songsee

Generate mel spectrogram, chromagram, and MFCC plots from audio files.

779|139|Updated Mar 7, 2026
One-click install
npx skills add https://github.com/taracodlabs/aiden --skill songsee-taracodlabs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/taracodlabs/aiden/tree/main/skills/songsee
Command: npx skills add https://github.com/taracodlabs/aiden --skill songsee-taracodlabs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Visualize audio content to reveal spectral and timbral structure for quick interpretation.

Core Features & Use Cases

  • Generate mel spectrogram, chromagram, and MFCC plots for audio analyses.
  • Compare recordings visually to inspect frequency and timbral differences.
  • Use in music analysis, speech processing, and debugging audio workflows.

Quick Start

Run the analysis on an audio file to generate mel spectrogram, chromagram, and MFCC plots.

Frequently Asked Questions about songsee

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

FAQPage Schema
How do I generate a mel spectrogram for audio analysis?

Generate MFCC plots from audio by extracting spectral features with librosa. This Skill produces PNG visualizations of mel-frequency cepstral coefficients to reveal timbral structure for speech processing and music analysis.

Can I visualize chromagrams to compare different music recordings?

Visualize chromagrams to compare recordings by extracting pitch-class profiles with librosa. This Skill generates PNG plots that highlight frequency and timbral differences between audio files for music analysis workflows.

Does this audio visualization approach require matplotlib and librosa?

This audio visualization approach requires both librosa and matplotlib to function. Librosa extracts spectral features like MFCC and chromagrams, while matplotlib renders the resulting data into PNG plots for analysis.

What is the best way to debug audio using spectral plots?

Debug audio using spectral plots by generating visualizations like mel spectrograms and chromagrams to inspect anomalies. This Skill creates PNG outputs that reveal underlying spectral and timbral structure for quick debugging.

Are the generated audio plots suitable for machine learning workflows?

The generated audio plots are suitable for machine learning workflows as static PNG outputs. They visualize mel spectrograms and MFCC data to help interpret spectral features for data analysis and model debugging.