skills.rest
letta-ai
letta-aiOFFICIAL
Explore all skills by this author →
Website𝕏@letta_aiGitHub

songsee

Generate spectrograms and feature panels from audio files via the songsee CLI.

327|85|Updated Jan 29, 2026
Search Tags:#CLI#visualization#audio#data-analysis#spectrogram#feature-panel
One-click install
npx skills add https://github.com/letta-ai/lettabot --skill songsee
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/letta-ai/lettabot/tree/main/.skills/songsee
Command: npx skills add https://github.com/letta-ai/lettabot --skill songsee

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Generating rich audio visualizations can be time-consuming and technically challenging. songsee automates the creation of spectrograms and feature panels from audio files, enabling quick insight and presentation-ready visuals.

Core Features & Use Cases

  • Spectrogram generation from WAV/MP3 audio files for quick visual inspection.
  • Multi-panel visualizations (mel, chroma, MFCC, hpss, loudness, tempogram, etc.) for in-depth analysis.
  • Time-slice export and batch processing to produce visuals for reports or research.
  • Command-line workflow that integrates into data pipelines or media analysis tasks.

Quick Start

Install songsee (brew) and run a few examples:

  • brew install steipete/tap/songsee
  • songsee track.mp3
  • songsee track.mp3 --viz spectrogram,mel,chroma

Frequently Asked Questions about songsee

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

FAQPage Schema
How do I generate an audio spectrogram from an MP3 or WAV file?▼

You can generate an audio spectrogram by running the songsee command-line tool on your WAV or MP3 file. It natively decodes WAV and MP3 formats to produce spectrograms for quick visual inspection of your audio tracks.

What audio feature panels can I create for in-depth data analysis?▼

You can create multi-panel feature visualizations including mel, chroma, MFCC, hpss, loudness, and tempogram panels. These feature panels enable in-depth audio analysis by displaying multiple audio characteristics simultaneously for comprehensive track comparison.

How does the CLI handle audio formats other than WAV and MP3?▼

The CLI natively decodes WAV and MP3 files, but uses ffmpeg for additional audio formats when available. This allows you to process a wider range of audio files for visualization and data analysis if ffmpeg is installed in your environment.

Can I batch process audio files to create visualizations for research reports?▼

Yes, you can use batch processing and time-slice export to produce visualizations for reports or research. The command-line workflow integrates into data pipelines, allowing you to process multiple tracks and prepare presentation-ready visuals for multimedia research.

Do I need to install any specific dependencies to use the audio visualization CLI?▼

You can install the tool using Homebrew via 'brew install steipete/tap/songsee'. While it natively decodes WAV and MP3, having ffmpeg installed is recommended to handle additional audio formats during spectrogram and feature panel generation.

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
okgoogle13okgoogle13
1

figma-to-component

Generate React component files from Figma Inspect panel details.

Community
Intermediate
Shana-AEShana-AE
2

web-design-guidelines

Review UI code against the latest Web Interface Guidelines.

Community
Intermediate
erichowenserichowens
181

2000s-visualization-expert

Render real-time audio-responsive WebGL visualizations using Butterchurn presets and Web Audio FFT data.

Community
Advanced