> ## Documentation Index
> Fetch the complete documentation index at: https://docs.dumplingai.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Document Processing

> Convert, merge, read, and extract data from documents and media files.

# Document Processing

Use DumplingAI to work with PDFs, documents, images, audio, and video files without building separate conversion and extraction pipelines.

## What it does

* Convert documents to PDF
* Merge PDFs and manage PDF metadata
* Extract text from files
* Extract structured data from documents, images, audio, and video
* Trim video before downstream processing

## Common use cases

* Turn uploaded files into AI-ready text
* Pull fields from invoices, forms, or reports
* Process media files before summarization
* Standardize file handling inside internal tools

## Why use it

You can handle multiple file types through one API instead of combining separate OCR, conversion, transcription, and media utilities.

## Related endpoints

<CardGroup cols={2}>
  <Card title="Doc to Text" icon="file-lines" href="/api-reference/endpoint/doc-to-text">
    Extract readable text from documents
  </Card>

  <Card title="Convert to PDF" icon="file-lines" href="/api-reference/endpoint/convert-to-pdf">
    Convert supported files into PDF format
  </Card>

  <Card title="Extract Document" icon="file-lines" href="/api-reference/endpoint/extract-document">
    Pull structured data from documents with AI
  </Card>

  <Card title="Extract Video" icon="video" href="/api-reference/endpoint/extract-video">
    Analyze and extract data from video files
  </Card>
</CardGroup>