A bridge that enables AI agents to capture and process real-time audio streams from any browser tab without platform-specific integrations.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install browser-audio-capture
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install browser-audio-capture using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Browser Audio Capture?
Browser Audio Capture is a specialized utility designed to give AI agents auditory capabilities within a web environment. By acting as a bridge between the browser's media layer and your AI pipeline, it allows for the seamless extraction of audio from meetings, webinars, and streaming platforms. As part of the Openclaw Skills ecosystem, this tool eliminates the need for complex API keys or per-platform OAuth setups, making it a universal solution for developers building intelligent listeners.
This skill is built for flexibility, supporting both a Python-based CLI for automated workflows and a dedicated Chrome extension for manual, persistent capture. Whether you are building a real-time meeting assistant or an automated podcast note-taker, this skill provides the raw audio data necessary to power modern transcription and analysis models.
Browser Audio Capture Use Cases
- Creating automated, real-time meeting summaries for Google Meet, Zoom, and Microsoft Teams.
- Extracting actionable notes and insights from YouTube videos, podcasts, and online courses.
- Monitoring earnings calls and live webinars for competitive intelligence.
- Analyzing customer support calls or sales demos performed via browser-based VoIP tools.
- Enabling AI agents to react to live audio cues during streaming events or discord sessions.
How Browser Audio Capture Works
- The user launches Chrome with remote debugging enabled on port 9222 to permit external interaction.
- The Openclaw Skills component identifies the target browser tab via the CLI or the extension interface.
- The skill hooks into the browser's audio stream, capturing high-quality PCM16 audio data in real-time.
- Captured audio is packaged into a JSON structure containing the raw Base64 data and source metadata.
- The payload is streamed to a local or remote HTTP endpoint (defaulting to port 8900) for processing by your AI agent.
Browser Audio Capture Setup
To get started, launch Google Chrome with the remote debugging port enabled:
/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome \
--remote-debugging-port=9222 --user-data-dir=$HOME/.chrome-debug-profile &
Install the required Python dependencies:
pip install aiohttp
For the CLI experience, use the following commands to manage your capture sessions:
# Detect and capture audio from a meeting tab
python3 -m browser_capture.cli capture
# Watch for new tabs every 15 seconds
python3 -m browser_capture.cli watch --interval 15
To use the Chrome Extension, navigate to chrome://extensions/, enable Developer mode, and use 'Load unpacked' to select the extension directory.
Browser Audio Capture Data Schema & Taxonomy
The skill streams data as a JSON payload to the configured endpoint. This structured format ensures that the Openclaw Skills consumer receives all necessary context for the audio stream.
| Property | Type | Description |
|---|---|---|
sessionId |
String | A unique identifier for the specific capture session. |
audio |
String | Base64 encoded PCM16 audio data. |
sampleRate |
Integer | The sample rate of the stream (default 16000). |
format |
String | The audio format (e.g., "pcm16"). |
tabUrl |
String | The source URL where the audio is being captured. |
tabTitle |
String | The HTML title of the source tab. |
Browser Audio Capture Advanced Features
- Continuous watch mode for automated discovery of meeting tabs based on URL patterns.
- Background persistent capture allowing the extension to stream audio even after the popup is closed.
- Multi-agent compatibility with support for Openclaw Skills, LangChain, CrewAI, and custom HTTP receivers.
- Direct integration capabilities with transcription services like Whisper, Deepgram, and NVIDIA Riva.
- Lightweight PCM16 encoding to minimize latency and CPU overhead during high-stakes captures.
SKILL.md
Loading
Related Openclaw Skills
watchclaw
An automated health monitoring and recovery watchdog designed to protect OpenClaw gateways from faulty configuration changes.
ShieldCortex
ShieldCortex provides AI agents with a secure, persistent memory system featuring semantic search, knowledge graphs, and a 6-layer defense pipeline.
Seats.aero Award Flight Search
Search and find award flight availability across 24 mileage programs using the seats.aero partner API.
Mermaid Diagrams Skill
The Mermaid Diagrams Skill enables the programmatic generation of visual charts and diagrams directly from text-based Mermaid syntax.
percept-ambient
An always-on ambient intelligence layer that builds a continuous knowledge graph of your conversations and projects without needing explicit commands.
Percept Listen
Ambient audio capture and local transcription for AI agents via wearable devices like Omi and Apple Watch.
METADATA
Featured*
