# Audio Capture

> Use this tool when you need to record and analyze audio on macOS, capturing both microphone input and system audio into separate channels of a stereo WAV file. It solves problems related to audio processing, testing, and debugging by providing a straightforward way to capture and inspect audio signals. Ideal for use cases requiring audio input analysis, such as voice assistants, speech recognition, or audio-based machine learning models.

Canonical page: https://skillsregistry.net/skills/bugorbn-audio-capture  
JSON: https://api.skillsregistry.net/v1/skills/bugorbn-audio-capture

## Description

Enables AI agents to record and analyze audio on macOS by capturing microphone input and system audio into named sessions. Recordings are returned as stereo WAV files with mic on the left channel and system output on the right. Uses a notarized Swift helper binary for audio capture, bundled alongside the TypeScript MCP server. Available via npm and Homebrew.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/bugorbn-audio-capture)
- **Repository:** <https://github.com/bugorbn/audio-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "bugorbn-audio-capture"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/bugorbn-audio-capture` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/bugorbn-audio-capture/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt
