DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to strip dead air and set loudness to -14 LUFS with Ffmpeg Skill

An agent removes silent gaps from a recording and sets its loudness to the -14 LUFS target.

  • Content
  • Intermediate
  • 30 minutes
  • From the README
  • Claude Code
  • Cursor
  • Codex

Who it is forA podcaster or presenter whose raw recording has long pauses and uneven volume and who wants a cleaned file before publishing.

The problemFinding and cutting silent gaps by hand is slow, and loudness levels often differ between recordings.

The outcomeAn edited file with silent gaps removed and integrated loudness near -14 LUFS with a true peak of -1 dBTP.

What you need first

  • ffmpeg and ffprobe on your PATH (run `npx ffmpeg-skill doctor` to check)
  • python3 on your PATH (on Windows, `python` or the `py` launcher may be needed instead)
  • Node.js, for `npx ffmpeg-skill`
  • A coding agent such as Claude Code, Cursor or Codex, or any MCP client

Steps

  1. Install the skill with npx ffmpeg-skill and check the machine with npx ffmpeg-skill doctor.
  2. Remove silences above a chosen threshold with python3 $S/silence.py recording.mp4 --threshold -35. (inferred, check the README)
  3. Normalize loudness with python3 $S/loudness.py cleaned.mp4 -I -14 --tp -1. (inferred, check the README)
  4. Verify the output with python3 $S/probe.py cleaned.mp4 --compact before publishing. (inferred, check the README)

Prompt for your agent

Using the ffmpeg-skill repo, remove silences from <recording> with a -35 threshold, then normalize loudness to -14 LUFS with a -1 true peak. Expected output: a cleaned MP4 with the target loudness. Verify the result with probe.py and report the duration change.

Caveat. The -35 dB threshold is only a starting point, so listen to the result and tune it for your recording.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page