Neura Market Logo

Songsee

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

Peter Steinberger

@steipete

What This Skill Does

Generates spectrograms and multi-panel feature visualizations from audio files using the songsee CLI. Supports time slicing, custom FFT settings, and various color palettes.

Replaces manual audio analysis workflows by providing a single command to produce publication-ready spectrograms and feature panels (mel, chroma, loudness, MFCC, etc.) without needing separate tools or scripts.

When to Use It

  • Create a spectrogram of an audio file for music analysis or sound design
  • Generate a multi-panel feature visualization (e.g., spectrogram, mel, chroma, loudness) for a research paper or presentation
  • Extract a time-slice spectrogram from a specific segment of a long audio recording
  • Produce a grayscale spectrogram for print publication or accessibility
  • Pipe audio from stdin to generate a spectrogram without saving intermediate files

Install

$ openclaw skills install @steipete/songsee

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.

Top skills in this category

Nano Banana Pro

@steipete

Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.

419106k

AdMapix

@fly0pants

AdMapix raw data layer for ad creatives, apps, rankings, downloads/revenue, and market metadata. Returns structured JSON from the AdMapix API; the calling ag...

296133k

YouTube Watcher

@michaelgathara

Fetch and read transcripts from YouTube videos. Use when you need to summarize a video, answer questions about its content, or extract information from it.

34255k

SuperDesign

@mpociot

Expert frontend design guidelines for creating beautiful, modern UIs. Use when building landing pages, dashboards, or any user interface.

19341k

Video Frames

@steipete

Extract frames or short clips from videos using ffmpeg.

13357k