mcpField
S
songsee

songsee

github.com/openclawCreative & media393.3k5.1k installsUpdated today
Repository

About songsee

songsee is a command-line skill that creates spectrograms and audio feature panels from audio files. It supports time slices, configurable visualizations, and grid output for multiple views.

Key features

  1. 01Render spectrograms and audio feature panels
  2. 02Choose multiple visualization types
  3. 03Select a time range
  4. 04Configure palette, size, and frequency range
  5. 05Read audio from stdin

Use cases

  1. 01Inspect the spectral content of a track
  2. 02Compare several audio visualizations in one image
  3. 03Render a selected portion of a recording
  4. 04Create a visualization from piped audio

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/openclaw/openclaw --skill songsee

After installing, type/songseein Claude Code to confirm it loaded.

Details

From the project README

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

  • --viz list (repeatable or comma-separated)
  • --style palette (classic, magma, inferno, viridis, gray)
  • --width / --height output size
  • --window / --hop FFT settings
  • --min-freq / --max-freq frequency range
  • --start / --duration time slice
  • --format jpg|png

Notes

  • WAV/MP3 decode native; other formats use ffmpeg if available.
  • Multiple --viz renders a grid.

Comments

Markdown supported