Checklist the per-video bar — engine/sim
79.8/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review thread-field-notes-W36-Sat 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 · 26.3s · 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 | 0–5.1s | kinetic-build | icon·wireframe | ♪ node_lock | Field note. You re-recorded the same intro forty times because you tweaked one word. on-screen: Re-recording the same line |
expected on screen: black ground · torus hero in the shared Signal Field · Nuntius leads · mark · kinetic-build · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual markshape torusground blacktreatment wireframemotion kinetic-buildpower laser-lockinstrument laser-trace→Re-recording the same line | |||||||
| 2 |  matches intent ChecklistCard template | teach | 5.1–10.1s | kinetic-build | icon·wireframe | ♪ node_lock | Old way: book the booth, read it again, and again, paying for studio time on every tiny edit. on-screen: Clone once, retake free |
expected on screen: black ground · a ChecklistCard panel over a dimmed Signal Field · Nuntius leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id ChecklistCardvisual node-graphshape torusground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→Clone once, retake freecurate items, nodes | |||||||
| 3 |  matches intent StackTrace template | diff | 10.1–16.3s | crossfade-8f | icon·wireframe | ♪ node_lock | Record one clean minute, clone it, and generate your next script. You'll never dread a typo again. on-screen: Clone one voice today |
expected on screen: black ground · a StackTrace panel over a dimmed Signal Field · Nuntius leads · code · crossfade-8f · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id StackTracevisual codeshape torusground blacktreatment wireframemotion crossfade-8fpower morphinstrument morph→Clone one voice todaycurate codeLines, errMsg, errType, fix, frames | |||||||
| 4 |  first render · fix pending ProcessFlow templatedead_airgeneric_scene | proof | 16.3–21.3s | receipts-count | icon·wireframe | ♪ node_lock | Field Notes |
expected on screen: black ground · a ProcessFlow panel over a dimmed Signal Field · Nuntius leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id ProcessFlowvisual receiptsshape torusground blacktreatment wireframemotion receipts-countpower receiptsinstrument spotlight→Field Notescurate statsLabels, steps | |||||||
| 5 |  first render · fix pending shared field signature-3ddead_airgeneric_scene | resolve | 21.3–26.3s | coalescence | icon·wireframe | ♪ bed_out | Field Notes |
expected on screen: black ground · torus hero in the shared Signal Field · Nuntius leads · coalescence · coalescence · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape torusground blacktreatment wireframemotion coalescencepower coalescenceinstrument coalescence→Field Notes | |||||||
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)
tiktokField note: you re-recorded the same intro 40 times because you tweaked one word. The fix: record one clean minute, clone your voice, then generate the next script from text. Change a word, regenerate, done. You'll never dread a typo again. (AI-assisted)
instagramField note
Re-recording the same line for one word? Stop.
Record one clean minute.
Clone the voice.
Generate the next script from text.
Fix a typo without booking the booth.
#voiceover #ai #audio #contentcreation #fieldnotes
linkedinField note: you re-recorded the same intro forty times because you tweaked one word. The old way meant booking the booth and reading it again, and again.
The move: record one clean minute, clone that voice, and generate your next script from text. Change a word, regenerate the line, ship it.
You will never dread a typo in a script again.
xField note: re-recording the same intro 40x over one word? Record one clean minute, clone the voice, generate the next script from text. Fix a typo without re-booking the booth.
facebookField note for anyone who records audio: you re-recorded the same intro forty times because you tweaked one word. The old way was booking the booth and reading it again and again. Instead, record one clean minute, clone that voice, and generate your next script from text. Now a typo is a quick regenerate, not a re-shoot. Give it a try.
threadsField note: you re-recorded the same intro 40 times because you changed one word.
The fix: record one clean minute, clone the voice, then generate the next script from text.
Change a word, regenerate. You'll never dread a typo again.
pinterestStop re-recording voiceovers over a single word. Record one clean minute, clone your voice, and generate your next script from text. A simple AI audio workflow that turns a typo fix into a quick regenerate instead of a full re-shoot.
blueskyField note: re-recording the same intro 40x over one word? Record one clean minute, clone the voice, generate the next script from text. Fix a typo without re-booking the booth.
youtubeTitle: Stop Re-Recording: Clone Your Voice Once
Field note for anyone who records audio. You re-recorded the same intro forty times because you tweaked one word. The old way meant booking the booth and reading it again and again. The move: record one clean minute, clone that voice, and generate your next script from text. Change a word, regenerate the line, ship it. Search terms: voice cloning, AI voiceover, audio workflow, content creation, text to speech.