songsee

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

Updated Mar 7, 2026
One-click install
npx skills add https://github.com/shalevamin/Tau_agent --skill songsee-shalevamin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/shalevamin/Tau_agent/tree/main/tau-agent-main/skills/songsee
Command: npx skills add https://github.com/shalevamin/Tau_agent --skill songsee-shalevamin

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning raw audio into visual representations like spectrograms and feature panels normally requires writing custom 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 visualizations 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 structure of several recordings. They generate multi-panel feature grids for each track to visually inspect timbre, tempo, and loudness patterns side by side. ## Quick Start Ask the agent to generate a spectrogram of your audio file, for example: create a spectrogram of track.mp3 using songsee and save it as a PNG.

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, --width, --height, and --style.

How to visualize multiple audio features in one image?

Pass a comma-separated list to the --viz flag, for example --viz spectrogram,mel,chroma,hpss,loudness,tempogram,mfcc,flux. Multiple visualizations are rendered together as a grid in a single output image.

What audio formats does songsee support?

WAV and MP3 files are decoded natively by songsee. Other audio formats are supported when ffmpeg is available on the system to handle decoding.

Can I generate a spectrogram of only part of a song?

Yes, use the --start and --duration flags to select a time slice, for example --start 12.5 --duration 8 to visualize an eight-second segment beginning at 12.5 seconds.

How do I install the songsee CLI?

Install songsee on macOS with Homebrew using the formula steipete/tap/songsee. After installation the songsee binary is available on your PATH for direct CLI use.