songsee

Generate spectrograms and feature-panel visualizations from audio files.

Updated Mar 22, 2026
One-click install
npx skills add https://github.com/MaxSaiets/myOpenCL --skill songsee-maxsaiets
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/MaxSaiets/myOpenCL/tree/main/openclaw/skills/songsee
Command: npx skills add https://github.com/MaxSaiets/myOpenCL --skill songsee-maxsaiets

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Turning audio into actionable visual insights by generating spectrograms and feature-panel visualizations automatically.

Core Features & Use Cases

  • Generate spectrograms and feature-panel visualizations from audio for quick inspection of spectral content and musical features.
  • Use in research, music analysis, or content creation to compare tracks, monitor audio characteristics, or validate audio processing pipelines.

Quick Start

Run songsee on an audio file to produce the default spectrogram visualization.

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 a CLI?

You can generate an audio spectrogram by running the CLI tool on common formats like WAV and MP3 to produce visual representations for quick spectral analysis.

What is a feature-panel visualization for music analysis?

A feature-panel visualization maps musical features from audio files to enable rapid sonic analysis, allowing you to monitor audio characteristics or compare tracks during research and content creation.

Can I process multiple audio files in batch to create spectrograms?

Yes, the tool supports batch runs for spectrogram creation, allowing you to process multiple audio files at once for streamlined comparison and validation of audio processing pipelines.

Does the tool support audio decoding for formats like MP3 and WAV?

Yes, the tool supports audio decoding natively with an ffmpeg fallback, ensuring it can process common formats like MP3 and WAV for spectrogram and feature-panel generation.

Can I configure the frequency range and windowing for audio visualization?

Yes, you can configure windowing and frequency ranges to customize your spectrogram visualizations, adapting the sonic analysis output to specific research or music analysis requirements.

What is the best way to inspect spectral content across streaming audio contexts?

To inspect spectral content across streaming audio contexts, use this CLI tool which supports streaming contexts alongside single-file processing and batch runs for continuous spectrogram visualization.