songsee

Generate audio spectrograms and feature visualizations from input files.

Updated May 5, 2026
One-click install
npx skills add https://github.com/Z43L/zeus-agent --skill songsee-z43l
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/Z43L/zeus-agent/tree/main/skills/media/songsee
Command: npx skills add https://github.com/Z43L/zeus-agent --skill songsee-z43l

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

songsee removes the manual effort of generating visual and analytical views of audio by producing spectrograms and common audio features directly from audio files.

Core Features & Use Cases

  • Spectrogram & multi-view visualizations: Generate standard spectrograms and a grid of feature visualizations (mel, chroma, MFCC, loudness, self-similarity, and more) for quick listening-like analysis.
  • Targeted time-slice analysis: Render only a specific time range using start time and duration to focus on events such as onsets, transitions, or motifs.
  • CLI-first workflow: Works from a file path or standard input to support repeatable pipelines for documentation, debugging, or automated inspection using downstream tools.

Use case example: analyze a song for changes in timbre and rhythm by generating a multi-panel image that combines spectrogram, chroma, loudness, tempogram, and spectral flux for a chosen segment.

Quick Start

Run songsee on your track file to generate a spectrogram image for rapid visual inspection.

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 a music file?

Generate an audio spectrogram by passing a file path or standard input to the CLI. The tool renders a standard spectrogram image for rapid visual inspection of your input audio.

What audio feature visualizations can I extract for music analysis?

Audio feature visualizations include spectrogram, mel, chroma, MFCC, loudness, self-similarity, tempogram, and spectral flux panels. These features are extracted from the input file and rendered as multi-view images.

Can I analyze a specific time slice of an audio track?

Analyze a specific time slice of an audio track by configuring the start time and duration parameters. This focuses the visualization on targeted events such as onsets, transitions, or motifs.

Does this audio feature extraction tool support automated CLI workflows?

This audio feature extraction tool supports automated CLI workflows by accepting input via file paths or standard input. This allows repeatable pipeline integration for documentation, debugging, or automated inspection.

What is the best way to visualize rhythm and timbre changes in a song?

Visualize rhythm and timbre changes by generating a multi-panel image combining spectrogram, chroma, loudness, tempogram, and spectral flux views. This provides a comparative visualization across multiple feature types.

Do I need external dependencies to render MFCC and chroma visualizations?

No external dependencies are required to render MFCC and chroma visualizations. The tool operates standalone to produce configurable output formats and dimensions for your audio analysis parameters.