songsee

Generate spectrogram and feature-panel visualizations from audio files.

5|Updated Jan 31, 2026
One-click install
npx skills add https://github.com/kcns008/clusterclaw --skill songsee-kcns008
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/kcns008/clusterclaw/tree/main/skills/songsee
Command: npx skills add https://github.com/kcns008/clusterclaw --skill songsee-kcns008

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you inspect audio visually instead of manually guessing what is happening in a track, making it easier to identify tonal content, rhythm, timbre, and changes over time.

Core Features & Use Cases

  • Spectrogram Generation: Create clear visual representations of frequency content across time for quick audio inspection.
  • Feature Panel Visualizations: Render multi-panel outputs such as chroma, MFCC, loudness, tempogram, and related audio features for deeper analysis.
  • Flexible Audio Slicing: Focus on a specific section of a track by choosing a start time and duration, which is useful for debugging a problem segment or comparing passages.
  • Use Case: An engineer can analyze a podcast intro, isolate a noisy section, and export a clean image for review or reporting.

Quick Start

Use the songsee skill to generate a spectrogram and feature panel image for the attached 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 from an audio file for music analysis?

To generate an audio spectrogram, use the songsee CLI to process common audio formats and export a visual frequency-time image. It renders clear spectrogram representations for quick inspection of tonal content and changes over time.

Can I visualize audio features like chroma and MFCC from a music track?

Yes, you can visualize audio features like chroma, MFCC, loudness, and tempogram. The tool renders multi-panel feature visualizations from audio files, enabling deeper inspection of rhythm and timbre alongside the spectrogram.

How do I analyze a specific time slice of an audio file?

You can analyze a specific time slice by specifying a start time and duration in the CLI. This flexible audio slicing focuses the spectrogram and feature panels on a targeted section, useful for debugging problem segments.

Does the visualization tool support ffmpeg decoding and stdin input?

Yes, the visualization tool supports optional ffmpeg decoding and accepts input from files or stdin. This allows configurable visualizations and image export directly within command-line workflows.

What is the best way to export audio feature panels as an image for reporting?

The best way to export audio feature panels as an image is using the songsee CLI. It generates clean multi-panel outputs including chroma and loudness, which can be exported directly for review or reporting.