This page requires JavaScript to display.
The Nolan Scott Team Sells and buys businesses from $1M to $15M+, and advises on the real estate that comes with them. nolanscottteam.com →
Example 16 / 18 · a sample from our Rolodex of 100+ automations Claude Skill
Automation Breakdown · Claude Skill

Remotion Reels

Record on a phone, drop the file in a folder, get back a finished reel. Claude cuts every silence and dead-air pause, transcribes the audio word by word, and burns TikTok-style captions synced to each spoken word, rendered with Remotion, no script ever typed.

15 pipeline steps
3 engines · ffmpeg, Whisper, Remotion
0 scripts typed
1 drop folder
True AI automation isn’t one clever workflow. It takes 20 to 40 workflows working together to make a real impact on a business. That’s what we do: a Rolodex of 100+ automations across different CRMs and platforms, ready to be custom-built for your specific CRM and software stack.
The Workflow
Scroll sideways · click any step for its explanation
true
false
true
false
No script, ever
Tyler records on his phone and drops the file. The transcript comes from the audio; the captions come from the transcript. He never types a word.
No froufrou
Deliberately simple vertical videos: his footage, tightened up, with bold word-synced captions. No motion graphics.
Multi-take rule
Several clips, many retakes → audio first, video later. His LAST attempt at a line is almost always the keeper; footage moves only after the takes are chosen.
▶
“Process the Video”
or make a reel
F
Check Raw Folder
the drop box
⇄
Fresh Session?
toolchain there?
{ }
Rebuild Toolchain
~4 min, idempotent
ff
Probe & Extract Audio
ffprobe + -vn
Wh
Whisper Transcribe
word-level times
ff
Detect Silences
-35dB / 0.45s
ff
Cut & Concat
keeper segments
{ }
Remap Word Timings
onto cut timeline
R
Write Caption Data
captions-data.ts
R
Render Final
CaptionedVideo
F
Send Draft + Transcript
30 MB chat cap
⇄
Captions Approved?
one skim
{ }
Fix Mis-Heard Words
edit + re-render
F
Archive Project
Completed\<name>
F
Commit Full-Quality
19 MB parts + md5
◈
The pipeline at a glance
Click any step to see exactly what it does. The pipeline reads left to right: stage the clip, cut the silences, sync the captions, render, one human skim, archive.
ffmpeg
Whisper
Remotion
Device folder
Logic / rules
Branch (if)
Trigger
How It Works

Phone clip in, finished reel out

01 · The Drop Box
Raw folder in, no ceremony

“Process the video in the Raw folder” is the whole instruction. Claude finds the clips, stages them to the cloud workspace, and rebuilds the toolchain (whisper + Remotion) if the session is fresh. For multi-take projects it works audio-first, transcribing every take and keeping the last attempt at each line before moving any heavy footage.

02 · The Auto-Edit
Silences out, captions on

Whisper transcribes the audio with word-level timestamps. ffmpeg detects every silence and dead-air pause, cuts them, and re-stitches the keeper segments. The word timings are remapped onto the cut timeline so Remotion can burn bold, uppercase captions with the current word highlighted, the style the algorithms read.

03 · Review & Archive
One skim, then it ships

The draft MP4 and transcript come back for a caption skim, the only human step. Mis-heard words are fixed in the caption data and only the render re-runs. On approval, the full-quality final lands in a Completed project folder with the transcript and original takes, and Raw is left empty for the next reel.

Next example: Vintage Lister →
AI · nolan scott team
Unpacking...