Free AI training for business owners·Every Thursday at 12pm, Paris time Free AI training·Thursdays 12pm Sign up

Case study · Inside Unkillable · Content

Automatic video editing saves hours and budget, and gets each episode from recording to publishing much faster.

Our video podcast is filmed with several cameras and microphones, often with a demo on screen. Instead of an editor, a pipeline we brief in plain language syncs, cuts, switches cameras, blurs private data and adds subtitles. Each episode saves about €600 and two days of editing, and ships in three formats.

Company
Unkillable Companies
Format
Multi-camera video podcast
Running since
October 2026
Two people talking outdoors, an episode of our podcast
An episode edited by the pipeline: camera switches, subtitles and intro included.

Business impact

€600saved per episode, compared with a freelance editor
2 days → 2 hof human editing time per episode
3formats from one recording: long, short and French

Estimated from freelance editing rates and our first episodes, October 2026.

Before and after.

Before How it worked

  • Days of editing per episode, or an editor on retainer
  • Confidential screens cut out or blurred by hand
  • One format per recording

After How it works now

  • A two-hour review instead of two days of editing
  • Private data blurred automatically in the edit
  • Long, short and French versions from the same recording

How it works.

The problem

A good interview podcast is mostly editing: syncing cameras, cutting hesitations, hiding what is confidential, adding subtitles. For three founders, that meant days per episode, or a costly editor.

What we built

A Claude Code skill and a few local tools. We hand over the rushes and say what we want; the pipeline does the mechanical work and stops where a human eye matters. The branded intro is generated in code for each guest.

  1. Sync

    Cameras and microphones aligned automatically.

  2. Select

    We tick the passages to keep, from the transcript.

  3. Cut

    Cuts land in silences; cameras switch calmly.

  4. Finish

    Screen inserted, private data blurred, subtitles burned in.

Built with Claude Code Whisper, run locally FFmpeg Final Cut Pro for the final sound

You can keep adding tools.
Or rebuild how your company works.

Book a discovery call 45 minutes With a founder

Not ready yet? Join the free live on how to create your company brain, every Thursday at 12pm, Paris time.

Sign up for the live