songsee

Generate audio feature visualizations like spectrograms from audio files via CLI.

5|1|Updated Mar 24, 2026
One-click install
npx skills add https://github.com/lengoctuong2005/Branding-Focused-Skills --skill songsee-lengoctuong2005
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/lengoctuong2005/Branding-Focused-Skills/tree/main/antigravity/skills/hermes-collection/media/songsee
Command: npx skills add https://github.com/lengoctuong2005/Branding-Focused-Skills --skill songsee-lengoctuong2005

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill solves the problem of manually generating audio feature visualizations by automating the process with songsee.

Core Features & Use Cases

  • Automated Audio Feature Extraction: songsee generates various audio feature visualizations such as spectrograms, mel-scaled spectrograms, pitch class distribution, harmonic/percussive separation, and more.
  • CLI-based Execution: songsee can be run from the command line, making it easy to integrate into scripts or automation pipelines.
  • Use Case: For audio engineers, musicians, or anyone analyzing audio files, songsee can save time by automatically generating the necessary visualizations.

Quick Start

Generate a spectrogram for the file 'track.mp3' using songsee.

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 from an audio file using the command line?

You can generate a spectrogram from an audio file using the command line by running songsee. It automates audio feature extraction to produce visualizations like mel-scaled spectrograms directly from your specified audio track.

Can I automate audio visualization generation for music analysis?

Yes, you can automate audio visualization generation for music analysis with songsee. Designed for CLI-based execution, it easily integrates into scripts or automation pipelines to automatically output spectrograms and pitch class distributions.

What types of audio feature visualizations can I create for audio analysis?

For audio analysis, you can create visualizations including spectrograms, mel-scaled spectrograms, pitch class distribution, and harmonic/percussive separation. These features are automatically extracted to help you analyze audio files visually.

Does songsee work well for harmonic and percussive source separation?

Yes, songsee works well for harmonic and percussive source separation by automatically generating visualizations of these separated components. This is suitable for musicians and audio engineers analyzing audio files.

What is the best way to visualize pitch class distribution from a music track?

The best way to visualize pitch class distribution from a music track is using an automated CLI tool like songsee. It processes your audio files to quickly generate the necessary visualizations for music analysis.

Can I integrate audio feature extraction into an automation pipeline?

Yes, you can integrate audio feature extraction into an automation pipeline because songsee supports CLI-based execution. This allows you to automatically generate spectrograms and other audio visualizations within your scripts.