songsee
Generate spectrograms and feature-panel visualizations from audio with the songsee CLI.
When & Why to Use This Skill
Songsee is a specialized Claude skill designed to transform audio files into detailed spectrograms and multi-panel feature visualizations. By leveraging a powerful CLI, it enables users to generate visual representations of audio characteristics such as pitch (chroma), loudness, and frequency distribution. This tool bridges the gap between audio processing and visual design, making it an essential utility for audio engineers, researchers, and creative professionals who need to analyze or showcase sound data visually.
Use Cases
- 1. Audio Analysis & Quality Control: Generate high-resolution spectrograms to visually inspect audio files for clipping, noise, or frequency inconsistencies.
- 2. Music Production & Research: Create multi-panel visualizations including chroma, mel-spectrograms, and tempograms to analyze the harmonic and rhythmic structure of a track.
- 3. Creative Asset Creation: Produce unique visual content from audio waveforms for use in social media posts, video backgrounds, or digital art projects.
- 4. Educational Demonstrations: Use visual feature panels to teach concepts of digital signal processing (DSP), such as MFCC or harmonic-percussive source separation (HPSS).
| name | songsee |
|---|---|
| description | Generate spectrograms and feature-panel visualizations from audio with the songsee CLI. |
| homepage | https://github.com/steipete/songsee |
| metadata | {"clawdbot":{"emoji":"🌊","requires":{"bins":["songsee"]},"install":[{"id":"brew","kind":"brew","formula":"steipete/tap/songsee","bins":["songsee"],"label":"Install songsee (brew)"}]}} |
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
--vizlist (repeatable or comma-separated)--stylepalette (classic, magma, inferno, viridis, gray)--width/--heightoutput size--window/--hopFFT settings--min-freq/--max-freqfrequency range--start/--durationtime slice--formatjpg|png
Notes
- WAV/MP3 decode native; other formats use ffmpeg if available.
- Multiple
--vizrenders a grid.