songsee

Generate spectrogram, mel-scaled, and harmonic feature plots from audio files.

1|Updated Jul 31, 2026
One-click install
npx skills add https://github.com/icyzh/hermes-web --skill songsee-icyzh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/icyzh/hermes-web/tree/main/skills/media/songsee
Command: npx skills add https://github.com/icyzh/hermes-web --skill songsee-icyzh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires go, ffmpeg.

What problem does it solve?

This Skill solves the difficulty of performing quick, visual audio analysis by automating the generation of spectrograms and feature plots directly from audio files.

Core Features & Use Cases

  • Multi-feature Visualization: Generate grids of spectrograms, mel-scaled plots, chroma features, and more in a single command.
  • Time-slice Analysis: Isolate specific segments of audio for detailed inspection.
  • Use Case: Use this tool to debug audio synthesis outputs or compare the harmonic structure of two different music tracks by generating side-by-side visual feature grids.

Quick Start

Use the songsee skill to generate a multi-panel visualization grid for the audio file track.mp3 including spectrogram, mel, and chroma features.

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 visual analysis?

Generate audio spectrograms by running a command-line analysis tool that processes your audio files. This produces multi-panel visual grids containing spectrograms, mel-scaled plots, and chroma features for detailed inspection.

Can I visualize specific time segments of an audio track for debugging synthesis pipelines?

Yes, you can isolate specific time segments of an audio track for detailed inspection. Time-slice analysis allows you to extract and visualize specific audio segments to debug synthesis outputs or compare harmonic structures.

Do I need ffmpeg to process diverse audio formats for mel-scaled plots?

You need ffmpeg as an optional dependency to process diverse audio formats for mel-scaled plots. Go is required for core spectrogram generation, while ffmpeg extends format support for analyzing diverse audio inputs.

What is the best way to compare the harmonic structure of two music tracks?

The best way to compare the harmonic structure of two music tracks is by generating side-by-side visual feature grids. This produces chroma features and spectrograms, allowing direct visual comparison of harmonic differences.

Does spectrogram generation work with Go for signal processing tasks?

Spectrogram generation works with Go for signal processing tasks. The tool requires Go to automate visual representations, supporting command-line audio analysis for music production and signal processing workflows.