songsee

Generate spectrograms and feature-panel visualizations from audio files.

1|1|Updated Feb 15, 2026
One-click install
npx skills add https://github.com/yunseo-kim/agent-toolbox --skill songsee-yunseo-kim
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/yunseo-kim/agent-toolbox/tree/main/catalog/skills/songsee
Command: npx skills add https://github.com/yunseo-kim/agent-toolbox --skill songsee-yunseo-kim

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill addresses the need to visually analyze audio data by generating spectrograms and other feature visualizations, making complex audio characteristics understandable.

Core Features & Use Cases

  • Spectrogram Generation: Create detailed spectrograms from audio files.
  • Multi-Feature Visualization: Generate various audio feature panels like Mel, Chroma, MFCC, etc.
  • Time Slicing: Extract specific segments of audio for focused analysis.
  • Use Case: A musician can use this Skill to visualize the frequency content of a track over time to identify specific sonic elements or issues.

Quick Start

Generate a spectrogram visualization for the audio file '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 audio file for frequency analysis?

To generate an audio spectrogram, you provide an audio file like 'track.mp3' to create a detailed visual representation of its frequency content over time. This process helps identify specific sonic elements or issues within the track.

Can I visualize specific audio segments using time slicing?

Yes, time slicing allows you to extract and visualize specific segments of an audio file for focused analysis. This targets exact regions of your audio data, generating detailed spectrograms and feature visualizations for just those selected moments.

What audio feature visualizations can I create besides standard spectrograms?

Besides standard spectrograms, you can generate multi-feature visualizations such as Mel, Chroma, and MFCC panels. These feature visualizations help analyze complex audio characteristics for music information retrieval and signal processing tasks.

Do I need ffmpeg to process non-native audio formats for visualization?

Yes, you need ffmpeg installed to process non-native audio formats for visualization. Native audio formats can be processed directly, but ffmpeg is required to decode and prepare other file types before generating spectrograms and feature panels.

Can I customize FFT settings and frequency ranges for audio spectrogram generation?

Yes, you can customize FFT settings and frequency ranges when generating audio spectrograms. This allows you to adjust the visualization parameters to focus on specific frequency bands and tailor the analysis for your audio processing needs.