73 articles about automation.
YouTube now demotes template-based bulk edits. How to repurpose long form video to shorts with per-clip cuts, real 9:16 crops, and captions from each segment.
Make's ChatGPT plugin is still in limited beta. Set up Make MCP in ChatGPT instead, and send the real video render to a job API that won't time out on you.
Zapier video processing has no FFmpeg step and a 150 MB file cap. What Zaps can really do with video, and where you need to hand the encode to a video API.
Replace audio in video API or FFmpeg CLI: measure drift with ffprobe, pad or trim instead of atempo, and re-burn captions against the new TTS timings.
Parse FFmpeg's -progress output for a real ffmpeg progress percentage: out_time_us against an ffprobe duration, speed= for ETA, and where parsing breaks.
To make FFmpeg add chapters you write an FFMETADATA file and remux with -c copy. The hard part is generating that file: TIMEBASE, escaping, and the last END.
YouTube Shorts series automation, end to end: cut one long video into numbered episodes, reframe to 1080x1920, burn an EP. N bar, and pull each thumbnail.
n8n large video transcription fails because n8n holds the whole file in memory. Hand the Drive URL to an audio-extraction API and send only a 4 MB track.
n8n 2.0 disables the Execute Command node by default, breaking FFmpeg workflows on upgrade. How to diagnose it, re-enable it, and replace it for good.
Extract last frame FFmpeg commands return the wrong frame after a fast seek. Use -sseof with -update 1, then join Veo 3 and Sora 2 clips with no seam.