louisedesadeleer/clipify

What it solves

Clipify is a tool for turning long-form videos, such as interviews or podcasts, into short, social-media-ready clips. It eliminates the need for expensive SaaS tools or slow manual editing by automating the segment selection, reframing, and subtitling process locally on your machine.

How it works

As a skill for Claude Code, Clipify uses Whisper to transcribe video and identify high-impact segments based on audio peaks and transcript analysis. To create vertical clips from horizontal video, it uses a motion-energy approach: it identifies the mouth and chin areas of speakers in a sample frame and uses ffmpeg to track motion energy in those areas to determine who is speaking. It then creates hard-cut pans to follow the active speaker or creates a split-screen view. Finally, it burns word-by-word captions into the video using ASS subtitles.

Who it’s for

Content creators who produce talking-head dialogue, such as podcasters and interviewers, who want to quickly generate clips for platforms like TikTok and LinkedIn without using cloud APIs.

Highlights

• Local Processing: Runs entirely on the user's machine without cloud APIs.
• Automated Segment Discovery: Proposes 3-5 clip-worthy candidates based on transcription and audio analysis.
• Automated Reframing: Converts 16:9 video to 9:16 by following the speaker via motion energy tracking rather than complex face detection models.
• Customizable Subtitles: Supports multiple caption styles, including opus-style word-by-word highlights.