songsee

Generate spectrograms and audio feature visualizations from audio files.

Updated Mar 25, 2026
One-click install
npx skills add https://github.com/afel6/scal-ai-pipeline --skill songsee-afel6
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/afel6/scal-ai-pipeline/tree/main/hermes_skills_library/media/songsee
Command: npx skills add https://github.com/afel6/scal-ai-pipeline --skill songsee-afel6

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Produce clear, publication-ready spectrograms and multi-panel audio feature visualizations from raw audio files so engineers and producers can quickly inspect spectral content, temporal patterns, and feature summaries without manual plotting.

Core Features & Use Cases

  • Multi-panel analysis: Render spectrogram, mel, chroma, MFCC, tempogram, flux, self-similarity and more in a single image grid for direct comparison.
  • CLI-first workflow: Integrate into automation or batch pipelines with options for start/duration, window/hop sizes, and output format selection.
  • Use Case: Use visual feature comparisons to debug synthesis artifacts, verify processing chains, or document audio processing steps for reports and reviews.

Quick Start

Run the songsee CLI on an audio file to create a multi-panel visualization image by running songsee track.mp3 -o spectrogram.png

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 for analysis?

Generate spectrograms by running the songsee CLI on an audio file and specifying an output image path. This produces publication-ready visualizations of spectral content for immediate analysis and documentation.

Can I render multiple audio feature visualizations like MFCC and chroma in one image?

Yes, you can render spectrogram, mel, chroma, MFCC, tempogram, flux, and self-similarity views together. The tool produces a single multi-panel image grid for direct visual comparison of these audio features.

Do I need ffmpeg to decode audio files for spectrogram generation?

You need the Go-installed songsee binary for spectrogram generation, while ffmpeg is optional. FFmpeg provides broader audio format decoding support if you are processing files beyond standard formats.

How do I automate batch audio visualization workflows for music production debugging?

Automate batch audio visualization by integrating the CLI-first songsee tool into your pipelines. You can specify start and duration parameters, window and hop sizes, and output formats to inspect synthesis artifacts across multiple files.

What is the best way to document audio processing steps for technical reports?

The best way to document audio processing steps is generating multi-panel visualizations. Create clear, publication-ready spectrogram and feature summary images to verify processing chains and include them directly in your reports.

Does songsee work with tempogram and spectral flux visualizations?

Yes, songsee supports tempogram and spectral flux visualizations alongside mel, chroma, and MFCC views. You can generate these specialized audio feature plots to inspect temporal patterns and verify processing chains.