songsee

Generate spectrogram and multi-feature visual panels from audio files.

Updated Feb 8, 2026
One-click install
npx skills add https://github.com/nomad3/openclaw-k8s --skill songsee-nomad3
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/nomad3/openclaw-k8s/tree/main/package/skills/songsee
Command: npx skills add https://github.com/nomad3/openclaw-k8s --skill songsee-nomad3

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Quickly turning audio files into useful visual representations so you can inspect sound characteristics without manually setting up analysis tooling.

Core Features & Use Cases

  • Spectrogram generation: Convert an audio track into a visual spectrogram for rapid review of frequency content over time.
  • Feature-panel visualization: Create multi-panel outputs that combine spectrograms with common audio features for tasks like music analysis, audio QA, and exploratory research.
  • Targeted time-slice rendering: Generate visuals for a specific time window to focus on events such as vocals onset, beats, or noise bursts.
  • Use Case: Analyze a short segment of a podcast to visualize when vocal energy changes by producing a time-sliced, multi-feature panel and exporting it as an image.

Quick Start

Run songsee on your audio to generate a spectrogram image and save it as a PNG output file.

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 sound inspection?

To generate a spectrogram from an audio file, this Skill processes common audio formats and outputs a visual spectrogram image. It converts audio tracks into visual frequency representations for rapid review without manual analysis setup.

What is audio feature panel visualization used for in music analysis?

Audio feature panel visualization combines spectrograms with multiple audio features into multi-panel outputs. It is used for music analysis, audio QA, and exploratory research to inspect sound characteristics and frequency content over time.

Can I visualize a specific time slice of an audio track to focus on vocal onsets?

Yes, you can visualize a specific time slice of an audio track to focus on events like vocal onsets, beats, or noise bursts. This Skill generates targeted time-slice visual outputs for focused inspection of specific audio segments.

Do I need the songsee CLI installed to create spectrogram images?

Yes, you need the songsee CLI installed to create spectrogram images. This Skill requires the songsee CLI to generate images from input audio using selectable visualization types and output format settings.

What is the best way to extract frequency content visuals for audio QA?

The best way to extract frequency content visuals for audio QA is generating multi-feature visual panels from audio files. This Skill creates configurable visualization grids combining spectrograms and audio features for rapid sound inspection.

What audio formats are supported for spectrogram generation?

Spectrogram generation supports common audio formats for visual output. This Skill processes standard audio files to produce spectrograms and multi-feature visual panels without requiring specialized audio analysis tooling.