songsee

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

Updated Mar 31, 2026
One-click install
npx skills add https://github.com/quiznat/Hermes_Sapho --skill songsee-quiznat
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/quiznat/Hermes_Sapho/tree/main/.hermes/skills/media/songsee
Command: npx skills add https://github.com/quiznat/Hermes_Sapho --skill songsee-quiznat

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Generate spectrograms and multi-panel audio feature visualizations from audio files to aid analysis and documentation.

Core Features & Use Cases

  • Generate spectrograms, mel spectra, chroma, MFCCs, and tempograms from audio inputs
  • Create multi-panel visualizations for comprehensive analysis and debugging of music or audio production
  • CLI-based tool with optional FFmpeg support for non-native formats

Quick Start

Process a local audio file to produce a visualization image.

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 for acoustic analysis?

You generate a spectrogram by processing a local audio file via a CLI-based visualization tool, which outputs multi-panel images for comprehensive acoustic analysis and visual documentation.

What audio features can I visualize alongside a standard spectrogram?

Alongside a spectrogram, you can visualize mel spectra, chroma, MFCCs, and tempograms. These multi-panel outputs support comparative acoustic analysis across formats and music production debugging.

Do I need FFmpeg to generate MFCC and chroma visualizations from non-native audio formats?

Yes, you need optional FFmpeg support to generate MFCC and chroma visualizations from non-native audio formats. The CLI tool processes native formats directly but relies on FFmpeg for extended compatibility.

Can I use a CLI tool to create multi-panel audio feature visuals for music production debugging?

Yes, you can use a CLI tool to create multi-panel audio feature visuals for music production debugging. It generates combined spectrogram, mel, chroma, MFCC, and tempogram outputs from a single audio input.

What is the best way to perform comparative acoustic analysis across different audio formats?

The best way to perform comparative acoustic analysis across formats is generating standardized multi-panel visualizations. By extracting spectrograms, MFCCs, and chroma from files, you can visually compare acoustic features directly.