skills.rest
BENZEMA216
BENZEMA216COMMUNITY
Explore all skills by this author →
GitHub

music-timbre

Extract MFCCs, spectral metrics, loudness, and dynamic range from audio files.

Updated Aug 27, 2026
Search Tags:#audio-analysis#loudness#stems#timbre#mfcc#spectral-features
One-click install
npx skills add https://github.com/BENZEMA216/dreamina-claude-skills --skill music-timbre
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: music-timbre
Source: https://github.com/BENZEMA216/dreamina-claude-skills/tree/main/.claude/skills/music-timbre
Command: npx skills add https://github.com/BENZEMA216/dreamina-claude-skills --skill music-timbre

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Analyze timbre and spectral features from audio to provide objective metrics for sound quality, comparisons, and design decisions.

Core Features & Use Cases

  • Compute MFCC coefficients and statistical summaries to characterize timbre.
  • Measure spectral centroid, bandwidth, rolloff, and ZCR to describe spectral shape.
  • Estimate loudness (LUFS) and dynamic range for perceptual loudness assessment.
  • Optional source separation to report stems for individual sources when available.

Quick Start

Run the tool on an audio file to obtain timbre and spectral metrics.

Frequently Asked Questions about music-timbre

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
Can I extract individual stems from a mixed audio track for sound design?▼

Loudness analysis is performed by estimating loudness in LUFS alongside dynamic range metrics. This perceptual loudness assessment provides objective data for sound quality evaluation and audio comparisons.

How do I measure LUFS and dynamic range for perceptual loudness assessment?▼

Yes, the Skill performs optional source separation to report stems for individual sources when available. This allows you to isolate and analyze individual audio sources within a mixed track.

Does the tool provide source separation for individual stems?▼

You need to provide a standard audio file as input. The Skill processes this audio input directly to deliver reproducible timbral and spectral metrics without requiring additional environment setup.

Do I need specific audio libraries to extract MFCC means and spectral metrics?▼

No additional dependencies are required. The Skill operates independently to process standard audio inputs and output timbral characteristics, spectral metrics, and loudness measurements for reproducible analysis.

Related Skills

Explore More Design & Creative Skills→
erichowenserichowens
181

2000s-visualization-expert

Render real-time audio-responsive WebGL visualizations using Butterchurn presets and Web Audio FFT data.

Community
Advanced
afel6afel6

songsee

Generate spectrograms and audio feature visualizations from audio files.

Community
Intermediate
bitwize-music-studiobitwize-music-studio
408

mastering-engineer

Analyze WAV tracks for loudness, true peak, and tonal balance to master audio.

Official
Advanced
DarkArty07DarkArty07
3

songsee

Generates spectrograms and multi-feature visualizations from audio files via CLI.

Community
Basic