YouTube Video Analyzer — ask AI anything about a video

Gemini AI watches the full video — audio and visuals — and answers any question you ask about it, citing timestamps. Extract every product mentioned, audit claims, describe what happens on screen, check brand appearances, pull quotes, verify compliance — one prompt, one answer.

What it does

• ✅ Any custom prompt — the AI watches the whole video before answering
• ✅ Sees visuals, not just speech: on-screen text, products shown, scenes, slides
• ✅ MM:SS timestamps in answers so you can jump to the moment
• ✅ Optional structured JSON output for pipelines and agents
• ✅ Works on videos without captions, any language, up to 150 minutes
• ✅ No API key needed — or bring your own Gemini key and pay 5× less

Example prompts

• "List every product, brand, or tool mentioned or shown, with timestamps and what is said about it."
• "Does this video make any health or financial claims? Quote each with its timestamp."
• "Describe every scene change and what is shown on screen."
• "Extract all statistics and numbers cited, with sources if given."
• "Is my brand X visible or mentioned anywhere in this video?"

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 an answer 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)
prompt	string (required)	Your question or task about the video
jsonOutput	boolean	Answer as machine-readable JSON (default false)
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": 754,
  "minutesCharged": 13,
  "prompt": "List every product mentioned…",
  "answer": "1. **Acme Widget** (02:14) — the host calls it…",
  "answerJson": null,
  "answerUrl": "https://api.apify.com/v2/key-value-stores/…/records/answer-….md",
  "status": "completed"
}

Use it via API

curl -X POST "https://api.apify.com/v2/acts/andok~youtube-video-analyzer/run-sync-get-dataset-items?token=$APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"videoUrl": "https://www.youtube.com/watch?v=…", "prompt": "Summarize every claim made about pricing."}'

FAQ

How is this different from transcript Q&A tools? Those only see caption text. This actor has Gemini watch the actual video — it catches products shown silently, on-screen text, demos, and scenes no transcript contains.

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 answer.