one shareable markdown report

Extract text and tables from Word and Excel files with local scripts

Condense text, conversations and documents into their key points

Convert DOCX, PDF and PPTX files to clean Markdown with table and image fixes

Route Word, PDF, Excel and Markdown document tasks to the right specialist

Generate formatted Word documents with tables, images and a verified layout

Build formatted Excel reports and parse macro-enabled financial models

Export Feishu or Lark docs, wikis and minutes transcripts to faithful Markdown

Repair hard-wrapped tables, paths and tool output in exported conversation text files

Convert Markdown into print-ready PDFs with clean themes and CJK typography

Turn a PDF into one self-contained HTML page with images, tables and reading order

Turn phone photos of paper documents into clean, scanner-style PDF files

Extract Word comments and tracked changes into a reviewable reconciliation table

Archive public WPS and KDocs pages, including mind maps, as SVG, PNG and Markdown

Read local or workspace PDFs and return a structured summary of their content

Pull tables and fields out of PDFs, Office files and scans with cited answers

Create and edit Excel workbooks with formulas that show computed values in any viewer

Read, write and filter Feishu spreadsheets and Bitable tables from the command line

Read, summarize, create and edit Feishu cloud docs, wikis and Markdown exports

Upload, download and share Feishu Drive files and manage wiki spaces and permissions

Add an image watermark such as a logo to PDF pages

Add a text mark to PDF pages with a simple interface

Add text watermarks to PDFs with custom font, size, color and position

Add watermarks to a PDF through an interactive prompt

Add watermarks to PDFs in bulk from command-line parameters

Remove the password protection from encrypted PDF files

Delete specific pages from a PDF and save the trimmed file

Convert old .doc Word files to the newer .docx format