---
title: "Live Stream Audio Monitor"
description: "Monitors live audio streams from RTMP, HLS, or Icecast sources using FFmpeg stream capture and real-time chunked transcription via Deepgram's streaming API or Whisper.cpp. Detects silence gaps, audio clipping, and loudness deviations from EBU R128 targets using pyloudnorm."
verification: "security_reviewed"
source: "https://github.com/FFmpeg/FFmpeg"
author: "FFmpeg"
category:
  - "Media & Transcription"
framework:
  - "Claude Code"
tool_ecosystem:
  github_repo: "FFmpeg/FFmpeg"
  github_stars: 58548
---

# Live Stream Audio Monitor

Monitors live audio streams from RTMP, HLS, or Icecast sources using FFmpeg stream capture and real-time chunked transcription via Deepgram's streaming API or Whisper.cpp. Detects silence gaps, audio clipping, and loudness deviations from EBU R128 targets using pyloudnorm.

## Installation

Choose whichever fits your setup:

1. Copy this skill folder into your local skills directory.
2. Clone the repo and symlink or copy the skill into your agent workspace.
3. Add the repo as a git submodule if you manage shared skills centrally.
4. Install it through your internal provisioning or packaging workflow.
5. Download the folder directly from GitHub and place it in your skills collection.

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/live-stream-audio-monitor/)