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

songsee · openclaw — Claude skill: audio spectrograms from the CLI

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.

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

What songsee does

The skill wires the songsee CLI into your agent. A single songsee track.mp3 renders a spectrogram; --viz builds a grid of panels — spectrogram, mel, chroma, hpss, selfsim, loudness, tempogram, mfcc, flux. Pass the list comma-separated or repeat the flag.

Most rendering knobs are exposed: palette via --style (classic, magma, inferno, viridis, gray), output size with --width and --height, FFT settings --window and --hop, frequency bounds --min-freq and --max-freq. You can slice a section with --start 12.5 --duration 8. Output is jpg or png.

WAV and MP3 decode natively; anything else needs ffmpeg installed. Stdin works too, so you can pipe audio in and get a png out. The CLI itself comes from the brew formula steipete/tap/songsee. Worth installing if you already poke at audio and want a picture fast. If you only need one-off visuals in a GUI editor, skip it.

What it helps with

  • render a spectrogram from an mp3 without leaving the terminal
  • compare mel, chroma and MFCC on one track in a single grid
  • cut a time slice of a recording and save it as an image
  • pipe audio through stdin and get a png back
  • set a custom frequency range and output dimensions

Example prompts for the agent

  • Generate a spectrogram for track.mp3
  • Build a panel with spectrogram, mel, chroma and mfcc, save it as panel.png
  • Take the slice starting at 12.5 seconds for 8 seconds and write it to slice.jpg

How to install songsee

1Skills CLI (Vercel)

npx skills add openclaw/openclaw --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 set48

The whole set →
summarize openclaw Runs a CLI tool to summarize or transcribe web articles, YouTube videos, podcasts, and local PDF documents directly within your AI assistant. Claude Code CX Codex Cursor +1 26,900installs weather openclaw This skill fetches current conditions and forecasts for a city, region, airport code, or coordinates. Use it to check rain and temperature or plan a trip. Claude Code CX Codex Cursor +1 9,300installs gog openclaw Guides an agent using the gog CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs. Use it when Google Workspace tasks need to run from a terminal. Claude Code CX Codex Cursor +1 8,500installs tmux openclaw Lets an agent work with live tmux sessions: read pane output, send keys and text, wait for a prompt line to show up. Claude Code CX Codex Cursor +1 8,400installs openai-whisper openclaw This skill lets your agent call the Whisper CLI to transcribe audio on your own machine. No API key needed. Claude Code CX Codex Cursor +1 7,100installs nano-pdf openclaw Edit PDF pages with plain text instructions through the nano-pdf CLI. Useful when you need to fix a typo or swap a heading without leaving your terminal. Claude Code CX Codex Cursor +1 7,100installs skill-creator openclaw A skill for writing, repairing and reviewing other skills. It splits behaviour into branches, sets the frontmatter and sorts resources into folders. Useful once your skill folder gets crowded. Claude Code CX Codex Cursor +1 6,700installs coding-agent openclaw This skill sends large coding tasks to Codex, Claude Code, or OpenCode as background workers. Use it for refactors, PR reviews, and issue-to-PR work. Claude Code CX Codex Cursor +1 6,500installs

Other versions of songsee

songsee community Generates spectrograms and multi-panel audio feature visualizations (mel, chroma, MFCC) via CLI. Useful for analyzing sound, comparing audio outputs, or documenting processing pipelines. Claude Code CX Codex Cursor +1 369installs

Similar

nature-figure Yuan1z0825 A skill that builds, revises and audits scientific figures for manuscripts in Python or R. Useful when plots go to submission, not to a report. Claude Code CX Codex Cursor +1 18,700installs baoyu-image-gen JimLiu Generates images via OpenAI, Google, DashScope, and other APIs directly inside your coding agent. Handles text prompts, image references, and parallel batch jobs. Claude Code CX Codex Cursor +1 33,600installs baoyu-infographic JimLiu Turns your text into an infographic: picks a layout and style, writes the prompt, renders the image. Claude Code CX Codex Cursor +1 32,800installs nature-polishing Yuan1z0825 A skill that polishes, translates and tightens existing academic prose. Facts, terminology and evidence boundaries stay intact. Claude Code CX Codex Cursor +1 17,400installs 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 media-use heygen-com Finds or generates media for HyperFrames videos, including voiceovers, music, cutouts, and color grades. Stores files locally in assets. Claude Code CX Codex Cursor +1 1,100,000installs mcp-builder official anthropics This skill walks through building an MCP server in TypeScript or Python, from reading the protocol spec to writing tests and evaluation questions. Claude Code Claude.ai 130,949installs

Questions about songsee

How do I install songsee in Claude?

Run npx skills add openclaw/openclaw --skill songsee -a claude-code. The CLI itself installs separately from the brew formula steipete/tap/songsee.

What does songsee do?

It generates spectrograms and feature panels from audio: mel, chroma, hpss, selfsim, loudness, tempogram, mfcc, flux. Output goes to jpg or png.

Which audio formats are supported?

WAV and MP3 decode natively. Other formats need ffmpeg available on the system.

Source text

SKILL.md · MIT 
---
name: songsee
description: "Generate spectrograms and feature-panel visualizations from audio with the songsee CLI."
homepage: https://github.com/steipete/songsee
metadata:
  {
    "openclaw":
      {
        "emoji": "🌊",
        "requires": { "bins": ["songsee"] },
        "install":
          [
            {
              "id": "brew",
              "kind": "brew",
              "formula": "steipete/tap/songsee",
              "bins": ["songsee"],
              "label": "Install songsee (brew)",
            },
          ],
      },
  }
---

# songsee

Generate spectrograms + feature panels from audio.

Quick start

- Spectrogram: `songsee track.mp3`
- Multi-panel: `songsee track.mp3 --viz spectrogram,mel,chroma,hpss,selfsim,loudness,tempogram,mfcc,flux`
- Time slice: `songsee track.mp3 --start 12.5 --duration 8 -o slice.jpg`
- Stdin: `cat track.mp3 | songsee - --format png -o out.png`

Common flags

- `--viz` list (repeatable or comma-separated)
- `--style` palette (classic, magma, inferno, viridis, gray)
- `--width` / `--height` output size
- `--window` / `--hop` FFT settings
- `--min-freq` / `--max-freq` frequency range
- `--start` / `--duration` time slice
- `--format` jpg|png

Notes

- WAV/MP3 decode native; other formats use ffmpeg if available.
- Multiple `--viz` renders a grid.

© openclaw · MIT · openclaw/openclaw

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