songsee

Generate spectrogram and feature-panel visualizations from audio files.

Updated Apr 8, 2026
One-click install
npx skills add https://github.com/JOHNNYWHITEMIKE/openclaw --skill songsee-johnnywhitemike
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/JOHNNYWHITEMIKE/openclaw/tree/main/openclaw/.openclaw/openclaw/skills/songsee
Command: npx skills add https://github.com/JOHNNYWHITEMIKE/openclaw --skill songsee-johnnywhitemike

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It turns audio files into readable visualizations so you can quickly understand frequency content and extract visual feature panels without manually building plots.

Core Features & Use Cases

  • Spectrogram generation: Produce detailed spectrogram images for audio exploration and analysis.
  • Multi-panel feature visualizations: Render grids of multiple audio descriptors (for example: mel, chroma, MFCC, loudness, tempo-related panels) in one output.
  • Time-slice rendering: Export visuals for a specific time window to focus on events within a track.

Quick Start

Run songsee track.mp3 to generate a spectrogram image from your audio file.

Frequently Asked Questions about songsee

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

FAQPage Schema
How do I generate a spectrogram image from an audio file?

To generate a spectrogram image, run the command `songsee track.mp3` to instantly process your audio file and output a frequency visualization.

Can I visualize multiple audio features like mel, chroma, and MFCC in one image?

Yes, you can render multi-panel feature visualizations that display multiple audio descriptors, including mel, chroma, MFCC, loudness, and tempo, within a single output image.

How do I export a spectrogram for a specific time slice of a track?

To export a time slice, use the visualization selection flags to specify a targeted time window, rendering a focused image of events within that specific audio segment.

What audio visualization formats does the spectrogram export support?

The spectrogram export supports common image formats, specifically allowing you to output your audio visualizations and feature panels as PNG or JPG files.

Do I need the songsee CLI workflow to create audio visualizations?

Yes, generating spectrogram and feature-panel visualizations requires the songsee CLI workflow to process audio descriptors and export the resulting image files.

What is the best way to compare multiple audio descriptors for signal analysis?

The best way to compare audio descriptors is by generating multi-panel feature visualizations, rendering grids of descriptors like loudness and tempo together in one image for signal analysis.