Generate spectrograms and multi-panel feature visualizations from audio via CLI.
npx skills add https://github.com/majunbao/learn --skill songsee-majunbao
Please help me install this Agent Skill. Skill: songsee Source: https://github.com/majunbao/learn/tree/main/openclaw_tags/openclaw-2026.3.2/skills/songsee Command: npx skills add https://github.com/majunbao/learn --skill songsee-majunbao
Generate spectrograms and feature-panel visualizations from audio with the songsee CLI, enabling quick analysis and reporting.
Process an audio file to generate a spectrogram and feature-panel visualizations using the songsee CLI.
High-intent search queries and answers about installing and using this skill.
You can generate an audio spectrogram by running the songsee CLI in your terminal, which processes the audio data and outputs visual panels for quick analysis and reporting.
You can generate multi-panel audio feature visualizations including mel, chroma, hpss, and mfcc panels, providing comprehensive feature data for music research and speech processing workflows.
Yes, the spectrogram generation supports configurable frequency ranges and styles, allowing you to customize the visual output to suit specific audio analysis or debugging requirements.
Using a CLI-driven audio analysis tool like songsee is an efficient way to analyze audio features in pipelines, as it allows you to quickly generate spectrograms and feature panels for transcripts or reports.
No external dependencies are required to use this audio spectrogram generation capability, as it operates as a standalone CLI tool ready to process audio data and output visualizations.
TitoPrauseeGenerate spectrogram and audio feature visualizations from audio files.
nomad3Generate spectrogram and multi-feature visual panels from audio files.
lengoctuong2005Generate audio feature visualizations like spectrograms from audio files via CLI.
ragnarokhaaConvert audio files into spectrograms and mel-spectrograms using songsee CLI.
