skills.rest
brikkoAI
brikkoAIOFFICIAL
Explore all skills by this author →
WebsiteGitHub

songsee

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

1|Updated May 3, 2026
Search Tags:#cli#feature extraction#audio processing#music production#spectrogram#audio analysis#audio visualization
One-click install
npx skills add https://github.com/brikkoAI/brikko-studio --skill songsee-brikkoai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/brikkoAI/brikko-studio/tree/main/packages/core/skills/songsee
Command: npx skills add https://github.com/brikkoAI/brikko-studio --skill songsee-brikkoai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manually creating audio visualizations for analysis, production, or research requires specialized audio processing knowledge and custom scripting, which is time-consuming and inaccessible to non-technical users.

Core Features & Use Cases

  • Spectrogram Generation: Create standard time-frequency spectrograms from WAV, MP3, and other audio formats (with ffmpeg fallback for unsupported formats).
  • Multi-Panel Feature Visualization: Render grids of audio features including mel spectrograms, chroma, MFCC, loudness, tempogram, and self-similarity matrices for deep audio analysis.
  • Use Case: Music producers can quickly visualize track characteristics to identify sections, or researchers can analyze audio features for machine learning dataset curation without writing custom audio processing code.

Quick Start

Use the songsee skill to generate a multi-panel feature visualization for your audio file 'demo-track.mp3'.

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 MP3 or WAV file?▼

To generate an audio spectrogram from an MP3 or WAV file, you can use this tool to process standard audio formats and output time-frequency visualizations without writing custom scripts.

Can I extract multiple audio features like MFCC and chroma for machine learning datasets?▼

Yes, you can extract audio features like MFCC, chroma, mel spectrograms, and tempogram for machine learning datasets by rendering multi-panel visualizations for deep audio analysis.

What audio formats are supported for audio visualization?▼

The audio visualization tool supports WAV and MP3 formats natively, with an ffmpeg fallback to process and visualize other unsupported audio file formats.

Do I need custom audio processing code to analyze tempograms and self-similarity matrices?▼

No, you do not need custom audio processing code to analyze tempograms and self-similarity matrices; the tool renders these multi-panel feature grids automatically from your audio files.

How do I customize FFT settings and time slicing for audio analysis?▼

You can customize FFT settings and time slicing for audio analysis directly through the command line interface, allowing precise control over the generated spectrogram and feature panel outputs.

Are there limitations when using ffmpeg fallback for unsupported audio formats?▼

When using the ffmpeg fallback for unsupported audio formats, limitations may arise from the underlying ffmpeg decoder's compatibility with specific or highly obscure audio containers.

Related Skills

Explore More Design & Creative Skills→
dsactivi-2dsactivi-2

songsee

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

Community
Basic
quiznatquiznat

songsee

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

Community
Intermediate
dawsonblockdawsonblock

songsee

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

Community
Advanced
nadicodeainadicodeai

songsee

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

Official
Intermediate