songsee

Generate spectrograms and mel, chroma, and MFCC visualizations from audio files via CLI.

1|Updated May 10, 2026
One-click install
npx skills add https://github.com/Dq666dinger/my-hermes --skill songsee-dq666dinger
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/Dq666dinger/my-hermes/tree/main/skills/media/songsee
Command: npx skills add https://github.com/Dq666dinger/my-hermes --skill songsee-dq666dinger

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Audio professionals and researchers need quick, scriptable visualizations of audio content without a GUI.

Core Features & Use Cases

  • Generate spectrograms (standard) and multi-panel visualizations of audio features like mel, chroma, and MFCC.
  • CLI-based workflow that integrates into data pipelines, experiments, and research notebooks.
  • Use Case: Analysts can inspect short audio clips or datasets to quickly compare frequency content and timbral changes.

Quick Start

Run songsee on an audio file to generate spectrograms and feature visualizations.

Frequently Asked Questions about songsee

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

FAQPage Schema
How do I generate audio spectrograms from the command line without a GUI?

You can generate audio spectrograms directly from the command line by running a CLI tool on an input audio file to produce standard visualizations of frequency content. This scriptable approach integrates into data pipelines and research notebooks.

Can I visualize MFCC, mel, and chroma audio features in a single workflow?

Yes, you can visualize MFCC, mel, and chroma audio features in a single workflow. The CLI tool generates multi-panel visualizations of these audio features to help analysts inspect timbral changes and compare frequency content across clips.

Does this audio visualization CLI support formats other than WAV and MP3?

Yes, this audio visualization CLI supports non-WAV/MP3 formats by optionally utilizing ffmpeg. This allows analysts to process and generate spectrograms from a wider variety of input audio files within their research workflows.

What is the best way to inspect audio frequency content for music analysis?

The best way to inspect audio frequency content for music analysis is using a CLI-driven method to generate spectrograms and multi-panel feature visualizations. This allows quick, scriptable inspection of timbral changes and frequency distribution.

How do I integrate audio feature extraction into a data pipeline?

You integrate audio feature extraction into a data pipeline by executing CLI commands on audio files to generate spectrograms and feature visualizations. This scriptable workflow automates the inspection of audio datasets within experiments.