songsee

Generate spectrograms and audio feature visualizations from audio files.

Updated Apr 20, 2026
One-click install
npx skills add https://github.com/matthew-johnson/hermes-agent --skill songsee-matthew-johnson
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/matthew-johnson/hermes-agent/tree/main/skills/media/songsee
Command: npx skills add https://github.com/matthew-johnson/hermes-agent --skill songsee-matthew-johnson

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Audio professionals often need quick, visual insights from audio files, but generating clear spectrograms and feature visualizations can be time-consuming and technically involved.

Core Features & Use Cases

  • Generate standard and multi-panel spectrograms (spectrogram, mel, chroma) and MFCCs from audio inputs.
  • Create multi-channel or grid visualizations for comparative analysis across tracks or datasets.
  • Use cases include music analysis, research on audio content, and debugging signal processing pipelines.

Quick Start

Install Go and the songsee CLI, then 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 and feature visualizations from an audio file?

To generate audio spectrograms, you install the songsee CLI and run it against an audio file path. It processes the input and outputs image files containing the requested spectrograms and feature visualizations.

What audio features can I visualize for signal processing and music analysis?

For music analysis and signal processing, you can visualize standard spectrograms, mel spectrograms, chroma features, and MFCCs. These visualizations help you inspect audio content and debug signal processing pipelines across diverse datasets.

Do I need a Go toolchain to generate mel spectrograms and MFCC visualizations?

Yes, you need a Go toolchain installed to use this workflow. The CLI requires Go to build and run the commands that generate mel spectrograms, chroma features, and MFCC visualizations from your local audio files.

Can I create multi-panel spectrograms for comparative analysis across multiple tracks?

Yes, you can create multi-channel or grid visualizations for comparative analysis across tracks. This allows you to compare spectrograms and audio features side-by-side when researching datasets or debugging audio processing pipelines.

What is the best way to visualize chroma and mel features for audio research?

The best way to visualize chroma and mel features for audio research is using a CLI workflow that outputs multi-panel images. This approach provides quick visual insights into audio content without manual plotting scripts.

Why does my audio spectrogram generation fail when processing diverse datasets?

Audio spectrogram generation fails often due to incorrect input file paths or unsupported audio formats. The CLI includes basic error handling, but ensuring your Go toolchain is properly configured and file paths are valid is required.