songsee

Generate spectrograms and multi-panel audio feature visualizations from audio files via CLI.

Updated Mar 26, 2026
One-click install
npx skills add https://github.com/cloudliness/Hermes-Autonomous-AI-Agent-Dialed-In-For-Windows-11 --skill songsee-cloudliness
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/cloudliness/Hermes-Autonomous-AI-Agent-Dialed-In-For-Windows-11/tree/main/skills/media/songsee
Command: npx skills add https://github.com/cloudliness/Hermes-Autonomous-AI-Agent-Dialed-In-For-Windows-11 --skill songsee-cloudliness

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Generate visualizations (spectrograms and multi-panel audio feature plots) from audio files to assist analysis, debugging, documentation, and presentation.

Core Features & Use Cases

  • Generate spectrograms and multi-panel visualizations (mel, chroma, MFCC, tempogram, etc.) from audio files via CLI.
  • Useful for audio analysis, music production debugging, educational demonstrations, and technical documentation.
  • Works with common formats (WAV, MP3) and can leverage optional dependencies (ffmpeg) for broader format support.

Quick Start

Run songsee track.mp3 to produce a multi-panel visualization image showing spectrograms, MFCCs, and chroma features.

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 MP3 file via command line?

Generate a spectrogram from an MP3 file by running a single CLI command to produce a multi-panel visualization image. The skill processes common audio formats like WAV and MP3 directly from the command line.

What audio features can I visualize for music production debugging?

Visualize audio features for music production debugging by generating multi-panel plots of spectrograms, mel, chroma, MFCC, and tempogram data. These visualizations assist in analyzing and identifying issues across audio tracks.

Do I need ffmpeg to visualize WAV and MP3 audio files?

You do not need ffmpeg to visualize WAV and MP3 audio files, as these common formats are supported natively. Ffmpeg is an optional dependency used to enable broader audio format support beyond standard files.

Can I use Go tooling to create multi-panel audio feature plots?

Yes, you can use Go tooling to create multi-panel audio feature plots. The skill relies on Go tooling to execute CLI commands that generate visual documentation from audio data.

What is the best way to document audio analysis results visually?

The best way to document audio analysis results visually is to generate multi-panel images containing spectrograms and feature plots. This creates clear technical documentation for presentations and educational demonstrations.

Are there limitations when generating chroma and MFCC visualizations from unsupported audio formats?

Generating chroma and MFCC visualizations from unsupported audio formats will fail without optional dependencies. Install ffmpeg to process broader audio formats and avoid limitations when visualizing non-standard files.