Checklist the per-video bar — engine/sim
80.6/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review thread-minus-the-hype-W31-Thu good|bad)⚠ 6 flag(s) — not yet ship-ready: copy_genericlow_vo_coveragedead_airgeneric_scene · see docs/strategy/VIDEO-CHECKLIST.md
Composition comp · template family · expected output
9:16 Reelrendered1:1 Squarepending16:9 Widepending9:16 4Kpending1:1 4Kpending16:9 4KpendingGIF (SMS)pending
expected output: 1/7 rendered — same matrix the /media preview surfaces for this asset.
Composition layer × scene 5 scenes · 27.4s · comp_id + rendered still + tier + the script
| # | Layer (comp_id · still · tier) | Beat | Timecode | Motion | Logo | Audio | VO / on-screen / caption |
|---|---|---|---|---|---|---|---|
| 1 |  matches intent shared field signature-3d | hook | 0–5.9s | kinetic-build | icon·wireframe | ♪ node_lock | Clone your brand voice from one prompt, they say. Out comes the same beige tone as everyone else. on-screen: "AI clones your voice" |
expected on screen: white ground · icosa hero in the shared Signal Field · Signum leads · mark · kinetic-build · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual markshape icosaground whitetreatment wireframemotion kinetic-buildpower laser-lockinstrument laser-trace→"AI clones your voice" | |||||||
| 2 |  matches intent JsonDiff template | diff | 5.9–12.4s | crossfade-8f | icon·wireframe | ♪ node_lock | What works: paste five things you actually wrote and a list of banned words, then the model mirrors you on-screen: Feed it real examples |
expected on screen: white ground · a JsonDiff panel over a dimmed Signal Field · Signum leads · code · crossfade-8f · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id JsonDiffvisual codeshape icosaground whitetreatment wireframemotion crossfade-8fpower morphinstrument morph→Feed it real examplescurate codeLines, fileName, lines | |||||||
| 3 |  matches intent NumberedList template | teach | 12.4–17.4s | kinetic-build | icon·wireframe | ♪ node_lock | The cost is owning a real voice first. Write five honest posts before you ever clone it. on-screen: The cost: a real sample |
expected on screen: white ground · a NumberedList panel over a dimmed Signal Field · Signum leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id NumberedListvisual node-graphshape icosaground whitetreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→The cost: a real samplecurate items, nodes | |||||||
| 4 |  first render · fix pending StatScoreboard templatedead_airgeneric_scene | proof | 17.4–22.4s | receipts-count | icon·wireframe | ♪ node_lock | Minus the Hype |
expected on screen: white ground · a StatScoreboard panel over a dimmed Signal Field · Signum leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id StatScoreboardvisual receiptsshape icosaground whitetreatment wireframemotion receipts-countpower receiptsinstrument spotlight→Minus the Hypecurate pillar, stats, statsLabels | |||||||
| 5 |  first render · fix pending shared field signature-3ddead_airgeneric_scene | resolve | 22.4–27.4s | coalescence | icon·color | ♪ bed_out | Minus the Hype |
expected on screen: white ground · icosa hero in the shared Signal Field · Signum leads · coalescence · coalescence · icon·color logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape icosaground whitetreatment colormotion coalescencepower coalescenceinstrument coalescence→Minus the Hype | |||||||
Format stack 3 aspects · same scenes[], re-cropped
9:16
1080×1920
Stories · TikTok · YouTube Shorts · Reels
1:1
1080×1080
LinkedIn · Facebook · Instagram
16:9
1920×1080
X/Twitter · YouTube · LinkedIn video
Channels 9 destinations
LinkedInX/TwitterYouTubeInstagramFacebookThreadsTikTokPinterestBluesky
Social captions supplemental published copy · per channel (comp_id level)
tiktok"Clone your brand voice from one prompt." Out comes the same beige tone as everyone else. What works: paste five things you actually wrote plus a list of banned words, and the model mirrors you. The cost is owning a real voice first. (AI-assisted)
instagram"AI clones your voice"
From one prompt? You get beige.
What works:
Paste 5 things you actually wrote.
Add a list of banned words.
Now the model mirrors you.
#brandvoice #aiwriting #copywriting #contentmarketing #marketingops
linkedinThe pitch: clone your brand voice from a single prompt. The result is usually the same beige tone everyone else gets. What actually works is feeding the model real material: paste five things you genuinely wrote, plus a list of words you never use. Then it mirrors you instead of the internet average. The catch is honest: you need a real voice to clone in the first place. Write five honest posts before you ever try it.
x"AI clones your voice" from one prompt = beige. What works: paste 5 things you actually wrote + a banned-words list, then the model mirrors you. The cost is owning a real voice first. temerarii.xyz
facebookPeople say AI can clone your brand voice from a single prompt. What you usually get is the same beige tone as everyone else. What actually works: paste five things you really wrote, add a list of banned words, and let the model mirror you. The catch is you need a real voice to clone first.
threads"AI clones your voice from one prompt." Out comes the same beige tone as everyone else. What works: paste five things you actually wrote and a list of banned words, then the model mirrors you. The cost is having a real voice to clone in the first place.
pinterestHow to clone your brand voice with AI the right way. A single prompt gives you a generic, beige tone. Instead, paste five real things you wrote plus a list of banned words, and the model mirrors your actual style. The requirement: you need a real, distinct voice to clone first. A practical content writing tip.
bluesky"AI clones your voice from one prompt" = beige. What works: paste 5 things you actually wrote + a banned-words list, then it mirrors you. You still need a real voice first.
youtubeTitle: AI Brand Voice Cloning, Minus the Hype: Feed It Real Examples
Clone your voice from one prompt and you get the same beige tone as everyone else. The method that works: paste five things you actually wrote and a list of banned words, then the model mirrors you. The honest catch is you need a real voice to clone first. We show the setup.