Verified against Gemini · 2026-05-20
Turn an uploaded video into timestamped notes and action items
A native multimodal prompt for Gemini's video understanding that returns timestamped highlights, decisions, and action items instead of a flat transcript of everything said.
The prompt
Ready to copy — highlighted parts are example details you can swap.
Watch the video I've uploaded above. This is a 40-minute recording of our Q3 planning meeting, roughly 40 minutes. Don't just transcribe it — extract the structure. OUTPUT 1. A timestamped list of the 10 most important moments (format: [mm:ss] — what happens/what's said), covering: budget decisions, headcount discussion, and anything about the Q4 launch date 2. Every decision made or commitment stated on camera, with the timestamp and who said it, if identifiable. 3. Every action item mentioned, with an owner (if named) and any deadline mentioned. 4. Anything said that contradicts something said earlier in the same video — with both timestamps. 5. If the audio is unclear or a section is inaudible, mark it as [unclear ~mm:ss] rather than guessing at words. Skip filler, small talk, and restated points — only budget decisions, headcount discussion, and anything about the Q4 launch date matters for this pass.
Customize the highlighted detailsoptional — the prompt above already works
Why this works
Gemini processes uploaded video as sampled frames plus audio together, not audio-only through a separate speech-to-text pass, so it can anchor output to visual timestamps and reference what's shown on screen, not just what's said. Asking for structure instead of a transcript matters because a flat transcript of a 40-minute meeting is barely more useful than the video itself — naming focus_areas up front stops the model from treating every restated point as equally important. The [unclear ~mm:ss] instruction directly targets a real failure mode: video with noisy audio or overlapping speakers gets transcribed with confident-sounding words that were never actually said, and marking those spans instead of guessing keeps the notes trustworthy enough to act on.
What you get back
[04:12] — Priya proposes moving the Q4 launch from Nov 3 to Nov 17; no objection recorded. [11:40] — Decision: engineering headcount request tabled until next planning cycle (stated by Marcus). [unclear ~22:15] — cross-talk, can't confirm who raised the budget concern. Action items: Priya to send revised launch timeline by Friday (no year stated — assumed current). Contradiction: at [04:12] the launch date moves to Nov 17, but at [31:02] someone references "the Nov 3 launch" — flagging for clarification.
Verified against
Gemini Gemini 3 Pro · 2026-05-20
Changelog
- 2026-05-20 — Initial publish, verified against Gemini 3 Pro on a 40-minute meeting recording.
Need this built into your business?
If a prompt isn't enough — what Scult builds, built and maintained for you — that's Scult's day job.
EXPLORE WHAT SCULT BUILDS
