惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

有赞技术团队
有赞技术团队
Stack Overflow Blog
Stack Overflow Blog
爱范儿
爱范儿
B
Blog
博客园 - 三生石上(FineUI控件)
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
A
About on SuperTechFans
C
Check Point Blog
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
P
Proofpoint News Feed
Engineering at Meta
Engineering at Meta
Y
Y Combinator Blog
WordPress大学
WordPress大学
小众软件
小众软件
博客园 - 司徒正美
Apple Machine Learning Research
Apple Machine Learning Research
Recent Announcements
Recent Announcements
L
LangChain Blog
大猫的无限游戏
大猫的无限游戏
阮一峰的网络日志
阮一峰的网络日志
D
DataBreaches.Net
博客园 - 聂微东
Microsoft Security Blog
Microsoft Security Blog
美团技术团队

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant
Auto-Publish 30 YouTube Shorts Per Week from One Long Video
Javid Jamae · 2026-06-18 · via DEV Community

Javid Jamae

Originally published at ffmpeg-micro.com

One 30-minute video contains enough material for 30+ YouTube Shorts. Most creators leave that content on the table because splitting, captioning, and publishing 30 clips manually takes hours. With n8n and FFmpeg Micro, you can automate the entire pipeline: split the long video, add captions to each clip, and schedule them for auto-publish.

The Pipeline at a Glance

  1. Split a long video into 30-60 second clips using FFmpeg Micro's trim and crop operations
  2. Caption each clip with burned-in subtitles using Whisper transcription
  3. Publish each captioned clip to YouTube on a schedule via the YouTube Data API

The whole thing runs in n8n, triggered by dropping a video URL into a webhook or a Google Drive folder.

Step 1: Split the Long Video into Clips

Use FFmpeg Micro's transcription endpoint to generate an SRT file and identify natural break points:

curl -X POST https://api.ffmpeg-micro.com/v1/transcribe \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"media_url": "https://storage.googleapis.com/your-bucket/long-video.mp4"}'

Then trim each clip:

curl -X POST https://api.ffmpeg-micro.com/v1/transcodes \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "inputs": [{"url": "https://storage.googleapis.com/your-bucket/long-video.mp4"}],
    "outputFormat": "mp4",
    "options": [
      {"option": "-ss", "argument": "00:02:15"},
      {"option": "-t", "argument": "45"},
      {"option": "-vf", "argument": "crop=ih*9/16:ih"},
      {"option": "-c:v", "argument": "libx264"},
      {"option": "-preset", "argument": "fast"}
    ]
  }'

One API call per clip. 45 seconds, 9:16 vertical, H.264.

Step 2: Add Captions

Transcribe each clip individually, then burn subtitles back in with FFmpeg Micro's text overlay.

Step 3: The n8n Workflow

Six nodes: Webhook trigger, HTTP Request (transcribe), Wait (poll), Code (parse SRT), Loop (trim+caption each clip), YouTube upload (scheduled publish).

const totalDuration = $input.first().json.duration;
const CLIP_DURATION = 45;
const segments = [];

for (let i = 0; i < Math.floor(totalDuration / CLIP_DURATION); i++) {
  const startSeconds = i * CLIP_DURATION;
  const hours = String(Math.floor(startSeconds / 3600)).padStart(2, '0');
  const mins = String(Math.floor((startSeconds % 3600) / 60)).padStart(2, '0');
  const secs = String(startSeconds % 60).padStart(2, '0');
  segments.push({
    clipNumber: i + 1,
    startTime: `${hours}:${mins}:${secs}`,
    duration: CLIP_DURATION
  });
}
return segments.map(s => ({ json: s }));

Cost Breakdown

For a 30-minute source video producing 30 clips: ~96 billable minutes total. One video per month fits in FFmpeg Micro's free tier (100 min/mo). Weekly production needs the Pro plan at $19/month.

FAQ

How many YouTube Shorts can I make from a 30-minute video?
30-40 Shorts at 45-60 seconds each.

Do I need to install FFmpeg?
No. FFmpeg Micro is a cloud API. HTTP requests from n8n handle everything.

Can I use Make.com instead of n8n?
Yes. FFmpeg Micro has an official Make.com app.