Checklist the per-video bar — engine/sim
85.2/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review thread-minus-the-hype-W43-Mon good|bad)⚠ 5 flag(s) — not yet ship-ready: low_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 · 31.2s · 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 | 0–6.1s | kinetic-build | icon·wireframe | ♪ node_lock | It looks like the future. Clone a voice, type any script, skip the studio for good. on-screen: "Voice clone = your spokesperson" |
expected on screen: white ground · dodeca hero in the shared Signal Field · Mensor leads · mark · kinetic-build · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual markshape dodecaground whitetreatment wireframemotion kinetic-buildpower laser-lockinstrument laser-trace→"Voice clone = your spokesperson" | |||||||
| 2 |  matches intent CodeWindow template | diff | 6.1–15.799999999999999s | crossfade-8f | icon·wireframe | ♪ node_lock | What we really do: a clean voice sample goes into ElevenLabs, then we still direct it. We mark the punctuation for pacing and redo lines for the right feel. on-screen: Reality: clean audio in, direction out |
expected on screen: white ground · a CodeWindow panel over a dimmed Signal Field · Mensor leads · code · crossfade-8f · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id CodeWindowvisual codeshape dodecaground whitetreatment wireframemotion crossfade-8fpower morphinstrument morph→Reality: clean audio in, direction outcurate codeLines, windowTitle | |||||||
| 3 |  matches intent ChecklistCard template | teach | 15.8–21.200000000000003s | kinetic-build | icon·wireframe | ♪ node_lock | The real cost of fire-and-forget cloning is a flat, odd read your audience tunes out. on-screen: The cost: uncanny, untrusted |
expected on screen: white ground · a ChecklistCard panel over a dimmed Signal Field · Mensor leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id ChecklistCardvisual node-graphshape dodecaground whitetreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→The cost: uncanny, untrustedcurate items, nodes | |||||||
| 4 |  first render · fix pending KpiGrid templatedead_airgeneric_scene | proof | 21.2–26.2s | receipts-count | icon·wireframe | ♪ node_lock | Minus the Hype |
expected on screen: white ground · a KpiGrid panel over a dimmed Signal Field · Mensor leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id KpiGridvisual receiptsshape dodecaground whitetreatment wireframemotion receipts-countpower receiptsinstrument spotlight→Minus the Hypecurate kpis, statsLabels | |||||||
| 5 |  first render · fix pending shared field signature-3ddead_airgeneric_scene | resolve | 26.2–31.2s | coalescence | icon·3d-extrude | ♪ bed_out | Minus the Hype |
expected on screen: white ground · dodeca hero in the shared Signal Field · Mensor leads · coalescence · coalescence · icon·3d-extrude logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape dodecaground whitetreatment 3d-extrudemotion 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)
tiktokThe pitch: clone a voice, type any script, skip the studio for good. The reality: we feed a clean sample into ElevenLabs, then still direct it. Fire-and-forget cloning sounds flat and odd, and people tune it out. (AI-assisted)
instagramVoice clone = your spokesperson?
The pitch sounds like the future.
The reality: clean audio in, real direction out.
The cost of skipping that: a flat, uncanny read.
We still mark pacing and redo lines.
#voiceai #elevenlabs #aivoice #contentcreation #minusthehype
linkedin"Voice clone equals your spokesperson" is the pitch: clone a voice, type any script, never book a studio again.
Our real workflow is narrower and it works. A clean voice sample goes into ElevenLabs, then we still direct the output. We mark the punctuation for pacing and redo lines for the right feel.
The cost of fire-and-forget cloning is a flat, uncanny read your audience tunes out. The tool is real. The direction is what makes it usable.
x"Voice clone = your spokesperson." Reality: clean sample into ElevenLabs, then we still direct it for pacing and feel. Fire-and-forget cloning sounds flat and uncanny. temerarii.xyz
facebookThe pitch says you can clone a voice, type any script, and never book a studio again. What we actually do: feed a clean sample into ElevenLabs, then still direct it for pacing and emphasis. Skip that step and you get a flat, uncanny read people tune out. See more at temerarii.xyz.
threads"Voice clone = your spokesperson."
The reality is narrower. A clean voice sample goes into ElevenLabs, then we still direct it. We mark pacing and redo lines for feel. Fire-and-forget cloning sounds flat and odd, and your audience tunes it out. The tool is real, the direction is the work.
pinterestAI voice cloning workflow, minus the hype: feed a clean voice sample into ElevenLabs, then direct the output with punctuation for pacing and retakes for emphasis. Fire-and-forget cloning produces a flat, uncanny read. The tool is real, but human direction is what makes AI voice usable.
bluesky"Voice clone = your spokesperson." Reality: clean sample into ElevenLabs, then we still direct it for pacing and feel. Fire-and-forget cloning sounds flat and uncanny.
youtubeTitle: Voice Cloning, Minus the Hype: Why You Still Have to Direct It
The pitch says clone a voice, type any script, and skip the studio for good. The real workflow: a clean voice sample into ElevenLabs, then human direction for pacing and emphasis. Fire-and-forget cloning produces a flat, uncanny read your audience tunes out. More at temerarii.xyz.