Generate spectrograms and audio feature visualizations (mel, chroma, MFCC, tempogram, etc.) from audio files via CLI. Useful for audio analysis, music production debugging, and visual documentation.
Real data. Real impact.
Emerging
Developers
Per week
Excellent
Skills give you superpowers. Install in 30 seconds.
Generate spectrograms and multi-panel audio feature visualizations from audio files.
Requires Go:
go install github.com/steipete/songsee/cmd/songsee@latest
Optional:
ffmpeg# Basic spectrogram songsee track.mp3 # Save to specific file songsee track.mp3 -o spectrogram.png # Multi-panel visualization grid songsee track.mp3 --viz spectrogram,mel,chroma,hpss,selfsim,loudness,tempogram,mfcc,flux # Time slice (start at 12.5s, 8s duration) songsee track.mp3 --start 12.5 --duration 8 -o slice.jpg # From stdin cat track.mp3 | songsee - --format png -o out.png
Use
--viz| Type | Description |
|---|---|
| Standard frequency spectrogram |
| Mel-scaled spectrogram |
| Pitch class distribution |
| Harmonic/percussive separation |
| Self-similarity matrix |
| Loudness over time |
| Tempo estimation |
| Mel-frequency cepstral coefficients |
| Spectral flux (onset detection) |
Multiple
--viz| Flag | Description |
|---|---|
| Visualization types (comma-separated) |
| Color palette: |
| Output image dimensions |
| FFT window and hop size |
| Frequency range filter |
| Time slice of the audio |
| Output format: |
| Output file path |
ffmpegvision_analyzeMIT
mkdir -p ~/.hermes/skills/media/songsee && curl -o ~/.hermes/skills/media/songsee/SKILL.md https://raw.githubusercontent.com/NousResearch/hermes-agent/main/skills/media/songsee/SKILL.md
1,500+ AI skills, agents & workflows. Install in 30 seconds. Part of the Torly.ai family.
© 2026 Torly.ai. All rights reserved.