What you get

  • A 1920x1080, 30 fps MP4 of 24 to 40 seconds with narration
  • A plan-driven HyperFrames composition for all seven beats
  • A verb-align script that times captions and verbs to the read
  • A permission gate and checks for crossfades, colourways and copy
  • Optional PopNow voice, music bed, typing sounds and b-roll

Good for

  • Integration launches where both companies signed off
  • Joint announcements with a short, real setup to show
  • Founder or product lead videos for a partner launch

Not for

  • One-sided compatibility claims or logo walls
  • Announcements the partner has not approved in writing
  • Films without a real presenter or recorded narration plan

How to use it

In Claude or ChatGPT

Use the PopNow skill "Partnership Announcement Video" (partnership-announcement-video) for this: We and Harbor Sync are announcing that our notes app now works inside their file manager. Narration is in ./narration.wav, presenter clip in ./presenter.mp4, permission email from their CMO attached.

In a coding agent

/popnow-partnership-announcement-video We and Harbor Sync are announcing that our notes app now works inside their file manager. Narration is in ./narration.wav, presenter clip in ./presenter.mp4, permission email from their CMO attached.

Then try

We have no recorded voice yet; quote a narration and tell me how you will disclose it.

Make the lite version with two setup steps.

What to have ready

  • Written permission from the partner and the presenter
  • Your narration, or approval for a disclosed synthetic voice
  • Both logo files and three real, tested setup commands
  • Node.js 22+ and FFmpeg

Similar skills

View all →

Questions

Can I use a partner's logo without asking?

No. The plan records who at the partner gave written permission for this film and when, and the check script blocks the final render until that and the presenter's consent are filled in.

How do the rolling verbs line up with the voice?

You lock the narration, transcribe it, and verb-align takes each verb's start from the transcript, snaps it to a frame and limits each roll to a third of the gap to the next verb.

Why is there no narration during the setup steps?

The walkthrough is the one part viewers read instead of hear. The music comes up there instead, and the check fails if a caption runs over it.

What does PopNow add?

A disclosed synthetic narration when there is no recording, a music bed, typing and click sounds, and faceless b-roll for the window if there is no presenter. It never generates a person.