Back Office · office.temerarii.xyz
One asset, all the way in — composition, the wireframe + storyboard, the output format stack, and the template, all read from the SAME content-index record. The expected output matches what /media surfaces for this post.
post topic-mm-livestreamkind topicweek —date —campaign multimedia-pillarpillar multimediabeat —asset videoduration 65.4sground blackscenes 9

Checklist the per-video bar — engine/sim

98.3/100
plain languagevo coverageno dead airuniquenesscaption fitcompletenesscleanliness
quantitative quality · weights learn from your reviews (engine.sim.memory review topic-mm-livestream good|bad)
⚠ 1 flag(s) — not yet ship-ready: too_complex · see docs/strategy/VIDEO-CHECKLIST.md

Composition comp · template family · expected output

composition SceneReelfamily / template SceneReel
9:16 Reelrendered1:1 Squarepending16:9 Widepending9:16 4Kpending1:1 4Kpending16:9 4KpendingGIF (SMS)pending
▶ open rendered mp4
expected output: 1/7 rendered — same matrix the /media preview surfaces for this asset.

Composition layer × scene 9 scenes · 65.4s · comp_id + rendered still + tier + the script

#Layer (comp_id · still · tier)BeatTimecodeMotionLogoAudioVO / on-screen / caption
1s1
matches intent
shared field
signature-3d		open0–7.2sspatial-parallaxicon·wireframe♪ —
A livestream doesn't have to look like a webcam in a closet. With a small AI rig, one person can run a produced broadcast.
on-screen: Go live, look produced
expected on screen: black ground · octa hero in the shared Signal Field · Lumen leads · node-graph · spatial-parallax · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape octaground blacktreatment wireframemotion spatial-parallaxpower summoninstrument summon→three-mark
2s2
matches intent
ListCard
template		legacy7.2–14.5scrossfade-8ficon·wireframe♪ —
The old way meant a switcher operator, a captioner, and someone clipping highlights after. Three roles, one stream.
on-screen: Old way: a crew per stream
expected on screen: black ground · a ListCard panel over a dimmed Signal Field · Lumen leads · crossfade-8f · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id ListCardshape octaground blacktreatment wireframemotion crossfade-8fpower morphinstrument decay→three-symboliccurate items
3s3
matches intent
NumberedList
template		teach14.5–23.6skinetic-buildicon·wireframe♪ —
It starts in OBS: pre-built scenes for camera, screen-share, and the lower-third, so switching looks intentional, not improvised.
on-screen: Scenes set up in OBS
expected on screen: black ground · a NumberedList panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id NumberedListvisual node-graphshape octaground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→html-in-canvas-panelcurate items, nodes
4s4
matches intent
ChecklistCard
template		teach23.6–31.3skinetic-buildicon·wireframe♪ —
We route the stream audio into Whisper running locally, which transcribes in near real time for live captions and a full transcript.
on-screen: Audio -> Whisper -> captions
expected on screen: black ground · a ChecklistCard panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id ChecklistCardvisual node-graphshape octaground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→three-diagramcurate items, nodes
5s5
matches intent
LegacyCard
template		teach31.3–38.3skinetic-buildicon·wireframe♪ —
During the stream we drop timestamps on the good moments. That marker list is the recipe for the clips we cut later.
on-screen: Timestamps mark the moments
expected on screen: black ground · a LegacyCard panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id LegacyCardvisual node-graphshape octaground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→html-in-canvas-codecurate nodes
6s6
matches intent
AnnotatedDiagram
template		teach38.3–46.9skinetic-buildicon·wireframe♪ —
After it ends, the flow runs itself: the transcript plus your timestamps feed FFmpeg, which cuts vertical clips for every platform.
on-screen: Stream -> transcript -> auto-clips
expected on screen: black ground · a AnnotatedDiagram panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id AnnotatedDiagramvisual node-graphshape octaground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→three-flowcurate callouts, nodes
7s7
matches intent
StatScoreboard
template		proof46.9–52.5sreceipts-counticon·wireframe♪ —
One hour live becomes a stack of short clips and a captioned replay, posted the same day.
on-screen: One stream, ten clips
expected on screen: black ground · a StatScoreboard panel over a dimmed Signal Field · Lumen leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id StatScoreboardvisual receiptsshape octaground blacktreatment wireframemotion receipts-countpower receiptsinstrument spotlight→html-in-canvas-receiptscurate pillar, stats, statsLabels
8s8
matches intent
shared field
signature-3d		futurist52.5–59.0sspatial-parallaxicon·wireframe♪ —
Soon a single creator can run weekly broadcasts that look like a studio made them, because the studio is
on-screen: Solo broadcasts at scale
expected on screen: black ground · octa hero in the shared Signal Field · Lumen leads · spatial-parallax · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldshape octaground blacktreatment wireframemotion spatial-parallaxpower spatial-parallaxinstrument laser-fire→three-forward
9s9
matches intent
shared field
signature-3d		resolve59.0–65.4scoalescenceicon·wireframe♪ swell
Want a livestream setup that clips itself? We'll wire the rig. Find us at temerarii.xyz.
on-screen: Build your stream rig
expected on screen: black ground · octa hero in the shared Signal Field · Lumen leads · coalescence · coalescence · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape octaground blacktreatment wireframemotion coalescencepower coalescenceinstrument coalescence→three-coalescence

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 12 destinations

LinkedInX/TwitterYouTubeInstagramFacebookThreadsTikTokPinterestBlueskyEmailSMSBlog

Social captions supplemental published copy · per channel (comp_id level)

tiktokA livestream does not have to look like a webcam in a closet. AI-assisted setup so one person runs a produced broadcast: pre-build scenes in OBS for camera, screen-share, and the lower-third, so switching looks intentional. Route the stream audio into Whisper running locally for live captions and a full transcript. Drop timestamps on the good moments live. After it ends, the transcript plus your timestamps feed FFmpeg, which cuts vertical clips for every platform. One hour live becomes a stack of clips, same day. temerarii.xyz
instagramGo live, look produced. One person, no crew. Pre-build OBS scenes: camera, screen-share, lower-third. Route audio into local Whisper for live captions. Drop timestamps on the good moments. Transcript + timestamps feed FFmpeg, which cuts vertical clips. One hour live becomes a stack of clips, same day. temerarii.xyz #livestream #obs #whisper #streamsetup #temerarii
linkedinA livestream does not have to look like a webcam in a closet. With a small AI rig, one person can run a produced broadcast. The old way meant a switcher operator, a captioner, and someone clipping highlights after, three roles for one stream. Here is how one person covers all three. It starts in OBS: pre-built scenes for camera, screen-share, and the lower-third, so switching looks intentional, not improvised. Route the stream audio into Whisper running locally, which transcribes in near real time for live captions and a full transcript. During the stream, drop timestamps on the good moments. That marker list is the recipe for the clips you cut later. After it ends, the transcript plus your timestamps feed FFmpeg, which cuts vertical clips for every platform. One hour live becomes a stack of short clips and a captioned replay, posted the same day. Want a setup that clips itself? temerarii.xyz
xA livestream does not have to look like a webcam in a closet. Pre-build OBS scenes, route audio into local Whisper for captions, drop timestamps on good moments, feed transcript + timestamps to FFmpeg. One hour live, a stack of clips, same day. temerarii.xyz
facebookA livestream does not have to look like a webcam in a closet. The old way meant three people: a switcher operator, a captioner, and someone clipping highlights after. Here is how one person does it. Pre-build scenes in OBS for camera, screen-share, and the lower-third so switching looks intentional. Route the stream audio into Whisper running locally for live captions and a full transcript. Drop timestamps on the good moments as you go. After it ends, the transcript plus your timestamps feed FFmpeg, which cuts vertical clips for every platform. One hour live becomes a stack of clips, posted the same day. Want a rig that clips itself? temerarii.xyz
threadsA livestream does not have to look like a webcam in a closet. Pre-build OBS scenes, route audio into local Whisper for live captions, drop timestamps on the good moments, then feed the transcript plus timestamps to FFmpeg for vertical clips. One hour live becomes a stack of clips, same day. temerarii.xyz
pinterestSolo livestream production setup: pre-build OBS scenes for camera, screen-share, and lower-third, route audio into local Whisper for live captions and a transcript, drop timestamps on the good moments, then feed transcript and timestamps to FFmpeg for vertical clips. One stream, ten clips, same day. Save this streaming workflow.
blueskyA livestream does not have to look like a webcam in a closet. One person: pre-built OBS scenes, local Whisper for live captions, timestamps on the good moments, then FFmpeg cuts the vertical clips. One hour live becomes a stack of clips, posted same day. temerarii.xyz
youtubeSolo Produced Livestream: OBS Scenes + Local Whisper Captions + Auto-Clips A livestream does not have to look like a webcam in a closet. With a small AI rig, one person can run a produced broadcast. The old way meant a switcher operator, a captioner, and someone clipping highlights after, three roles for one stream. Here is how one person covers all three, given away. It starts in OBS: pre-built scenes for camera, screen-share, and the lower-third, so switching looks intentional, not improvised. Route the stream audio into Whisper running locally, which transcribes in near real time for live captions and a full transcript. During the stream, drop timestamps on the good moments. That marker list is the recipe for the clips you cut later. After it ends, the flow runs itself: the transcript plus your timestamps feed FFmpeg, which cuts vertical clips for every platform. One hour live becomes a stack of short clips and a captioned replay, posted the same day. What is next: a single creator runs weekly broadcasts that look like a studio made them. Want a livestream setup that clips itself? We will wire the rig. temerarii.xyz

Cross-links every lens is a view on this one record

→ Wireframe · scenes→ Calendar week→ Media (audience preview)→ Storyboard hub→ Day view→ Channel view