songsee

Generate spectrogram and feature map visualizations from audio files.

Updated May 4, 2026
One-click install
npx skills add https://github.com/InverterNetwork/hermes-agent --skill songsee-inverternetwork
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/InverterNetwork/hermes-agent/tree/main/skills/media/songsee
Command: npx skills add https://github.com/InverterNetwork/hermes-agent --skill songsee-inverternetwork

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires go, ffmpeg.

What problem does it solve?

This skill solves the difficulty of performing quick, visual audio analysis and feature extraction without needing complex digital audio workstation software.

Core Features & Use Cases

  • Multi-panel Visualization: Generate grids of spectrograms, mel-scaled features, chroma, and more in a single image.
  • Audio Feature Extraction: Compute technical metrics like MFCCs, tempograms, and spectral flux for signal analysis.
  • Use Case: Use this tool to debug audio synthesis outputs or compare the frequency characteristics of different audio samples by generating a side-by-side visual report.

Quick Start

Use the songsee skill to generate a multi-panel visualization grid for the audio file track.mp3 and save the output as a png image.

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 need an audio analysis tool that computes visual representations of audio features. This skill requires ffmpeg for non-native audio format decoding to process mp3 inputs and output visual spectrograms.

What is the best way to visualize mel, chroma, and MFCC features together?

Visualizing mel, chroma, and MFCC features together requires generating a multi-panel visualization grid. This skill computes these audio feature maps and combines them into a single image for side-by-side signal analysis.

Can I compute tempograms and spectral flux for music production debugging?

You can compute tempograms and spectral flux for music production debugging by applying signal processing techniques to audio files. This skill extracts these technical metrics to help debug audio synthesis outputs and compare frequency characteristics.

Do I need ffmpeg to decode audio formats for spectrogram generation?

You need ffmpeg to decode non-native audio formats for spectrogram generation. The core visualization processing relies on a Go binary, but ffmpeg is required as a dependency to handle formats like mp3 that are not natively supported.

How do I extract MFCCs from an audio track without a digital audio workstation?

To extract MFCCs from an audio track without a digital audio workstation, use a command-line interface tool for audio analysis. This skill computes MFCCs and other feature maps directly from audio files, bypassing complex DAW software.

Does this audio analysis tool work with Go and what are its limitations?

This audio analysis tool works with Go by utilizing a dedicated Go binary for its core processing. A limitation is that it requires ffmpeg as an optional dependency to decode non-native audio formats, limiting standalone format support.