Presentation extraction

Extract structured data from PowerPoint presentations

Send PowerPoint files and extract slide content, titles, bullet points, and embedded tables. The API understands slide structure and can pull data from specific slides or the entire deck.

How it works

1

Send your PPTX file

Upload via the API or pass a URL. The API auto-detects the format.

2

Define your schema

Describe the fields you want as a JSON schema. The API maps your document to your structure.

3

Get structured JSON

Receive typed data with confidence scores and citations back to the source document.

Example request

curl -X POST https://dev.thedrive.ai/api/v1/extract \
  -H "X-API-Key: your_key" \
  -F "file=@document.pptx" \
  -F 'schema={"title": "string", "slide_count": "number", "key_points": ["string"]}'

PPTX processing features

Slide-by-slide parsing

Each slide is parsed individually with titles, body text, and embedded content.

Table and chart extraction

Tables and chart data embedded in slides are extracted with structure preserved.

Speaker notes

Access speaker notes alongside slide content for complete context.

Start extracting from PPTX files

Free tier includes 100 credits/month. No credit card required.