songsee

Generate high-resolution spectrograms and multi-panel audio feature visualizations from audio files.

Updated Mar 13, 2026
One-click install
npx skills add https://github.com/Yogi-076/Vajrascan.on --skill songsee-yogi-076
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/Yogi-076/Vajrascan.on/tree/main/moltbot/skills/songsee
Command: npx skills add https://github.com/Yogi-076/Vajrascan.on --skill songsee-yogi-076

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Quickly produce visual, shareable representations of audio so you can inspect frequency content, temporal features, and derived audio descriptors without manual signal processing.

Core Features & Use Cases

  • Spectrogram generation: Create high-resolution spectrogram images from local audio files.
  • Multi-panel feature visualization: Produce combined visual panels including mel, chroma, hpss, self-similarity, loudness, tempogram, mfcc, and flux.
  • Flexible input and slicing: Support for time-sliced exports and piped stdin input; useful for music analysis, audio debugging, and dataset previewing.

Quick Start

Generate a spectrogram image of track.mp3 and save the result as out.png using the songsee CLI.

Frequently Asked Questions about songsee

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate a spectrogram from an audio file?

To generate a spectrogram, run the songsee CLI on a local audio file to create a high-resolution frequency visualization image, saving the output to formats like PNG. It natively decodes audio and falls back to ffmpeg for unsupported formats.

What is multi-panel audio feature visualization for music analysis?

Multi-panel audio feature visualization generates combined image panels displaying mel, chroma, hpss, self-similarity, loudness, tempogram, mfcc, and flux. This extracts derived audio descriptors to inspect temporal and frequency features without manual signal processing.

Can I visualize piped audio streams or time-sliced excerpts?

Yes, you can visualize piped stdin audio streams and time-sliced excerpts. The songsee CLI supports flexible input and slicing, allowing you to generate visual feature panels for specific track segments or streamed audio data.

Does songsee work with ffmpeg for non-native audio decodes?

Yes, songsee works with ffmpeg to handle non-native audio decodes. When the CLI encounters an unsupported audio format, it automatically falls back to ffmpeg to process the raw audio file for visualization generation.

What audio features can I extract for dataset previewing and debugging?

You can extract mel, chroma, hpss, self-similarity, loudness, tempogram, mfcc, and flux features. These derived audio descriptors are rendered as visual panels, making the tool useful for music analysis, audio debugging, and dataset previewing.