Generate spectrograms and multi-feature panels from audio files via CLI.
npx skills add https://github.com/MOODMNKY-LLC/mnky-atlas --skill songsee-moodmnky-llc
Please help me install this Agent Skill. Skill: songsee Source: https://github.com/MOODMNKY-LLC/mnky-atlas/tree/main/skills/songsee Command: npx skills add https://github.com/MOODMNKY-LLC/mnky-atlas --skill songsee-moodmnky-llc
Audio analysis typically requires specialized tools to convert raw sound files into visual representations of frequency and feature data, a process that is time-consuming and inaccessible without dedicated software. This skill automates that workflow using the songsee CLI, eliminating manual setup and tooling overhead.
Use the songsee skill to generate a full multi-panel feature visualization from your audio file 'track.mp3'.
High-intent search queries and answers about installing and using this skill.
Generate spectrograms by processing raw audio files like WAV and MP3 through the songsee CLI, which automates frequency visualization without manual setup. It outputs standard frequency spectrograms and supports additional formats via ffmpeg.
Visualize multiple audio features in one view by rendering a multi-feature panel grid. This generates a single customizable output displaying mel spectrograms, chroma vectors, MFCCs, and loudness simultaneously for comprehensive music analysis.
Extract and visualize specific time slices from long audio files for targeted inspection. Time-sliced analysis allows audio engineers and sound designers to isolate and visualize particular sections of a track without processing the entire file.
Supported audio formats for visualization include standard WAV and MP3 files. Additional audio formats are supported through ffmpeg integration, allowing flexible audio processing across various input types for spectrogram generation.
Audio analysis no longer requires specialized software to create spectrograms. The songsee CLI automates the workflow, eliminating manual setup and tooling overhead to instantly convert raw sound files into visual frequency representations.
FFT parameters are fully configurable for spectrogram generation. The audio visualization process supports customizable FFT and visualization parameters, allowing precise control over frequency analysis output tailored to specific audio engineering workflows.
TitoPrauseeGenerate spectrogram and audio feature visualizations from audio files.
samlaggzGenerate spectrograms and multi-panel audio feature visualizations from audio files via CLI.
agentic-inGenerate spectrograms and multi-panel audio feature visualizations from audio files.
Z43LGenerate audio spectrograms and feature visualizations from input files.
