songsee

Generate spectrograms and feature-panel visualizations from audio files using the songsee CLI.

Updated Feb 4, 2026
One-click install
npx skills add https://github.com/lehalpaul/agents --skill songsee-lehalpaul
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/lehalpaul/agents/tree/main/skills/songsee
Command: npx skills add https://github.com/lehalpaul/agents --skill songsee-lehalpaul

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps users visualize audio data by generating spectrograms and other feature-panel visualizations, making complex audio information more accessible.

Core Features & Use Cases

  • Spectrogram Generation: Create visual representations of audio frequencies over time.
  • Multi-Panel Visualizations: Generate a grid of various audio features like mel, chroma, MFCC, and loudness.
  • Time Slicing: Extract specific segments of audio for detailed analysis.
  • Use Case: Analyze the frequency content of a music track to identify specific instruments or vocal patterns.

Quick Start

Generate a spectrogram for the audio file 'track.mp3'.

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?

To generate an audio spectrogram, you can use a CLI tool that processes your audio file and outputs a visual representation of frequencies over time. This Skill leverages the songsee binary to create detailed spectrograms from supported formats.

What audio formats can I visualize using ffmpeg?

You can visualize various audio formats using ffmpeg. Since this Skill relies on ffmpeg for audio processing, it supports any format ffmpeg can decode to generate spectrograms and feature-panel visualizations.

Can I extract a specific time slice from an audio track for visualization?

Yes, you can extract specific time slices from an audio track for visualization. The Skill offers detailed control over time slicing, allowing you to isolate and analyze specific segments of your audio data.

How do I create multi-panel visualizations for mel, chroma, and MFCC features?

To create multi-panel visualizations for features like mel, chroma, and MFCC, the Skill generates a grid layout. This displays multiple audio feature panels simultaneously, making complex audio information more accessible.

Do I need to install any specific binaries to visualize audio with this Skill?

Yes, you need the songsee binary installed to use this Skill. Additionally, ffmpeg is required to support the various audio formats processed during spectrogram and feature-panel generation.