Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

songsee · nousresearch — Claude Code skill: audio spectrograms and feature analysis

Generates spectrograms and multi-panel audio feature visualizations (mel, chroma, MFCC) via CLI. Useful for analyzing sound, comparing audio outputs, or documenting processing pipelines.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add NousResearch/hermes-agent --skill songsee -a claude-code
Open on GitHub

What songsee does

songsee takes an MP3 or WAV file and renders a spectrogram—or stacks multiple panels: mel-scaled spectrogram, pitch class distribution, harmonic/percussive separation, self-similarity matrix, loudness, tempogram, MFCC, and spectral flux. Each visualization type can run alone or combined into a single grid.

Requires Go: go install github.com/steipete/songsee/cmd/songsee@latest. For formats beyond WAV and MP3, ffmpeg is needed. You control the color palette (classic, magma, inferno, viridis, gray), dimensions, frequency range, and time slices via command-line flags.

Visualizations can be analyzed automatically with vision_analyze or inspected by eye. Handy for debugging audio synthesis, comparing model outputs, or documenting audio processing workflows.

What it helps with

  • Generate a spectrogram from an MP3 and save it as PNG
  • Visualize multiple audio features in one grid (mel, chroma, MFCC)
  • Extract and visualize a time slice of an audio file
  • Compare spectral characteristics of different audio outputs
  • Customize color scheme and dimensions for visualization

Example prompts for the agent

  • Generate a spectrogram from this MP3 and save it as PNG
  • Show mel spectrogram, chroma, and MFCC in a single visualization
  • Draw a spectrogram from 12.5 seconds for 8 seconds duration

How to install songsee

1Skills CLI (Vercel)

npx skills add NousResearch/hermes-agent --skill songsee -a claude-code

2Manually: put the files in place

~/.claude/skills/songsee/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/songsee/

From the same set42

The whole set →
dogfood Teknium (teknium1), Hermes Agent A skill for exploratory QA of a web app: it walks the pages, captures console errors and screenshots, then writes a bug report. Claude Code CX Codex Cursor +1 6,400installs humanizer Siqi Chen (@blader, https://github.com/blader/humanizer), ported by Hermes Agent This skill removes common AI writing patterns and gives drafts a more natural voice. Use it for docs, posts, emails, and other text. Claude Code CX Codex Cursor +1 1,300installs popular-web-designs Hermes Agent + Teknium (design systems sourced from VoltAgent/awesome-design-md) 54 real-world design systems (Stripe, Linear, Vercel, Claude) with CSS tokens, typography, and components for building pages styled after known brands. Claude Code CX Codex Cursor +1 914installs powerpoint Nous Research Creates, reads, and edits .pptx presentations with python-pptx. Use it for slide decks, extracting presentation content, and template-based updates. Claude Code CX Codex Cursor +1 751installs claude-design BadTechBandit Skill for building HTML artifacts — landing pages, prototypes, decks — in Claude Code, Codex and Cursor. Reads project context and produces a self-contained file with markup and styles. Claude Code CX Codex Cursor +1 645installs llm-wiki Hermes Agent A skill for building a persistent knowledge base from interlinked markdown files. The agent summarizes sources, cross-references pages, and maintains consistency while you curate and direct the analysis. Claude Code CX Codex Cursor +1 603installs yuanbao Teknium (teknium1), Hermes Agent Connects agents to Yuanbao groups to query members, send mentions using @nickname, and deliver direct messages with attachments. Claude Code CX Codex Cursor +1 564installs songwriting-and-ai-music Teknium (teknium1), Hermes Agent Provides songwriting structures, prosody techniques, and Suno AI prompt formulas that rely on sound details rather than artist names. Claude Code CX Codex Cursor +1 563installs

Other versions of songsee

songsee openclaw Turns an audio file into a spectrogram or a feature panel with mel, chroma, MFCC and more. Useful when you want to see a track instead of just hearing it. Claude Code CX Codex Cursor +1 5,100installs

Similar

omni-cache cheaper-inference Skill for viewing LLM cache statistics, clearing entries, configuring TTL policies, and controlling semantic-similarity caching thresholds. Use it to optimize cache performance and monitor cache state. Claude Code CX Codex Cursor +1 961installs market-segments phuryn Skill to identify and analyze 3–5 customer segments: demographics, jobs-to-be-done, pain points, and product fit. Use it to understand who to target and why. Claude Code CX Codex Cursor +1 2,800installs news-aggregator-skill cclank The skill pulls fresh posts from Hacker News, GitHub, arXiv, Hugging Face Papers, BBC, Reuters and about forty other sources, plus user OPML feeds, and turns them into one report. Claude Code CX Codex Cursor +1 6,000installs cli-batches cheaper-inference Submit and monitor batch inference jobs from the CLI using OmniRoute. Upload input files, inspect batch status, and retrieve results for CI/CD pipelines. Claude Code CX Codex Cursor +1 951installs omni-proxies cheaper-inference Configures HTTP, HTTPS and SOCKS proxies for upstream provider requests, with per-provider or global rules, connectivity checks and rotation. Claude Code CX Codex Cursor +1 947installs scientific-schematics K-Dense-AI Creates PNG drafts of scientific diagrams and runs a separate quality review. Use it for neural network architectures, flowcharts, system diagrams, and biological pathways. Claude Code CX Codex Cursor +1 2,200installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs writing-for-agents Matt Pocock Guidance for writing skills and agent-facing documents. Use it when editing AGENTS.md, CLAUDE.md, or reference files reached from them. Claude Code 466,719installs

Questions about songsee

How do I install songsee in Claude Code?

Run npx skills add NousResearch/hermes-agent --skill songsee -a claude-code, then check ~/.claude/skills/songsee/SKILL.md.

What does songsee do?

It generates spectrograms and multi-panel visualizations of audio features (mel, chroma, MFCC, loudness, tempogram, and more) from MP3 or WAV files via the command line.

Which audio formats does songsee support?

WAV and MP3 natively. Other formats require ffmpeg.

Source text

SKILL.md · MIT 
---
name: songsee
description: "Audio spectrograms/features (mel, chroma, MFCC) via CLI."
version: 1.0.0
author: community
license: MIT
platforms: [linux, macos, windows]
metadata:
  hermes:
    tags: [Audio, Visualization, Spectrogram, Music, Analysis]
    homepage: https://github.com/steipete/songsee
prerequisites:
  commands: [songsee]
---

# songsee

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

## Prerequisites

Requires [Go](https://go.dev/doc/install):
```bash
go install github.com/steipete/songsee/cmd/songsee@latest
```

Optional: `ffmpeg` for formats beyond WAV/MP3.

## Quick Start

```bash
# Basic spectrogram
songsee track.mp3

# Save to specific file
songsee track.mp3 -o spectrogram.png

# Multi-panel visualization grid
songsee track.mp3 --viz spectrogram,mel,chroma,hpss,selfsim,loudness,tempogram,mfcc,flux

# Time slice (start at 12.5s, 8s duration)
songsee track.mp3 --start 12.5 --duration 8 -o slice.jpg

# From stdin
cat track.mp3 | songsee - --format png -o out.png
```

## Visualization Types

Use `--viz` with comma-separated values:

| Type | Description |
|------|-------------|
| `spectrogram` | Standard frequency spectrogram |
| `mel` | Mel-scaled spectrogram |
| `chroma` | Pitch class distribution |
| `hpss` | Harmonic/percussive separation |
| `selfsim` | Self-similarity matrix |
| `loudness` | Loudness over time |
| `tempogram` | Tempo estimation |
| `mfcc` | Mel-frequency cepstral coefficients |
| `flux` | Spectral flux (onset detection) |

Multiple `--viz` types render as a grid in a single image.

## Common Flags

| Flag | Description |
|------|-------------|
| `--viz` | Visualization types (comma-separated) |
| `--style` | Color palette: `classic`, `magma`, `inferno`, `viridis`, `gray` |
| `--width` / `--height` | Output image dimensions |
| `--window` / `--hop` | FFT window and hop size |
| `--min-freq` / `--max-freq` | Frequency range filter |
| `--start` / `--duration` | Time slice of the audio |
| `--format` | Output format: `jpg` or `png` |
| `-o` | Output file path |

## Notes

- WAV and MP3 are decoded natively; other formats require `ffmpeg`
- Output images can be inspected with `vision_analyze` for automated audio analysis
- Useful for comparing audio outputs, debugging synthesis, or documenting audio processing pipelines

© community · MIT · NousResearch/hermes-agent

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor