songsee

Generate spectrograms and feature panels from audio files via CLI.

Updated Apr 7, 2026
One-click install
npx skills add https://github.com/vut08905/openclaw-app --skill songsee-vut08905
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/vut08905/openclaw-app/tree/main/skills/songsee
Command: npx skills add https://github.com/vut08905/openclaw-app --skill songsee-vut08905

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transform audio into visual representations to analyze frequency content and features without manual plotting.

Core Features & Use Cases

  • Generate spectrograms and feature panels directly from audio files for quick analysis.
  • Create multi-panel visualizations with a single command, supporting various visualization types (spectrogram, mel, chroma, hpss, and more).
  • Works in CLI workflows, enabling per-track and batch processing, and supports time-slice exports.

Quick Start

Run songsee on an audio file to generate a spectrogram and a multi-panel 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?

Generate a spectrogram from an audio file by running a CLI command that decodes native audio formats and outputs visual frequency panels. The tool supports single-file workflows and batch processing of multiple tracks without manual plotting.

Can I create multi-panel audio visualizations like mel and chroma in one command?

Create multi-panel audio visualizations like mel and chroma by using the --viz flag to specify multiple visualization types in a single command. Supported panels include spectrogram, mel, chroma, and hpss for comprehensive audio feature analysis.

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

You need ffmpeg to visualize non-native audio formats, as the tool requires native audio decoding by default but supports optional ffmpeg integration for broader file compatibility. Standard native formats can be processed without additional dependencies.

What is the best way to batch process audio tracks for visual analysis?

Batch process audio tracks for visual analysis by integrating the CLI tool into automated workflows that iterate over multiple audio files. This enables per-track spectrogram and feature panel generation, supporting time-slice exports for granular audio visualization.

Does this audio analysis tool support live stream visualization?

This audio analysis tool supports live stream visualization by generating real-time plots from streams or archives. It processes live audio inputs to output continuous spectrograms and feature panels for dynamic frequency monitoring.

What are the limitations of using CLI-based audio visualization for spectrograms?

Limitations of CLI-based audio visualization include requiring native audio decoding capabilities or optional ffmpeg for non-native formats, and operating within command-line workflows rather than providing interactive graphical interfaces for spectrogram exploration.