Skill1.3k repo starsupdated today

songsee

Songsee generates spectrograms and audio feature visualizations from audio files via command-line interface. Use it to analyze and visualize audio characteristics like mel-spectrograms, chromagrams, loudness, and temporal features, with flexible output sizing, frequency ranges, time slicing, and multi-panel grid rendering options for music analysis and debugging.

View source Repository: trpc-agent-go

Install in Claude Code

Copy

git clone --depth 1 https://github.com/trpc-group/trpc-agent-go /tmp/songsee && cp -r /tmp/songsee/openclaw/skills/songsee ~/.claude/skills/songsee

Then start a new Claude Code session; the skill loads automatically.

Definition

SKILL.md

# 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.