Generate audio spectrograms and analyze audio features from the command line.
npx skills add https://github.com/heximao/agents --skill songsee-heximao
Please help me install this Agent Skill. Skill: songsee Source: https://github.com/heximao/agents/tree/main/skill-archive/docker-hermes/media/songsee Command: npx skills add https://github.com/heximao/agents --skill songsee-heximao
This Skill provides a convenient way to generate audio spectrograms and analyze audio features directly from the command line, simplifying the process of audio analysis.
Generate a spectrogram for 'track.mp3' using songsee.
High-intent search queries and answers about installing and using this skill.
You can generate an audio spectrogram using command-line tools by running the songsee script on your audio file, which creates a visual representation of the audio signals directly in your terminal.
You can extract and visualize audio features such as mel, chroma, and MFCC to analyze music signals, providing detailed insights into the audio content for engineering or research purposes.
ffmpeg is an optional dependency for handling additional audio formats, but the core audio feature analysis and spectrogram generation can run using Go for execution without it.
Yes, this CLI tool is suitable for musicians and audio engineers needing to quickly inspect audio content, allowing you to visualize audio signals and extract features directly.
The best way to visualize audio features like MFCC is using a command-line script that processes the audio signal and generates visual representations, simplifying the audio analysis process.
huidgeGenerate multi-panel spectrogram visualizations from audio files.
ghufronbagaskaraGenerate spectrogram, mel, chroma, and MFCC visualizations from audio files.
the-open-agentGenerate spectrograms and feature panels from local MP3 or WAV files.
xjtulycExtract pitch, formants, intensity, spectrograms, and VOT from speech audio.
