Create audio spectrograms and multi-panel visualizations via CLI.

Install

mkdir -p .claude/skills/songsee && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/3425" && unzip -o skill.zip -d .claude/skills/songsee && rm skill.zip

Installs to .claude/skills/songsee

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Generate spectrograms and feature-panel visualizations from audio with the songsee CLI.
87 charsno explicit “when” trigger
Beginner

Key capabilities

  • Generate audio spectrograms
  • Create multi-panel feature visualizations
  • Extract MFCC, chroma, and temporal features
  • Perform time-sliced audio analysis

How it works

The skill uses the songsee CLI to decode audio and render visual representations based on specified visualization flags and FFT settings.

Inputs & outputs

You give it
Audio file path
You get back
Visual image file of audio features

When to use songsee

  • Generate audio spectrogram
  • Visualize mel frequency features
  • Create time-sliced audio analysis

About this skill

songsee

Generate spectrograms + feature panels from audio.

Quick start

  • Spectrogram: songsee track.mp3
  • Multi-panel: songsee track.mp3 --viz spectrogram,mel,chroma,hpss,selfsim,loudness,tempogram,mfcc,flux
  • Time slice: songsee track.mp3 --start 12.5 --duration 8 -o slice.jpg
  • Stdin: cat track.mp3 | songsee - --format png -o out.png

Common flags

  • --viz list (repeatable or comma-separated)
  • --style palette (classic, magma, inferno, viridis, gray)
  • --width / --height output size
  • --window / --hop FFT settings
  • --min-freq / --max-freq frequency range
  • --start / --duration time slice
  • --format jpg|png

Notes

  • WAV/MP3 decode native; other formats use ffmpeg if available.
  • Multiple --viz renders a grid.

When not to use it

  • When processing non-audio file formats without ffmpeg

Prerequisites

songsee CLI installed

Limitations

  • Requires ffmpeg for non-native formats
  • Output limited to jpg or png formats

How it compares

It allows for generating complex multi-panel grids of audio features in a single command compared to manual plotting libraries.

Compared to similar skills

songsee side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
songsee (this skill)12moNo flagsBeginner
data-storytelling472moNo flagsIntermediate
csv-data-summarizer159moReviewBeginner
umap-learn62moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry