songsee

Generate spectrograms and extract audio features from command-line audio files.

Updated May 8, 2026
One-click install
npx skills add https://github.com/gztcode/my-skills --skill songsee-gztcode
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/gztcode/my-skills/tree/main/songsee
Command: npx skills add https://github.com/gztcode/my-skills --skill songsee-gztcode

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ffmpeg, and includes scripts (resource) and assets (resource) components.

What problem does it solve?

Manages complex audio analysis by converting audio files into various visualizations for in-depth analysis.

Core Features & Use Cases

  • Spectrogram Generation: Creates visual representations of audio waveforms for frequency analysis.
  • Feature Extraction: Calculates features like Mel-frequency cepstral coefficients (MFCCs) for audio processing tasks.
  • Multi-panel Visualizations: Displays a grid of multiple visualizations for a comprehensive view of the audio data.
  • Use Case: Ideal for musicians or audio engineers looking to debug their tracks, analyze sound for academic research, or produce music with enhanced audio characteristics.

Quick Start

Generate a spectrogram from the audio file 'track.mp3' with the command 'songsee 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 for frequency analysis?

To generate a spectrogram for frequency analysis, pass an audio file like 'track.mp3' to the command-line interface. It processes the audio waveform into a visual representation, allowing you to analyze frequency content directly from your terminal.

What is MFCC extraction and how does it work for audio files?

MFCC extraction calculates Mel-frequency cepstral coefficients from audio files to represent the short-term power spectrum of sound. This feature extraction mechanism processes audio characteristics, making it highly suitable for music production and academic audio analysis tasks.

Do I need ffmpeg to extract audio features from mp3 files?

You optionally need ffmpeg installed to extract audio features and support additional file formats beyond standard inputs. While basic feature extraction may function without it, ffmpeg provides extended file compatibility for comprehensive audio analysis.

Can I visualize multiple audio features in a single panel for music production?

Yes, you can visualize multiple audio features in a single panel for music production. The tool generates multi-panel visualizations, displaying a grid of multiple graphs to provide a comprehensive view of the audio data and its extracted characteristics.

What is the best way to debug audio tracks using a command-line interface?

The best way to debug audio tracks using a command-line interface is by generating spectrograms and extracting features like MFCCs. This process converts audio files into visual representations, enabling sound engineers to pinpoint frequency issues and analyze waveforms effectively.