Video Understanding — transcript, on-screen text, hook & summary from any short-form video

🎁 Free trial until Nov 20, 2026: your first 5 videos are free (no charge for analysis or translation). After that, $0.01 per video.

Paste a TikTok, Instagram Reel, YouTube Short (or 1,000+ other sites) link and get everything that is in the video as clean JSON — not just the speech.

You get	Details
🗣️ Speech transcript	Timestamped segments, 99 languages auto-detected (works on videos without captions)
🔤 On-screen text (OCR)	Text overlays, captions, product names read from frames
🎬 Scene descriptions	One line per sampled frame — what is actually shown
🪝 First-3-second hook	What grabs attention at the start, from the opening frame + first words only
📝 Summary, topics, CTA	3–5 bullet summary, keywords, call-to-action
🌐 Translation (optional)	Transcript translated with timestamps kept (ja, es, de, fr, pt-BR, zh, ko …)

Why this one

• All-in-one. Most actors return only the transcript. Marketers and AI agents need the hook, the text on screen and the visuals too — one run, one row.
• Accurate. Speech model benchmarked at 2.2% word error rate on 1 hour of human-captioned talks.
• Cheap. You only pay for videos that were analyzed successfully. Failed or private videos are free.
• Fast. A 60-second TikTok takes about 30–45 seconds end to end.

Input

{ "videoUrls": ["https://www.tiktok.com/@user/video/123"], "translateTo": "ja", "frames": 6 }

Output (one item per video)

{
  "source": "https://www.tiktok.com/@cookingwithkatiecross/video/7490716178357243182",
  "status": "ok",
  "language": "en",
  "duration": 61.4,
  "hook": "A hand holds a plate of Mexican cheesy chicken and rice while queso is poured over it; overlay text 'Mexican Cheesy Chicken & Rice'; speaker: 'Tonight for supper we're making…'",
  "summary": ["…"], "topics": ["…"], "call_to_action": "",
  "transcript": [{"start": 0.0, "end": 4.9, "text": "Tonight for supper we're making…"}],
  "frames": [{"t": 0.5, "on_screen_text": "Mexican Cheesy Chicken & Rice", "scene": "…"}],
  "translation": {"lang": "ja", "text": "[0s] 今夜の夕食は…"}
}

Use cases

• Competitor & trend research: why do top videos in a niche work? (hooks, on-screen text, CTAs)
• Content repurposing: video → blog post / caption / script
• Feeding AI agents and RAG pipelines with what is said and shown in videos
• Localization: translated, timestamped transcripts

Notes

• Public videos only. Max 20 minutes per video.
• Works great with the Apify MCP server, so Claude / ChatGPT agents can call it directly.

More tools from Brain Spice

• Video Transcript + On-screen Text + Hook & Summary AI — TikTok / Reels / Shorts breakdown, $0.01 per video
• Podcast & Audio Transcript with Speakers, Chapters, SRT — who said what + chapters, $0.008 per minute
• YouTube Comments AI Analyzer — sentiment, viewer questions, content ideas, $1 per 1,000 comments

Use it from code, n8n, Make or an AI agent

API (one call, waits for the result):

curl -X POST "https://api.apify.com/v2/acts/vidlens~video-understanding/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"videoUrls": ["https://www.tiktok.com/@user/video/123"]}'

Python:

from apify_client import ApifyClient
client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("vidlens/video-understanding").call(run_input={"videoUrls": ["https://www.tiktok.com/@user/video/123"]})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item)

• n8n: use the Apify node → "Run actor and get dataset", actor vidlens/video-understanding.
• Make / Zapier: use the Apify app → "Run an Actor", then "Get dataset items".
• AI agents (Claude, ChatGPT, Cursor): available through the Apify MCP server (https://mcp.apify.com) — add vidlens/video-understanding as a tool.