AI Video Editing Flows

Reel teardown #25: an AI myth reel in a letterboxed strip, with a narrator and a closing question

We took apart one Instagram reel by @mavriwka, an AI myth reel in a letterboxed strip, with a narrator and a closing question. It had 1,991,623 plays on 5 Nov 2026, 3.7x its page's median. Length, cuts, pace and loudness were measured by script, and the frames were read one by one.

The reel in numbers

The reel we took apart. Posted Oct 2, 2026 Open on Instagram (opens in a new tab)

Reel by @mavriwka on Instagram. Watch the original reel. We link to it and do not copy it.

Posted on 2 Oct 2026. Plays and followers as shown on Instagram on 5 Nov 2026.

MeasureValueWhat it means
Length78.6 sLength of the file we measured.
Plays when measured on 5 Nov 20261,991,623Plays as shown on Instagram that day. They include replays.
The page's median plays over its last ~10 reels541,642Plays of a typical recent reel on this page.
This reel against that median3.7xThis reel's plays divided by the page median.
Followers107,771Followers of the page on 5 Nov 2026.
Hard cuts per minute0.0Hard cuts counted by script. Fast dissolves are not counted. The script found one shot because only the letterboxed strip changes. It is not a one-take film, so the cuts-per-minute figure understates the editing inside the strip.
Median shot length78.57 sMedian time between hard cuts.
First hard cut atNo hard cut foundTime of the first hard cut the script found.
Hard cuts in the first 3 s0Hard cuts found before the 3 s mark.
Big visual changes per minute0.0Hard cuts plus large camera travel or scene changes.
Integrated loudness-14.1 LUFSIntegrated loudness of the audio track, in LUFS.
Speech2.58 words per second, language guess: EnglishWords per second and a language guess from a speech-to-text pass.

The first three seconds

What we saw frame by frame: Frame 0: ultra-wide 2.39:1 letterboxed strip in the middle of a black 9:16 frame; Greek hall with columns, laurel garlands, gold braziers, gods mingle; slow camera drift.

By script, there is no hard cut in this reel and 0 big visual changes in the first 3 s.

Frame 0 is a wide cinematic strip in the middle of a black vertical frame: a Greek hall with columns, laurel garlands and gold braziers, with a slow camera drift.

Captions and on-screen text

What we saw frame by frame: none.

The notes record no on-screen text. The narrator carries the story.

Shots and pace

What we saw frame by frame: Detector sees story beats change by cuts the detector misses; slow camera moves.

By script: 1 shot, 0.0 hard cuts a minute, a median shot of 78.57 s, and 0.0 big visual changes a minute.

The script found one shot because only the letterboxed strip changes, so it misses cuts inside the strip. It is not a one-take film: the notes say the story beats change by cuts the detector misses. Read the cuts-per-minute figure with that in mind.

Sound

What we saw frame by frame: Music: Enya 'Boadicea (2009 Remaster)'; English narrator.

Measured loudness: -14.1 LUFS. Speech: 2.58 words per second, language guess: English.

A music track under an English narrator. The notes name the track; we do not repeat it.

Structure and ending

  • Structure: Hook: everyone but you invited then they excluded Eris then golden apple thrown then Trojan War setup then question to viewer.
  • Ending: Ends with question 'was Eris responsible?'; caption made with Higgsfield.

The hook is that everyone but you was invited, then Eris is excluded, a golden apple is thrown, the Trojan War is set up, and a question goes to the viewer. The reel ends on that question.

Effects we have for this

There is no on-screen text in this reel, so nothing on our effect list applies. Browse all our effects for the nearest options.

Method and limits

  • Length, size and frame rate: read from the file.
  • Hard cuts, shot length and first cut: a script that finds hard cuts between frames. Fast dissolves are missed.
  • Big visual changes: hard cuts plus large camera travel or scene changes.
  • Loudness: integrated loudness of the audio track in LUFS. It is blank when the file had no audio track.
  • Speech: words per second and a language guess from a speech-to-text pass.
  • Plays, followers and the page median: collected by Apify on 5 Nov 2026.
  • What we saw frame by frame: a model read a contact sheet of the reel. Treat these as observations, not measurements.
  • Hard-cut counts miss dissolves, so a reel built on dissolves can show close to zero hard cuts.
  • The big visual change count also counts camera travel and scene changes, so it is not the same as the cut count. We show both.
  • Some full-HD files had no audio track, so loudness and speech are blank for those reels.
  • Plays include replays. Shares and follower conversion cannot be seen from outside.
  • Ten reels from one page are not ten independent tests.
  • Hashtag discovery favours pages that already had a hit, so breakout pages are over-represented.
  • Plays per follower favours small, newer pages; it measures reach health, not size.
  • Formats measured on only one to three pages are hypotheses.
  • No number here is a promise about what a new reel will do.

Plays and followers as shown on Instagram on 5 Nov 2026. We link to the reel and do not copy or embed it.

Page checked on Nov 4, 2026.