songsee

Generate spectrograms and multi-panel feature visualizations from audio files.

1|1|Updated Apr 26, 2026
One-click install
npx skills add https://github.com/BermudaLocals/hermes-agent-lite --skill songsee-bermudalocals
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/BermudaLocals/hermes-agent-lite/tree/main/skills/media/songsee
Command: npx skills add https://github.com/BermudaLocals/hermes-agent-lite --skill songsee-bermudalocals

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Audio professionals and enthusiasts often need quick, repeatable visuals of audio signals for analysis, documentation, or collaboration; manual visualization is time-consuming and error-prone.

Core Features & Use Cases

  • Generate spectrograms and multi-panel audio feature visualizations from audio files (spectrogram, mel, chroma, mfcc, tempogram, etc.).
  • Visualize audio for debugging music production workflows, academic analyses, and teaching materials.
  • Supports CLI-based workflows to produce ready-to-share visuals from WAV/MP3 inputs.

Quick Start

Run songsee on an audio file to generate a multi-panel visualization from the input track.

Frequently Asked Questions about songsee

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

FAQPage Schema
How do I generate spectrograms and audio feature visualizations from a WAV or MP3 file?

Audio feature visualization generates multi-panel displays like spectrograms, mel, chroma, and MFCC plots from sound signals. These visuals help analysts, music producers, and educators debug workflows, analyze academic content, and create teaching materials from audio files.

Do I need ffmpeg to visualize audio formats beyond native WAV and MP3 support?

You need Go tooling installed to build the songsee CLI tool before generating audio visualizations. Optional ffmpeg is required only if you need to process audio formats beyond native WAV and MP3 support, ensuring your input files are decoded properly.

What audio features can I visualize for music production debugging and academic analysis?

You can generate spectrogram, mel, chroma, MFCC, and tempogram visualizations for music production debugging and academic analysis. These multi-panel audio feature visualizations provide quick, repeatable visual references to analyze and document audio signal characteristics.

What is the best way to automate spectrogram generation for multiple audio tracks?

The best way to automate spectrogram generation for multiple audio tracks is using the CLI-based workflow. It processes WAV and MP3 inputs to produce ready-to-share multi-panel visuals, enabling repeatable audio signal documentation and batch analysis without manual visualization errors.