songsee

Generate spectrograms and audio feature visualizations from audio files.

Updated Apr 11, 2026
One-click install
npx skills add https://github.com/musical-basics/hermes-build-2 --skill songsee-musical-basics
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/musical-basics/hermes-build-2/tree/main/skills/media/songsee
Command: npx skills add https://github.com/musical-basics/hermes-build-2 --skill songsee-musical-basics

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Turn raw audio into clear visual diagnostics for analysis, music production debugging, and documentation by generating spectrograms and multi-panel audio feature plots from files or streams.

Core Features & Use Cases

  • Spectrogram & Mel Visualizations: Create standard and mel-scaled spectrograms for frequency-domain inspection.
  • Multi-feature Grids: Produce combined panels including chroma, MFCC, tempogram, hpss, self-similarity, loudness, and spectral flux for detailed comparisons and troubleshooting.
  • Flexible CLI Workflow: Support for time-slicing, stdin input, and PNG/JPG output makes this useful for automated pipelines, single-file inspection, or comparing mix/master variants.
  • Use Case: Compare rendered exports from different synth or effect settings to identify spectral masking or transient issues.

Quick Start

Generate a spectrogram and multi-panel audio feature image from track.mp3 by running the songsee CLI and saving the result to spectrogram.png.

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 production debugging?

Generate spectrograms from audio files by running the songsee CLI to produce visual diagnostics. It supports standard and mel-scaled spectrograms for frequency-domain inspection, outputting results directly to PNG or JPG formats.

What audio feature visualizations can I create for spectral analysis?

Audio feature visualizations include multi-panel grids for chroma, MFCC, tempogram, hpss, self-similarity, loudness, and spectral flux. These combined panels allow detailed frequency-domain comparisons and troubleshooting of spectral masking or transient issues.

Can I visualize specific time slices of an audio track using CLI?

Time-sliced inspection is supported directly through the CLI workflow. You can target specific segments of an audio file for detailed visualization, making it useful for comparing mix variants or analyzing isolated sections of a track.

Does audio spectrogram generation work with MP3 files and stdin input?

Yes, the CLI processes MP3 files and accepts stdin input for flexible workflows. Optional ffmpeg decoding is supported to handle various audio formats, making it suitable for both single-file inspection and automated pipelines.

What's the best way to automate audio visualization for documentation?

Automate audio visualization for documentation by integrating the CLI into automated pipelines. It supports stdin input, time-slicing, and PNG or JPG output, enabling consistent generation of spectrograms and feature plots for exported tracks.