Songsee

songsee turns audio files into visual representations: spectrograms, mel frequency plots, chroma features, and several other analysis panels that audio engineers and music researchers actually use. You can render a single visualization or combine up to nine panels in a grid, slice specific time ranges, and pipe from stdin. The CLI feels thoughtfully designed with sensible defaults but plenty of control over FFT windows, frequency ranges, and color palettes. It's the kind of tool that's genuinely useful when debugging audio processing pipelines or just trying to see what's happening in a track beyond waveforms. Native WAV and MP3 support, falls back to ffmpeg for everything else.

skills.sh installs: 2.6K
GitHub stars: 382.8K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add steipete/clawdis --skill songsee --agent claude-code

Installs into .claude/skills of the current project.

Files

songsee

Generate spectrograms + feature panels from audio.

Quick start

Spectrogram: songsee track.mp3
Multi-panel: songsee track.mp3 --viz spectrogram,mel,chroma,hpss,selfsim,loudness,tempogram,mfcc,flux
Time slice: songsee track.mp3 --start 12.5 --duration 8 -o slice.jpg
Stdin: cat track.mp3 | songsee - --format png -o out.png

Common flags