PPTX Text Extractor — PowerPoint to Text, Google Drive, Speaker Notes

Extract text, speaker notes, and slide structure from any PowerPoint (.pptx) file — including Google Drive share links and Dropbox URLs. Batch up to 50 files per run. $0.02 per file + $0.001/slide.

⚡ Run in 30 seconds

Paste any PowerPoint URL and click Start:

# Direct PPTX URL
https://example.com/presentation.pptx

# Google Drive share link (auto-resolved)
https://drive.google.com/file/d/1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs74OgVE2upms/view

# Dropbox share link (auto-resolved)
https://www.dropbox.com/s/abc123/slides.pptx?dl=0

---

Why this exists

PowerPoint is the dominant format for business presentations, research decks, and executive briefings — yet the content is locked inside a binary format that LLMs and search engines can't read directly.

This actor extracts every slide's content in clean text format, preserving slide titles, body text, tables, and speaker notes. Feed the output directly into RAG pipelines, vector stores, or LLM prompts.

---

What you get

Summary row (one per file)

{
  "_type": "summary",
  "url": "https://example.com/slides.pptx",
  "ok": true,
  "slide_count": 24,
  "title": "Q4 2026 Business Review",
  "author": "Jane Smith",
  "total_word_count": 3840,
  "total_char_count": 22100,
  "created": "2026-10-01T09:00:00+00:00"
}

Per-slide row (one per slide)

{
  "_type": "slide",
  "url": "https://example.com/slides.pptx",
  "slide": 3,
  "title": "Revenue Breakdown",
  "text": "Revenue Breakdown\nQ4 2026 vs Q3 2026\nProduct A | $4.2M | +12%\nProduct B | $1.8M | -3%",
  "word_count": 18,
  "char_count": 89,
  "notes": "Highlight the product A growth — driven by EMEA expansion.",
  "shape_count": 5
}

---

Use cases

1. RAG pipelines — Index presentation content in a vector database for semantic search
2. LLM summarization — Feed slide text directly to Claude/GPT for meeting prep summaries
3. Content auditing — Batch-extract text from a library of company presentations
4. Search indexing — Make presentation decks searchable in internal knowledge bases
5. Translation — Extract text, translate, then reconstruct (with another tool)
6. Compliance review — Scan slides for sensitive content, keywords, or policy violations

---

Input

Parameter	Type	Default	Description
urls	array	—	List of .pptx URLs (direct links, Google Drive, Dropbox). Max 50
includeNotes	boolean	true	Extract speaker notes from each slide
includeSlideRows	boolean	true	Output per-slide rows (plus summary). Set false for summary-only
maxFiles	integer	50	Max files per run (cap at 50)

---

Quick start

Single file

{
  "urls": ["https://example.com/q4-review.pptx"]
}

Batch — summary only (no per-slide rows)

{
  "urls": [
    "https://example.com/deck1.pptx",
    "https://example.com/deck2.pptx"
  ],
  "includeSlideRows": false
}

Google Drive deck without speaker notes

{
  "urls": ["https://drive.google.com/file/d/1abc.../view"],
  "includeNotes": false
}

---

Supported URL formats

Source	Example
Direct .pptx URL	https://example.com/file.pptx
Google Drive	https://drive.google.com/file/d/{id}/view
Google Drive (open)	https://drive.google.com/open?id={id}
Dropbox	https://www.dropbox.com/s/{key}/file.pptx?dl=0

---

Pricing

Pay-Per-Event: $0.02 per file + $0.001 per slide

Files	Avg slides	Cost
1 file	20 slides	$0.04
10 files	20 slides each	$0.40
50 files	20 slides each	$2.00

---

Related actors (same author)

• PDF Text Extractor — PDF → text, tables, Markdown
• DOCX Text Extractor — Word documents
• Excel Extractor — Excel spreadsheets
• Image OCR Extractor — Images to text

---

Feedback

A quick review helps others find it: Leave a review on Apify Store