songsee

Generate spectrograms and feature panels from audio files via CLI.

32|9|Updated Feb 12, 2026
One-click install
npx skills add https://github.com/DotNetAge/mindx --skill songsee-dotnetage
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/DotNetAge/mindx/tree/main/skills/songsee
Command: npx skills add https://github.com/DotNetAge/mindx --skill songsee-dotnetage

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Visualizes audio input by producing spectrograms and related visual panels to replace manual audio analysis.

Core Features & Use Cases

  • Visualize frequency spectra from audio files as spectrograms.
  • Generate feature panels (mel, chroma, loudness, MFCC, etc.) for music analysis and research.
  • Use cases include music tagging, audio QA, and educational demonstrations.

Quick Start

Run songsee track.mp3 to generate a spectrogram visualization immediately.

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 a spectrogram, run the command songsee track.mp3 to instantly visualize frequency spectra from your audio files.

Can I visualize mel, chroma, and MFCC features for music analysis?

Yes, you can generate feature panels for mel, chroma, loudness, and MFCC alongside spectrograms to streamline music analysis and research tasks.

Does this audio visualization tool support Windows environments?

No, this spectrogram visualization tool supports darwin and linux environments and requires the songsee binary to execute audio analysis commands.

What is the best way to analyze audio quality for production tracks?

The best way to analyze audio quality is by generating spectrograms and loudness feature panels, which replace manual audio analysis for production and QA tasks.

Can I use command-line flags to customize audio analysis outputs?

Yes, you can use CLI flags such as --viz and file inputs to customize spectrogram visualizations and feature panel generation for your audio analysis workflow.