skills.rest
JoeyJoziah
JoeyJoziahCOMMUNITY
Explore all skills by this author →
GitHub

songsee

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

Updated Aug 13, 2025
Search Tags:#cli#analysis#visualization#audio#feature-extraction#spectrogram#mfcc
One-click install
npx skills add https://github.com/JoeyJoziah/investment-analysis-platform --skill songsee-joeyjoziah
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/JoeyJoziah/investment-analysis-platform/tree/main/.claude/skills/songsee
Command: npx skills add https://github.com/JoeyJoziah/investment-analysis-platform --skill songsee-joeyjoziah

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

songsee turns audio files into clear visual representations so you can inspect frequency content, timing, and texture without manually building analysis pipelines.

Core Features & Use Cases

  • Spectrogram Generation: Create detailed spectrograms for quick inspection of audio structure.
  • Multi-Panel Feature Views: Render mel, chroma, hpss, self-similarity, loudness, tempogram, mfcc, and flux panels in one pass.
  • Use Case: Use it to compare songs, diagnose audio issues, or create publication-ready visual summaries for sound analysis.

Quick Start

Run songsee on an audio file to generate a spectrogram or multi-panel visualization.

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 or WAV file?▼

To generate a spectrogram from an MP3 or WAV file, run songsee on your audio input to produce detailed visual representations of frequency content and timing for quick structural inspection.

Can I visualize MFCC and chroma features in a single multi-panel view?▼

Yes, you can visualize MFCC and chroma features in a single multi-panel view. Songsee renders mel, chroma, hpss, self-similarity, loudness, tempogram, and flux panels in one pass for comprehensive audio analysis.

What audio formats are supported for feature extraction and visualization?▼

Supported audio formats for feature extraction and visualization include native WAV and MP3 decoding, with ffmpeg-assisted format support available for other file types to ensure broad compatibility.

Can I customize the time slicing and color palette of generated spectrograms?▼

Yes, you can customize generated spectrograms. Songsee produces configurable image outputs with adjustable time slicing, sizing, and palette controls to create publication-ready visual summaries.

What is the best way to compare songs using audio feature visualizations?▼

The best way to compare songs using audio feature visualizations is to generate multi-panel views of spectral, mel, and self-similarity data. This allows you to diagnose audio issues and compare textures side-by-side.

Do I need to install ffmpeg to decode audio files for analysis?▼

You do not strictly need ffmpeg to decode audio files for analysis. Native WAV and MP3 decoding is supported, but ffmpeg-assisted format support is required for decoding other audio file formats.

Related Skills

Explore More Data & Analytics Skills→
dsactivi-2dsactivi-2

songsee

Generate spectrograms and feature-panel visualizations from audio files using the songsee CLI.

Community
Basic
ruiyangruiyiruiyangruiyi

songsee

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

Community
Basic
JKhyroJKhyro

songsee

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

Community
Intermediate
StarlitnightlyStarlitnightly
1.2k

data-viz-plots

Generate publication-quality plots with matplotlib and seaborn.

Community
Advanced