LoudnessKitv1.0.0

Masters to −16 LUFS for podcasts, −14 for YouTube and music, EBU R 128 and ATSC for broadcast, and the ACX audiobook rules, with true-peak limits.

See what you can make

Made with this SkillMastered audio at each platform's loudness

19 LU apart before, 0.1 LU after

Open full example

What you get

Mastered audio at each platform's loudness

What you can make

  • Masters to −16 LUFS for podcasts, −14 for YouTube and music, EBU R 128 and ATSC for broadcast, and the ACX audiobook rules, with true-peak limits.
  • Measures, trims silence, filters rumble and normalizes in two passes, linear when the peaks allow, then measures the encoded file again.
  • Flags clipping and DC offset, keeps a whole series consistent, and gives waveforms and a listening page with loudness-matched comparison.
Explore delivered files5 groups
  • audio/ with the mastered files
  • waveforms/ before and after
  • index.html to listen, with loudness-matched comparison
  • report.md with every measurement and note
  • manifest.json with the figures measured after encoding

Good fit

Podcasters, video creators, audiobook narrators, course makers and editors delivering audio to a platform.

Know the limits

Sets level, peaks, silence at the ends and rumble; it does not remove background noise, level individual speakers, edit content or upload. Needs FFmpeg.

About this skill

Your agent asks where the audio will be published and LoudnessKit measures every file with FFmpeg: integrated loudness, loudness range and true peak to ITU-R BS.1770, peak and RMS levels, noise floor, DC offset, clipping and silence at both ends. It filters low rumble, trims the silence to half a second, then normalizes in two passes with loudnorm, as a pure gain when the peaks allow, or with ACX's RMS, peak and noise-floor rules for audiobooks. Profiles cover podcasts (−16 LUFS), quieter mono speech (−19), YouTube and music streaming (−14), EBU R 128 and ATSC A/85 broadcast. Each encoded file is measured again, so the report shows what listeners will get, and a series of episodes ends up at the same level. You get the mastered files, before-and-after waveforms, a listening page with loudness-matched comparison and a report with notes on clipping, wide loudness range and noise. Requires Node.js 20+ and FFmpeg.

FROM PACKAGE TO FIRST RESULT

Your first result, with your agent

Choose a starting point, add the content you already have, then let your agent check the setup and create one result.

View example result

Purchase access is required. Unzip the package into the project folder below, or let your agent follow the installation guide. .agents/skills/loudnesskit

Your project name, audience and the content or images you already have are enough to start. Your agent will ask for anything essential that is missing.

3. Let your agent guide the first result

Package location: .agents/skills/loudnesskit

Use LoudnessKit to master all ten episodes of my podcast to −16 LUFS so they sound the same. Start from examples/small-hours.json.

Use a new output folder and preserve existing files. Inspect the actual deliverables (audio/ with the mastered files, waveforms/ before and after, index.html to listen, with loudness-matched comparison), open the visual result and explain failed checks. An incomplete dependency check is not a successful result. Ask before paid services and do not publish automatically.
Before calling it done
  • Dependencies checked before rendering
  • Actual files open and work with your content
  • Editable source saved in a new folder
Made your first result? Share your experience →
Installation options & technical requirements

Start with your agent

Give this request to Claude Code, Codex or Cursor. Your agent can collect the missing details and guide your first result.

Use LoudnessKit to master all ten episodes of my podcast to −16 LUFS so they sound the same. Start from examples/small-hours.json.

Purchase access is required to install the package. Technical commands are available below when you need them.

US$4.99 · MIT licenseNode.js 20+ · FFmpeg · no API keyNo API key or paid provider
  1. 01

    Choose your agent

    These steps use a project folder. Open the project in your agent and run terminal commands from its root.

    Codex directory guide

    Package folder .agents/skills/loudnesskit

  2. 02

    Add the package

    Download and unzip the package into the folder above. Keep all its files together, with SKILL.md directly inside that folder.

    Downloads require a verified account and purchase access. Choose a new folder if this Skill is already installed.

  3. 03

    Run the included sample

    Manual sample commands and technical details

    Read SKILL.md, review the generator and check its runtime requirements before running:

    cd .agents/skills/loudnesskit
    Install FFmpeg
    node scripts/render.mjs --input examples/small-hours.json --output ./mastered
    Your first result

    Listen in index.html with "same loudness" on, read the notes in report.md, then publish the files in audio/.

    Small Hours is fictional; its voices were synthesized for the example. LoudnessKit sets level, peaks, silence at the ends and low rumble; it does not remove noise, level individual speakers or edit content.

    If mastered already exists, change the output to ./mastered-2. Existing files are never overwritten.

    Prefer to ask your agent?

    Use LoudnessKit to master my audio. Ask where it will be published, normalize every file to that platform's loudness and true-peak limit, trim the silence, keep episodes consistent, and show me before-and-after measurements and a listening page.

Reviews

Share your first result

Tried this workflow? Help others decide with an honest review.

Before you choose this Skill

How do I get LoudnessKit?

The listed individual package price is USD 4.99. Premium downloads require a confirmed purchase or active membership. Your agent subscription, model access and external provider credits are separate.

Which agents can use this skill?

This release lists Codex, Claude Code, Cursor as intended installation hosts. Check the package’s dependencies and permissions before running it. These labels do not certify that every workflow has been tested in every agent.

What files can this workflow generate?

The documented 1.0.0 workflow lists: audio/ with the mastered files; waveforms/ before and after; index.html to listen, with loudness-matched comparison; report.md with every measurement and note; manifest.json with the figures measured after encoding. Some files or exports are optional; follow the package’s setup and inspect the delivered result.

What should I check before using the result?

Small Hours is fictional; its voices were synthesized for the example. LoudnessKit sets level, peaks, silence at the ends and low rumble; it does not remove noise, level individual speakers or edit content.

$4.99One-time purchase