songsee

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

Updated Sep 1, 2021
One-click install
npx skills add https://github.com/unclehowell/unclehowell --skill songsee-unclehowell
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/unclehowell/unclehowell/tree/main/skills/media/songsee
Command: npx skills add https://github.com/unclehowell/unclehowell --skill songsee-unclehowell

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manually creating detailed spectrograms and audio feature visualizations is time‑consuming and requires specialized tools, hindering quick analysis and documentation of audio content.

Core Features & Use Cases

  • Multi‑panel visualizations: Combine spectrogram, mel, chroma, MFCC, and more into a single image.
  • Customizable output: Adjust size, style, frequency range, and time slices via command‑line flags.
  • Use case: Audio engineers can instantly generate a comprehensive visual report of a track to compare processing stages or debug synthesis issues.

Quick Start

Use the songsee skill to generate a multi‑panel spectrogram image for '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 mp3 file for audio analysis?

To generate a spectrogram from an mp3 file, you can create a multi-panel visualization image that combines spectrogram, mel, chroma, and MFCC features to provide visual insight into frequency, timbre, and rhythm.

What is the best way to visualize MFCC and chroma features for music production?

Visualizing MFCC and chroma features is best achieved by combining them into a single multi-panel image, which allows audio engineers to instantly compare processing stages or debug synthesis issues within a track.

Do I need ffmpeg installed to create audio visualizations?

You need the songsee command-line tool installed via Go to create audio visualizations, and you optionally need ffmpeg installed to extend support for additional audio formats beyond the default.

Can I customize the frequency range and size of an audio spectrogram?

You can customize the spectrogram output by adjusting the size, style, frequency range, and time slices via command-line flags, tailoring the visual report to specific audio analysis or documentation tasks.

What limitations exist when using command-line tools for audio feature visualization?

Limitations include requiring the songsee tool installed via Go and optionally ffmpeg for extended format support, meaning manual command-line execution is necessary rather than using a graphical interface for visualizations.