Generate spectrograms and audio feature visualizations from audio files.
npx skills add https://github.com/jleechanorg/hermes-agent --skill songsee-jleechanorg
Please help me install this Agent Skill. Skill: songsee Source: https://github.com/jleechanorg/hermes-agent/tree/main/skills/media/songsee Command: npx skills add https://github.com/jleechanorg/hermes-agent --skill songsee-jleechanorg
Generate spectrograms and multi-panel audio feature visualizations from audio files.
Generate a spectrogram image from the input file track.mp3 using the songsee CLI.
High-intent search queries and answers about installing and using this skill.
You generate spectrograms and audio feature visualizations by running the songsee CLI on individual tracks or multiple files in a batch workflow, producing multi-panel visual summaries for audio analysis.
For music analysis and speech processing, you can visualize spectrograms, mel spectrograms, chroma, and MFCCs to analyze audio content and generate quick visual summaries.
Yes, you need to install Go to run spectrogram generation locally, specifically by using the command go install github.com/steipete/songsee/cmd/songsee@latest to set up the required songsee CLI environment.
Yes, you can process multiple audio files in a batch workflow for comparative spectrogram analysis, which arranges the output visualizations in a grid layout to compare audio features across tracks.
The best way to extract MFCCs and chroma features for visual audio analysis is using a CLI tool that automates the generation of multi-panel visualizations directly from your source audio files.
huidgeGenerate multi-panel spectrogram visualizations from audio files.
AlvaroBianoGenerate spectrogram, mel, chroma, hpss, mfcc visualizations from audio files to PNG/JPG using songsee CLI.
quiznatGenerate spectrograms and multi-panel audio feature visualizations from audio files.
nelohenriqGenerate spectrograms and audio feature visualizations from audio files.
