songsee

Generate spectrograms and multi-panel audio feature visualizations from WAV/MP3 files.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/Aevonix/colony-ai --skill songsee-aevonix
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/Aevonix/colony-ai/tree/main/skills/media/songsee
Command: npx skills add https://github.com/Aevonix/colony-ai --skill songsee-aevonix

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Generate spectrograms and multi-panel audio feature visualizations from audio files to accelerate analysis, debugging, and documentation of audio workflows.

Core Features & Use Cases

  • Spectrograms & Visualizations: Generate standard spectrograms, mel, chroma, MFCC, tempogram, and related plots from input audio.
  • Multi-panel Grids: Create grid visualizations combining multiple feature types for quick comparisons.
  • Use Case: Analyze a track to compare pitch content, tempo, and timbre, or document processing pipelines for a release.

Quick Start

Visualize audio by generating a spectrogram from input 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?

Generating a spectrogram from an audio file involves processing WAV or MP3 inputs to visualize frequency content over time. This requires a Go toolchain and the songsee command to execute the visualization workflow.

What audio features can I visualize for music production debugging?

For music production debugging, you can visualize audio features such as mel, chroma, MFCC, tempogram, loudness, and flux. Generating multi-panel grids of these features helps compare pitch content, tempo, and timbre during track analysis.

Do I need ffmpeg to visualize MP3 audio files?

You need ffmpeg only as an optional dependency to process additional audio formats beyond native support. The core visualization functionality relies on a Go toolchain and the songsee command to handle WAV and MP3 inputs.

Can I create multi-panel grids comparing different audio features?

Yes, you can create multi-panel grids combining multiple feature types like spectrogram, chroma, and MFCC for quick visual comparisons. This allows you to analyze pitch content, tempo, and timbre within a single consolidated visualization output.

What is the best way to document an audio processing pipeline for a release?

The best way to document an audio processing pipeline for a release is to generate multi-panel audio feature visualizations from your files. Visualizing spectrograms, chroma, and loudness provides clear visual documentation of the track's processing characteristics.