songsee

Generate multi-panel audio feature visualizations from audio files using the songsee CLI.

Updated Apr 30, 2026
One-click install
npx skills add https://github.com/photonics-dhl/Hermes --skill songsee-photonics-dhl
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/photonics-dhl/Hermes/tree/main/hermes-home/skills/media/songsee
Command: npx skills add https://github.com/photonics-dhl/Hermes --skill songsee-photonics-dhl

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Generate spectrograms and multi-panel audio feature visualizations from audio files to facilitate quick analysis, debugging, and documentation of audio processing workflows.

Core Features & Use Cases

  • Generate spectrograms and multi-panel visualizations (spectrogram, mel, chroma, hpss, selfsim, loudness, tempogram, mfcc, flux) from input audio.
  • Useful for audio analysis, music production debugging, and visual documentation of processing pipelines.
  • Use Case: Quickly compare different processing steps or track segments by visualizing feature panels side by side.

Quick Start

Run songsee on an audio file to produce the visualization image according to your chosen options.

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 and multi-panel audio visualizations from my tracks?

You can generate audio visualizations by running a CLI tool that renders multi-panel plots of spectrograms, mel, chroma, and MFCCs directly from your input audio files. This approach facilitates quick analysis, production debugging, and visual documentation of audio processing workflows.

What audio features can I visualize for music analysis alongside a spectrogram?

For music analysis, you can visualize spectrograms alongside mel, chroma, MFCCs, loudness, tempogram, flux, HPSS, and self-similarity matrices. These multi-panel plots help you compare different processing steps or track segments side by side.

Do I need Go and ffmpeg to create audio visualizations from unsupported file formats?

You need Go installed to set up the visualization CLI, and you need ffmpeg as an optional dependency to handle unsupported audio formats. This environment setup allows you to process and render visualizations from various input audio files.

Can I specify the output format and visualization types when rendering audio features?

Yes, you can specify output formats and visualization types by using the --viz and --format options in the CLI. This allows you to customize the generated multi-panel plots to include specific audio features like MFCCs or spectrograms for your documentation.

What is the best way to compare different audio processing steps visually?

The best way to compare audio processing steps is to generate multi-panel visualizations of features like spectrograms, mel, and chroma side by side. This visual documentation allows you to quickly analyze track segments and identify differences in your processing pipeline.