songsee

Generate spectrograms and feature panels from WAV or MP3 audio files using the songsee CLI.

Updated Jan 1, 2026
One-click install
npx skills add https://github.com/hcnimi/clawdis --skill songsee-hcnimi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/hcnimi/clawdis/tree/main/skills/songsee
Command: npx skills add https://github.com/hcnimi/clawdis --skill songsee-hcnimi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Visualize audio content quickly by producing spectrograms and feature panels from audio files, reducing manual plotting and analysis time.

Core Features & Use Cases

  • Generate spectrograms to inspect frequency content and temporal structure of audio tracks.
  • Create multi-panel feature visualizations (e.g., MFCCs, chroma, spectral flux) for music analysis and signal-processing tasks.
  • Use in research, data curation, or QA pipelines to compare tracks and verify audio processing results.

Quick Start

Run songsee on an audio file to generate spectrograms and feature panels.

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?

You generate a spectrogram by running the songsee CLI on an audio file. It processes input formats like WAV and MP3 to produce visual representations of frequency content and temporal structure.

Can I visualize MFCCs and chroma features for music analysis?

Yes, you can visualize MFCCs, chroma, and spectral flux by creating multi-panel feature visualizations. These feature panels support music analysis and signal-processing tasks directly from the audio input.

Do I need to install any binary before generating audio spectrograms?

Yes, generating audio spectrograms requires the songsee binary to be installed and accessible in your environment. The CLI relies on this system-level binary to process audio files and render visualizations.

What audio formats are supported for spectrogram generation?

Spectrogram generation supports WAV and MP3 input formats. The CLI processes these audio files to produce spectrograms and optional visualization panels for audio QA workflows.

What is the best way to compare audio tracks for QA pipelines?

The best way to compare tracks in QA pipelines is generating spectrograms and feature panels. This provides quick visual representations to verify audio processing results and inspect frequency content differences.

Why use a CLI for audio visualization instead of manual plotting?

Using a CLI for audio visualization reduces manual plotting and analysis time. It automates spectrogram and feature panel generation, enabling quick visual inspections for research and data curation workflows.