songsee

Generate spectrograms and audio feature charts from audio files via command line.

7|1|Updated Jul 26, 2026
One-click install
npx skills add https://github.com/paxlabs-inc/ion-agent --skill songsee-paxlabs-inc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/paxlabs-inc/ion-agent/tree/main/skills/media/songsee
Command: npx skills add https://github.com/paxlabs-inc/ion-agent --skill songsee-paxlabs-inc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ffmpeg.

What problem does it solve?

This skill addresses the difficulty of manually analyzing audio files by providing a command-line interface to generate visual representations of sound, such as spectrograms and pitch distributions.

Core Features & Use Cases

  • Multi-panel Visualization: Generate complex grids showing mel-spectrograms, chroma, MFCCs, and more in a single image.
  • Audio Analysis: Quickly debug synthesis, compare audio outputs, or document processing pipelines through visual evidence.
  • Use Case: A developer working on a music synthesis project can use this to generate a tempogram and spectral flux chart to verify the timing and onset detection accuracy of their audio output.

Quick Start

Use the songsee skill to generate a multi-panel visualization grid for the audio file track.mp3 by running the command songsee track.mp3 --viz spectrogram,mel,chroma,hpss,selfsim,loudness,tempogram,mfcc,flux.

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 and MFCC charts from an audio file?

To generate an audio spectrogram and MFCC charts, use the command-line tool to process your audio file and output a multi-panel visualization grid. Run a command like songsee track.mp3 --viz spectrogram,mfcc to create the visual representations.

Does the audio visualization CLI require ffmpeg to process mp3 files?

Yes, the audio visualization CLI requires ffmpeg to decode non-native audio formats like mp3. The songsee binary handles native formats and analysis, but ffmpeg is an optional dependency needed for broader audio file format support.

Can I visualize pitch class distribution and harmonic separation for music synthesis debugging?

Yes, you can visualize pitch class distribution and harmonic separation by requesting chroma and hpss visualizations. These audio analysis charts help debug music synthesis by verifying timing and onset detection accuracy in your audio output.

What is the best way to compare audio outputs and document processing pipelines visually?

The best way to compare audio outputs visually is to generate multi-panel visualization grids including mel-spectrograms, spectral flux, and loudness charts. This provides visual evidence to document processing pipelines and compare different audio outputs.

What audio features can I visualize besides a standard spectrogram?

Besides a standard spectrogram, you can visualize mel-spectrograms, chroma, MFCCs, harmonic-percussive source separation, self-similarity, loudness, tempograms, and spectral flux in a single complex grid image.