songsee

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

Updated Apr 16, 2026
One-click install
npx skills add https://github.com/jacardl/New-Radar --skill songsee-jacardl
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/jacardl/New-Radar/tree/main/backend/frameworks/hermes-agent/skills/media/songsee
Command: npx skills add https://github.com/jacardl/New-Radar --skill songsee-jacardl

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Generate spectrograms and multi-panel audio feature visualizations from audio files to aid analysis, music production debugging, and visual documentation.

Core Features & Use Cases

  • Generate spectrograms (mel, chroma, MFCC, tempogram, etc.) and multi-panel visualizations from common audio formats.
  • Save outputs as image files for reports, dashboards, and tutorials.
  • Use the CLI to reproduce visual analyses for music production, podcasting, or research workflows.

Quick Start

Run songsee on an audio file to generate spectrograms and multi-panel audio feature visualizations.

Frequently Asked Questions about songsee

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

FAQPage Schema
How do I generate a mel-spectrogram from an audio file for music production debugging?

Yes, you can visualize MFCC and chroma features by running the songsee CLI on your audio file. The tool generates multi-panel visualizations of these audio characteristics and saves them as image files for research or podcasting workflows.

Do I need ffmpeg to visualize audio spectrograms in non-native formats?

You need Go tooling and the songsee command installed to generate audio feature visualizations. These prerequisites enable the CLI to process input audio files and output multi-panel spectrogram images for your analysis workflows.

What's the best way to create multi-panel audio feature visualizations for a report?

Audio spectrogram visualization with this CLI is limited to generating static image files from input audio. It requires Go tooling and the songsee command to be installed, and relies on optional ffmpeg for handling non-native audio formats.

Can I generate tempogram visualizations from audio files using a command line tool?

Yes, you can generate tempogram visualizations alongside mel, chroma, and MFCC spectrograms using the songsee command line tool. It processes your input audio files and outputs multi-panel images suitable for audio analysis.

How do I save audio feature visualizations as image files for tutorials?

Save audio feature visualizations as image files by running the songsee CLI on your audio input. The tool generates spectrograms and multi-panel feature plots, providing static visual outputs suitable for tutorials and documentation.