songsee

Generate spectrograms and feature-panel visualizations from WAV/MP3 audio files.

Updated Apr 7, 2026
One-click install
npx skills add https://github.com/Luzzer/Kraken --skill songsee-luzzer
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/Luzzer/Kraken/tree/main/skills/songsee
Command: npx skills add https://github.com/Luzzer/Kraken --skill songsee-luzzer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Generate spectrograms and feature-panel visualizations from audio with minimal setup, enabling quick visual analysis of audio tracks.

Core Features & Use Cases

  • Spectrogram rendering from audio formats (WAV/MP3) to PNG/JPG for quick inspection.
  • Feature-panel visualizations such as mel, chroma, HPSS, self-similarity, loudness, tempo, MFCC, and flux for in-depth analysis.
  • Use case: researchers and creators can visually inspect a track's texture and timing to inform editing or analysis.

Quick Start

Run songsee on an audio file (for example track.mp3) to generate a spectrogram and a set of feature panels.

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, you can run the songsee binary on your audio track to render and export the visualization directly to PNG or JPG formats for quick visual inspection.

What audio feature visualizations can I extract for music research?

For music research, you can generate feature-panel visualizations including mel, chroma, HPSS, self-similarity, loudness, tempo, MFCC, and flux to visually inspect a track's texture and timing.

Do I need ffmpeg to process audio files for visualization?

You do not strictly need ffmpeg to process audio files for visualization, as WAV and MP3 decoding is handled natively; however, ffmpeg is supported to handle decoding when needed for broader compatibility.

Can I use spectrogram visualization for batch audio reviews and podcast production?

Yes, you can use spectrogram visualization for batch audio reviews and podcast production workflows, as the tool supports both single-track analysis and batch processing to inform editing decisions.

What's the best way to visually analyze audio texture and timing?

The best way to visually analyze audio texture and timing is by generating feature-panel visualizations like mel, chroma, and self-similarity, which provide in-depth graphical representations of your audio track's characteristics.