songsee

Extract audio features and generate spectrograms from audio files.

1|1|Updated May 9, 2026
One-click install
npx skills add https://github.com/ldzhhxx/Hermes_offline_v2 --skill songsee-ldzhhxx
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/ldzhhxx/Hermes_offline_v2/tree/main/hermes-agent/skills/media/songsee
Command: npx skills add https://github.com/ldzhhxx/Hermes_offline_v2 --skill songsee-ldzhhxx

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires go, ffmpeg, and includes scripts (resource) components.

What problem does it solve?

This Skill solves the problem of generating spectrograms and audio features from audio files, which can be useful for music analysis, audio research, and other audio processing tasks.

Core Features & Use Cases

  • Audio Feature Extraction: Extracts various audio features such as mel, chroma, MFCC, and more.
  • Spectrogram Generation: Creates visual representations of audio files in the form of spectrograms.
  • Use Case: If you're a music researcher looking for a quick way to visualize the audio features of a track, or a developer needing audio data for machine learning models, this Skill can be quite helpful.

Quick Start

Generate a spectrogram of the file 'example.mp3' using the songsee skill.

Frequently Asked Questions about songsee

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract audio features like MFCC and chroma from an audio file?

To extract audio features like MFCC and chroma, you can use this Skill to process audio files and generate structured data for music analysis or machine learning applications. It requires Go to run the extraction scripts.

What is the best way to generate a spectrogram for music analysis?

Generating a spectrogram for music analysis involves creating visual representations of audio frequencies over time. This Skill automates spectrogram generation from your audio tracks to help visualize audio characteristics.

Do I need ffmpeg to process audio files with this spectrogram generator?

You need ffmpeg to process additional audio formats with this spectrogram generator. Go is required for the core functionality, while ffmpeg is an optional dependency to support a wider range of audio file inputs.

Can I use this audio analysis tool for machine learning datasets?

You can use this audio analysis tool for machine learning datasets by extracting audio features such as mel, chroma, and MFCC. It provides the structured audio data needed to train and evaluate machine learning models.

How does spectrogram generation work for audio research?

Spectrogram generation for audio research works by translating audio signals into visual frequency representations. This Skill processes the audio file to output images showing how the frequency spectrum changes over time.

What audio formats are supported for feature extraction?

Feature extraction supports audio formats handled natively by Go, with additional formats supported if ffmpeg is installed. This allows you to process standard audio files for your music research projects.