YouTube AI Summarizer — watches the whole video

Gemini AI watches the full video — audio and visuals — and delivers a clean summary, the key takeaways, and timestamped key moments. Not a caption rehash: it works on videos with no captions, in any language, and it sees what's on screen (slides, demos, charts, on-screen text).

What it does

• ✅ Summary in your chosen style (bullets / paragraphs / detailed notes with headings) and length
• ✅ Key points — the takeaways, one sentence each
• ✅ Key moments — notable timestamps you can jump to
• ✅ Works on videos without captions, any spoken language
• ✅ Optional output language (summarize a Japanese video in English)
• ✅ Downloadable markdown file for notes apps
• ✅ No API key needed — or bring your own Gemini key and pay 5× less

Pricing

Charged per minute of video (minimum 5 minutes per video), plus a $0.02 actor start fee.

Video length	No API key (bundled)	With your Gemini key
Short (≤5 min)	$0.75	$0.15
10 min	$1.50	$0.30
30 min	$4.50	$0.90
60 min	$9.00	$1.80

Bring your own key and save 5×: create a free key at aistudio.google.com/apikey and paste it into the geminiApiKey field (stored encrypted, used only for your run). Google token costs (a few cents per hour of video) are then billed to your Google account.

You are only charged when a summary is actually delivered — failed or timed-out runs charge nothing beyond the start fee.

Input

Field	Type	Description
videoUrl	string (required)	Public YouTube video URL (watch, youtu.be, or Shorts link)
style	string	bullets (default), paragraph, or detailed-notes
summaryLength	string	short, medium (default), or long
outputLanguage	string	Optional — e.g. "English"; defaults to the video's language
includeKeyMoments	boolean	Timestamped notable moments (default true)
model	string	gemini-3.7-flash (default) or gemini-3.5-flash-lite
geminiApiKey	secret string	Optional — your Google AI Studio key for 5× cheaper runs

Output

One dataset item per run:

{
  "videoUrl": "https://www.youtube.com/watch?v=…",
  "videoTitle": "…",
  "durationSeconds": 1260,
  "minutesCharged": 21,
  "summary": "- The talk introduces …",
  "keyPoints": ["…", "…"],
  "keyMoments": [
    { "timestamp": "03:12", "description": "Live demo of the new feature" }
  ],
  "markdownUrl": "https://api.apify.com/v2/key-value-stores/…/records/summary-….md",
  "status": "completed"
}

Use it via API

curl -X POST "https://api.apify.com/v2/acts/andok~youtube-ai-summarizer/run-sync-get-dataset-items?token=$APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"videoUrl": "https://www.youtube.com/watch?v=…", "summaryLength": "long"}'

FAQ

How is this different from transcript-based summarizers? Those summarize captions — they miss anything visual and fail when captions don't exist. This actor has Gemini watch the actual video: it sees the slides, demos, and on-screen text, and hears the audio directly.

What videos are supported? Public, finished YouTube videos up to 120 minutes (150 minutes with your own key). Private, unlisted, and live videos are not supported.

What if the run fails? You are never charged per-minute fees for a failed or undelivered summary.