songsee

Generate spectrograms and audio feature-panel visualizations from audio files with the songsee CLI.

Updated Mar 30, 2026
One-click install
npx skills add https://github.com/srgaba/open-claw --skill songsee-srgaba
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/srgaba/open-claw/tree/main/project/skills/songsee
Command: npx skills add https://github.com/srgaba/open-claw --skill songsee-srgaba

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning raw audio into visual representations like spectrograms and feature panels normally requires writing signal-processing code. This Skill wraps the songsee CLI so you can produce publication-ready audio visualizations with a single command. ## Core Features & Use Cases - Spectrogram Generation: Render a spectrogram from any audio file with one command. - Multi-Panel Feature Grids: Combine mel, chroma, HPSS, self-similarity, loudness, tempogram, MFCC, and flux views into a single grid image. - Flexible Output Control: Adjust palette, dimensions, FFT window/hop, frequency range, time slices, and JPG/PNG output format. - Use Case: A music researcher wants to compare the spectral content of a chorus section across tracks. They render an 8-second time slice of each track as a mel spectrogram with the magma palette for side-by-side analysis. ## Quick Start Use the songsee skill to generate a spectrogram of my track.mp3 file and save it as a PNG image.

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?

Run songsee followed by the audio file path, such as songsee track.mp3, to produce a spectrogram image. You can control the output with flags like --format png, --width, --height, and --style for the color palette.

How to visualize multiple audio features in one image?

Pass a comma-separated list to the --viz flag, for example --viz spectrogram,mel,chroma,tempogram. songsee renders each selected feature as a panel in a single grid image.

What audio formats does songsee support?

songsee decodes WAV and MP3 files natively. Other audio formats are supported when ffmpeg is available on the system, which songsee uses as a fallback decoder.

Can I render only a specific section of a song?

Yes, use the --start and --duration flags to select a time slice in seconds, for example --start 12.5 --duration 8. The visualization is rendered only for that portion of the audio.

How do I install the songsee CLI?

Install songsee via Homebrew with the steipete/tap/songsee formula. The songsee binary must be present on your system before the Skill can generate visualizations.