Video to PDF · Apify actor
Get the slides out of any lecture or webinar video
Nobody sent you the deck? Give this tool the recording and get back every unique slide as an image, with its start and end time, the text on it (OCR in 8 language groups) and one PDF of all slides. Slides that build up line by line are merged into their final version, and the speaker shots in between are skipped. No API key, no browser extension, no screenshots by hand.
What it does
Video to Slides, in short
- Finds each slide change and keeps one image per unique slide, with its start and end timestamp
- Merges slides that build up bullet by bullet into their most complete version
- Reads the text on every slide (OCR: English, Chinese, Japanese, Korean, Cyrillic, Arabic, Devanagari, Greek, Thai and accented Latin)
- One PDF of all slides, one overview contact sheet and an
allTextfield with every slide's text, ready for notes or an AI model - Optional crop for slides that share the frame with a speaker camera or burned-in subtitles
- Direct video file links only; video platform pages are refused on purpose
Who it's for
Built for
Example
Input and output
One dataset row per result, downloadable as JSON, CSV or Excel, or read through the Apify API.
{
"videoUrls": ["https://example.com/recordings/lecture-03.mp4"],
"sensitivity": "medium",
"ocr": true,
"ocrLanguage": "en",
"outputPdf": true
}One slide row from a real cloud run on a recorded conference talk, shortened. Each video also gets a summary row with pdfUrl, contactSheetUrl and allText.
{
"type": "slide",
"fileName": "lecture-03.mp4",
"slideIndex": 5,
"startSeconds": 146.25,
"endSeconds": 213.75,
"timecode": "00:02:26.250",
"durationSeconds": 67.5,
"imageUrl": "https://api.apify.com/v2/key-value-stores/.../records/...-slide-005.jpg",
"width": 1920,
"height": 1080,
"text": "Uncitedness (publications):\n12% - 82% (Lariviere & Gingras 2009)",
"ocrConfidence": 0.9749
}Pricing
Pay per result. Failures are free.
No subscription, no monthly minimum. Apify platform compute is included in the price; Apify also adds a tiny start fee per run ($0.00005 per GB of run memory).
| You run | You pay |
|---|---|
| A 10-minute webinar, 15 slides | $0.07 |
| A 60-minute lecture, 40 slides | $0.22 |
| A 5-minute screen recording, 10 screens | $0.045 |
1 failed download = $0.00
Not charged:
- The PDF, the contact sheet, the summary row and the allText field
- Refused links, failed downloads, unreadable files and audio-only files
Slides are charged once each, after duplicates and speaker shots are removed. Video minutes are charged per started minute of video scanned. You can set Maximum cost per run in the run options and the actor stops cleanly when it is reached.
FAQ
Questions
Can I get a PDF of the slides from a video?
Yes. Every video gets one PDF with one slide per page, linked in the summary row as pdfUrl.
Does it work when the speaker is on screen too?
Yes. Speaker-only shots are skipped. When the slide shares the frame with a large webcam, set the slide area crop for cleaner results.
Which languages can it read?
English, Chinese, Japanese, Korean, Cyrillic, Arabic, Devanagari, Greek, Thai and accented Latin languages. Pick the slide language in the input.
Can I use YouTube links?
No. Video platforms forbid downloading in their terms, so the actor refuses them (free row). Use the original recording file.
What are the limits?
A slide shown again later at a different zoom appears twice, and full-screen photos count as slides.
Try Video to Slides on Apify
Apify's free plan includes monthly platform credit you can use to try it. Also callable from AI assistants through the Kanto Labs MCP server.
Other Kanto Labs tools
Video Frame Extractor
Scene-change keyframes, thumbnails or one frame every N seconds, plus a contact sheet.
Video to LLM Context
Scenes, one keyframe per scene and the transcript per scene, as a ready-to-paste prompt block.
Video OCR
Burned-in subtitles, captions, hook text and lower-thirds as timed text, a transcript and SRT/VTT.