Checklist the per-video bar — engine/sim
78.9/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review thread-receipts-W32-Fri 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 · 26.6s · comp_id + rendered still + tier + the script
| # | Layer (comp_id · still · tier) | Beat | Timecode | Motion | Logo | Audio | VO / on-screen / caption |
|---|---|---|---|---|---|---|---|
| 1 |  matches intent StatScoreboard template | stat | 0–5.6s | receipts-count | icon·liquid-chrome | ♪ node_lock | One cloned voice narrating three hundred and four script lines — same tone every time. on-screen: 1 voice. 304 lines. |
expected on screen: red ground · a StatScoreboard panel over a dimmed Signal Field · Nuntius leads · receipts · receipts-count · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id StatScoreboardvisual receiptsshape torusground redtreatment liquid-chromemotion receipts-countpower receiptsinstrument spotlight→1 voice. 304 lines.curate pillar, stats, statsLabels | |||||||
| 2 |  matches intent ComparisonTable template | proof | 5.6–10.6s | receipts-count | icon·white-knockout | ♪ node_lock | Hiring a voice session for every single video was the old cost. We cloned the voice once and reused it across all three hundred and four lines. on-screen: Clone once. Reuse. |
expected on screen: red ground · a ComparisonTable panel over a dimmed Signal Field · Nuntius leads · receipts · receipts-count · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id ComparisonTablevisual receiptsshape torusground redtreatment white-knockoutmotion receipts-countpower receiptsinstrument spotlight→Clone once. Reuse.curate colA, colB, rows, statsLabels | |||||||
| 3 |  matches intent JsonDiff template | diff | 10.6–16.6s | crossfade-8f | icon·liquid-chrome | ♪ node_lock | Soon your brand voice is a function call. Clone it once, script the lines, and narrate at scale. on-screen: Voice as an API. |
expected on screen: red ground · a JsonDiff panel over a dimmed Signal Field · Nuntius leads · code · crossfade-8f · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id JsonDiffvisual codeshape torusground redtreatment liquid-chromemotion crossfade-8fpower morphinstrument morph→Voice as an API.curate codeLines, fileName, lines | |||||||
| 4 |  first render · fix pending FlowSchematic templatedead_airgeneric_scene | step | 16.6–21.6s | kinetic-build | icon·white-knockout | ♪ node_lock | Receipts |
expected on screen: red ground · a FlowSchematic panel over a dimmed Signal Field · Nuntius leads · pipeline · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id FlowSchematicvisual pipelineshape torusground redtreatment white-knockoutmotion kinetic-buildpower throwinstrument laser-trace→Receiptscurate stages, steps | |||||||
| 5 |  first render · fix pending shared field signature-3ddead_airgeneric_scene | resolve | 21.6–26.6s | coalescence | icon·liquid-chrome | ♪ bed_out | Receipts |
expected on screen: red ground · torus hero in the shared Signal Field · Nuntius leads · coalescence · coalescence · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape torusground redtreatment liquid-chromemotion coalescencepower coalescenceinstrument coalescence→Receipts | |||||||
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)
tiktokReceipts: one cloned voice narrated 304 script lines, same tone every time. The old way was hiring a voice session per video. Soon your brand voice is a function call. Clone it once, script the lines, narrate at scale. (AI-assisted)
instagram1 voice. 304 lines. Same tone.
Old cost: a VO session per video.
New way: clone the voice once.
Then the brand voice is a function call.
Script the lines. Narrate at scale.
These are our own receipts.
#voiceai #contentops #buildinpublic #automation #creators
linkedinHere is a receipt from our own pipeline: one cloned voice narrated three hundred and four script lines, with the same tone every single time.
The old cost was hiring a voice-over session for every video. That does not scale when you are publishing daily across a whole calendar.
The shift is treating your brand voice as a function call. You clone it once, script the lines, and narrate at scale. The voice stays consistent whether it is line one or line three hundred. Consistency at volume is the whole point.
xReceipt: one cloned voice narrated 304 script lines, same tone every time. Old cost was a VO session per video. New way: your brand voice is a function call. Clone once, script the lines, narrate at scale. temerarii.xyz
facebookHere is a receipt from our own work: one cloned voice narrated 304 script lines with the same tone every time. The old way was hiring a voice session per video, which does not scale. Now your brand voice is a function call. Clone it once, script the lines, and narrate at scale. See how at temerarii.xyz.
threadsReceipt: one cloned voice narrated 304 script lines, same tone every time. The old cost was a voice session per video. Now the brand voice is a function call. Clone it once, script the lines, narrate at scale. Line one sounds like line 304.
pinterestVoice cloning for content at scale, with real receipts. How one cloned brand voice can narrate hundreds of script lines with consistent tone, why per-video voice-over sessions do not scale, and treating brand voice as a reusable function call.
blueskyReceipt: one cloned voice narrated 304 script lines, same tone every time. Old cost was a VO session per video. New way: your brand voice is a function call. Clone once, script the lines, narrate at scale.
youtubeTitle: One Cloned Voice, 304 Script Lines (Brand Voice as an API)
A receipt from our own pipeline: one cloned voice narrated three hundred and four script lines with the same tone every time. The old cost was hiring a voice-over session per video, which does not scale for daily publishing. The shift is treating your brand voice as a function call: clone it once, script the lines, and narrate at scale. More at temerarii.xyz.