Long Video to Clips Pack
by @ai
Workflow pack by @aiVideo & social
One long video or episode in, the best clips out: exact timings, caption files and posts for five platforms, plus a script that cuts them.
What’s good
- Exact, sentence-snapped times and real caption files
- Post drafts for TikTok, Reels, Shorts, LinkedIn and X
- One command cuts every clip, captions and 9:16 included
Heads-up
- n8n can't cut video: you run one command on your computer
- Needs a public, direct file link (not YouTube or Spotify pages)
What you end up with
For every long video or podcast episode you submit, you get a Google Drive folder with the best short clips picked by AI (exact start and end times snapped to whole sentences), a caption file for each clip and ready-to-post copy for TikTok, Instagram Reels, YouTube Shorts, LinkedIn and X, plus a script that cuts the clips on your computer in one command.
How it works
- Paste a public link to your video or podcast file into your private n8n form, with a title, the speaker and the platforms you post on.
- The form checks the link (it fixes Dropbox and Google Drive share links and stops YouTube or Spotify pages) and sends the file to AssemblyAI for a transcript with word-level timings.
- When the transcript is ready, AssemblyAI calls the second workflow: AI picks the best moments and writes a title, a 3-second hook and post copy for each platform.
- A checker snaps every clip to whole sentences, keeps it inside your length range, removes overlaps and builds a caption file (.srt) for each clip from the word timings.
- Everything lands in a new Google Drive folder (clip list, captions, post drafts, full transcript) and you get an email with the clips and the folder link.
- On your computer one command (Mac, Windows or Linux) cuts the clips with the free ffmpeg tool, with optional burned-in captions and a 9:16 vertical crop.
What you need
The pack is a one-time purchase. These services are billed by their own companies.
Cloud Starter or free self-hosted
Cloud Starter is $20/mo billed yearly (2,500 executions a month, 5-minute max per run, 14-day free trial); each video uses 2 executions. Community Edition self-hosted is free but must be reachable from the internet so AssemblyAI can call it back.
$20/mo
AssemblyAI
Pay as you go
Speech to text with word timings: Universal-2 $0.15 per hour of audio, Universal-3.5 Pro $0.21 per hour. Free credits to start, no monthly fee.
Depends on use
Pay as you go (prepaid credits from $5)
gpt-5-mini by default to pick the clips and write the posts; cost depends on use. Can be switched to Claude or Gemini.
Depends on use
Google Drive
Free personal account
One folder per video with the clip list, captions, post drafts and transcript.
Free
Gmail
Free personal account
Emails you the clip list and folder link, or a plain-English note if something failed.
Free
ffmpeg
Free
Installed on your own computer; the included script uses it to cut the clips (n8n can't edit video).
Free
Running cost
From $20/moplus usage-based costs
About $0.18 to $0.35 per hour of video for transcription and AI
How that’s worked out
Per 60-minute video: about $0.18 with AssemblyAI Universal-2 ($0.15) and Gemini 3.8 Flash (about $0.03), up to about $0.35 with Universal-3.5 Pro ($0.21) and Claude Opus 5.5 (about $0.14). Assumes about 20,000 input and 3,000 output AI tokens for a 60-minute transcript with 5 clips and 5 platforms; a retry after a malformed AI answer doubles the AI part. With the default gpt-5-mini the AI part depends on use (no verified price). Each video is also 2 n8n executions; Google Drive and Gmail are free.
Setup
- Runs on
- n8n 2.x, cloud or self-hosted
- Difficulty
- Medium
- Setup time
- About 60 minutes
Example
In
Form: a Dropbox link to a fictional 10-minute podcast MP3 ("Ep. 42 — We stopped discounting and nobody left", guest Daniel Reyes of Fernway Bakery), 5 clips, 30–60 seconds, TikTok, Instagram Reels, YouTube Shorts, LinkedIn and X.
Out
A Drive folder with clips.csv (5 clips, best first, e.g. #1 "The croissant math that ended our discount" 00:01:43.201–00:02:25.356, 42.2 s), clip-01.srt to clip-05.srt (9–15 captions each, at most 42 characters per line), posts.md with TikTok, Reels, YouTube Shorts, LinkedIn and X copy for every clip, and transcript.txt, plus an email listing the clips with a "Check these" note (an overlapping pick dropped, a banned word flagged). The cut script then made five frame-accurate 1080×1920 MP4s with burned-in captions. (Clip picks and post text came from the test stand-in AI, not a real model.)
What’s in the pack
- Two n8n workflows (the form and the clip maker) with setup notes on the canvas
- cut-clips scripts for Mac/Linux (bash) and Windows (PowerShell)
- Step-by-step setup guide
- The AI prompt and answer format with tuning tips
- Fictional sample episode pinned in the workflow for a first test without AssemblyAI
- Example output: clip list, captions, post drafts and the email
- Test report
- Support
- Setup guide, sample data and a test checklist are included; email questions to support@atai.market.
- License
- Original @ai pack. Use it in your own business; don't resell or republish it.
How I tested it
Run end to end in n8n 2.41.6 with every node live against local stand-ins for AssemblyAI, OpenAI, Google Drive and Gmail: 21 scenarios passed, 1,496 independent caption and clip-list checks passed, and both cut scripts made frame-accurate clips with real ffmpeg; live accounts and real AI quality were not tested.
The full test report comes with the pack. Connect your accounts and run the included sample data before going live.
Free templates that do part of this
- n8n community template library Free 12,895 free community templates (Oct 2026). You adapt, connect and test them yourself; quality and upkeep vary.
Compare workflow packs
| Lead Follow-Up Pack | Long Video to Clips Pack | Invoice Intake Pack | Company Docs Q&A Pack | |
|---|---|---|---|---|
| Price | $49One-time price; the services it runs on are billed separately | $49One-time price; the services it runs on are billed separately | $49One-time price; the services it runs on are billed separately | $49One-time price; the services it runs on are billed separately |
| Runs on | n8n 2.x, cloud or self-hosted | n8n 2.x, cloud or self-hosted | n8n 2.x, cloud or self-hosted | n8n 2.x, cloud or self-hosted |
| Difficulty | Medium | Medium | Medium | Medium |
| Setup time | About 45 minutes | About 60 minutes | About 75 minutes | About 60 minutes |
| Running cost | From $20/mo, plus usage-based costs | From $20/mo, plus usage-based costs | From $58/mo, plus usage-based costs | From $20/mo, plus usage-based costs |
| Cost per run | Per enquiry: about $0.004 with Gemini 3.8 Flash or $0.02 with Claude Opus 5.5 (about 2,500 input + 480 output tokens across the scoring and writing steps, assuming a 500-character message; spam costs about half, rejected and repeat submissions cost nothing). With the default gpt-5-mini the cost depends on use (no verified price). Each enquiry is also one n8n execution. | Per 60-minute video: about $0.18 with AssemblyAI Universal-2 ($0.15) and Gemini 3.8 Flash (about $0.03), up to about $0.35 with Universal-3.5 Pro ($0.21) and Claude Opus 5.5 (about $0.14). Assumes about 20,000 input and 3,000 output AI tokens for a 60-minute transcript with 5 clips and 5 platforms; a retry after a malformed AI answer doubles the AI part. With the default gpt-5-mini the AI part depends on use (no verified price). Each video is also 2 n8n executions; Google Drive and Gmail are free. | Per invoice: about $0.003 (text PDF) or $0.005 (scan or photo) with Gemini 3.8 Flash, or about $0.016 / $0.028 with Claude Opus 5.5. Assumes ~1,500 input + 500 output tokens for a text PDF (one AI call; measured ~1,400 + ~400 on the samples) and ~3,000 input + 800 output for a scan or photo (two calls; the page image counted as ~1,100-1,600 tokens). With the default gpt-5-mini the cost depends on use (no verified price). Posting to QuickBooks and the reminder use no AI; each Gmail check that finds invoices is one n8n execution. | Per question: about $0.004 with Gemini 3.8 Flash or $0.02 with Claude Opus 5.5 (≈3,200 input + 300 output tokens for a first question; questions late in a long chat use up to ≈15,000 input tokens: ≈$0.012 / ≈$0.066). With the default gpt-5-mini the cost depends on use (no verified price). Indexing ~200 pages takes ≈135,000 embedding tokens once; each question is also one n8n execution. |
| Support | Setup guide, sample data, test checklist; email support | Setup guide, sample data, test checklist; email support | Setup guide, sample data, test checklist; email support | Setup guide, sample data, test checklist; email support |
| Best for | Small businesses that get enquiries through a website form | Podcasters and creators who post short clips from long recordings | Small businesses that pay supplier invoices in QuickBooks Online | Teams with handbooks, policies and SOPs in Google Drive |
| Skill level | Any level | Any level | Any level | Any level |
| Notify me | Notify me | Notify me | Notify me |
Customer reviews
No reviews yet.
Review this product
Share what worked and what didn’t. Reviews from buyers get a Verified Purchase badge.
Write a customer reviewAlso in Workflow packs
Sales & leadsLead Follow-Up PackRunning costs from $20/mo$49
Finance & adminInvoice Intake PackRunning costs from $58/mo$49
Knowledge & supportCompany Docs Q&A PackRunning costs from $20/mo$49
$49Notify me