songsee

Generate spectrograms and audio feature visualizations from audio files.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/HugoAlmeidaMoreira/zeus-agent --skill songsee-hugoalmeidamoreira
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/HugoAlmeidaMoreira/zeus-agent/tree/main/skills/media/songsee
Command: npx skills add https://github.com/HugoAlmeidaMoreira/zeus-agent --skill songsee-hugoalmeidamoreira

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Convert audio content into visual representations by generating spectrograms and other feature visualizations from audio files, enabling quick analysis and comparison.

Core Features & Use Cases

  • Generate standard spectrograms, Mel spectra, MFCCs, and chroma visualizations from audio files.
  • Produce multi-panel visualizations to compare different feature sets side-by-side.
  • Use in music analysis, academic research, and media pipelines to inspect spectral content and track changes over time.

Quick Start

Process an audio file to generate the default spectrogram visualization.

Frequently Asked Questions about songsee

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

FAQPage Schema
How do I generate an audio spectrogram from an MP3 or WAV file?

To generate an audio spectrogram, you can process single or batch MP3 and WAV files using the songsee CLI to convert audio content into visual representations for quick analysis.

Can I visualize MFCC, Mel spectra, and chroma features side-by-side for music analysis?

Yes, you can generate multi-panel visualizations to compare MFCC, Mel spectra, and chroma features side-by-side from a single audio file to inspect spectral content and track changes over time.

Do I need ffmpeg installed to process audio formats beyond WAV and MP3?

You do not need ffmpeg installed for WAV and MP3 formats, but it is an optional dependency required to process and visualize other common audio formats within your media pipelines.

What is the best way to batch process audio files for spectral insights in a media pipeline?

The best way to batch process audio files for spectral insights is to apply the songsee CLI directly within your media pipelines, allowing you to automate spectrogram and feature generation across multiple files quickly.

When should I use CLI-based audio feature visualization instead of other data and analytics tools?

You should use CLI-based audio feature visualization when you need to integrate quick spectral insights into automated music analysis workflows or media pipelines without deploying a complex graphical interface.