ModaTransform

Moda Transform Document APIs Early beta

Convert, parse, and index any document

Turn any PDF or scanned document into editable DOCX and PPTX, into text, tables, and structure, or into a searchable archive that Claude can answer questions from, with citations.

Contact us View docs
ONE SCANNED PAGE, THREE OPERATIONS

Parse

Read a document into its full data representation, including text, tables, and structure.

One document → full data representation

Extract

Specify the data you need and extract it from one or more documents, such as invoice totals across a set of files.

One or more documents → selected data

Index

Digitize scans and image-only PDFs, then index them so every page is searchable. Queries return matching documents with the page and position of each hit.

Scanned archive → searchable, machine-readable text

Convert

Turn a PDF, HTML page, or raster image into a native, editable file. PowerPoint output includes charts, slide masters, text, and shapes; raster documents can be separated into text, image, and shape layers.

One source file → native, editable output

Generate

Submit a JSON or XML document description and receive a PDF, PPTX, or DOCX file.

Document description → generated file

Embed

Add a DOCX editor, PDF editor, PPTX editor, or 2D vector canvas to your application. Each editor is React-compatible.

  • DOCX editor
  • PDF editor
  • PPTX editor
  • 2D vector canvas
An editor inside your application

More operations

Single-purpose operations that run on the same documents and the same job API.

  • Anonymize

    Find names, addresses, account numbers, and other personal data, and replace them with placeholders.

  • Redact

    Permanently remove selected regions and their underlying text, not just cover them with a box.

  • Classify

    Sort a batch of mixed files into your own document types, such as invoice, contract, or statement.

  • Split

    Break a file into separate documents by page range, by bookmark, or at detected document boundaries.

  • Merge

    Combine several files into one document, keeping bookmarks, page numbering, and outlines intact.

  • Compare

    Diff two versions of a document and return the text, table, and layout changes between them.

  • Translate

    Translate a document into another language and rebuild it with its original layout and styling.

  • Fill

    Populate form fields in a PDF or DOCX template from a JSON payload and return the completed file.

  • Thumbnail

    Render page previews at any size for list views, search results, and file pickers.

Early beta

Request API access

Contact us for beta access, supported formats, and pricing.

Contact us