Agent Skills
› wukongrobot/wukongbot
› songsee
songsee
GitHub用于从音频文件生成频谱图和特征面板可视化的CLI工具，支持多种可视化类型、样式及时间切片功能。
触发场景
需要生成音频频谱图或特征面板
进行音频信号分析与可视化处理
安装
npx skills add wukongrobot/wukongbot --skill songsee -g -y
SKILL.md
Frontmatter
{
"name": "songsee",
"homepage": "https:\/\/github.com\/steipete\/songsee",
"metadata": {
"moltbot": {
"emoji": "🌊",
"install": [
{
"id": "brew",
"bins": [
"songsee"
],
"kind": "brew",
"label": "Install songsee (brew)",
"formula": "steipete\/tap\/songsee"
}
],
"requires": {
"bins": [
"songsee"
]
}
}
},
"description": "Generate spectrograms and feature-panel visualizations from audio with the songsee CLI."
}
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.
版本历史
- 2a72816 当前 2026-08-20 10:15
