An intelligent voice-to-note assistant that transcribes audio into structured Markdown summaries with speaker identification and action items.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install audio-note-taker
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 audio-note-taker 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 Audio Note Taker?
Audio Note Taker is a high-performance utility designed to bridge the gap between spoken dialogue and actionable documentation. By leveraging state-of-the-art AI, this tool within the Openclaw Skills ecosystem processes recordings to generate structured, searchable, and professional notes. It is particularly effective at handling multi-language environments and complex discussions, ensuring no critical information is lost during the transcription process.
The skill combines the power of OpenAI Whisper for high-fidelity transcription with Large Language Models (LLMs) to perform semantic analysis. This allows users of Openclaw Skills to transform raw audio files into organized Markdown documents containing meeting minutes, key decisions, and clearly defined tasks without manual effort.
Audio Note Taker Use Cases
- Automatically transcribing meeting recordings and extracting structured action items.
- Converting academic lectures or seminars into organized study notes and summaries.
- Streamlining interview processing by generating text drafts from audio recordings.
- Documenting project retrospectives by turning spoken feedback into structured records.
- Converting quick voice memos into archived, searchable text for personal knowledge management.
How Audio Note Taker Works
- The user provides an audio file or recording path as input to the skill command.
- The system uses ffmpeg for audio pre-processing, including format conversion and noise reduction.
- Audio data is sent to the Whisper API to achieve high-accuracy speech-to-text conversion.
- Optional speaker diarization is performed to distinguish between different participants in the dialogue.
- The transcribed text is processed by an LLM to identify core themes, decisions, and specific action items.
- A final Markdown file is generated, incorporating metadata, summaries, and the full transcript.
Audio Note Taker Setup
To get started with this skill from the Openclaw Skills library, ensure you have the system dependencies and API keys configured:
- Install system dependencies:
apt install -y ffmpeg
- Configure your environment variables:
export OPENAI_API_KEY='your-api-key-here'
- Execute a basic transcription:
audio-note-taker /path/to/recording.m4a
Audio Note Taker Data Schema & Taxonomy
The skill produces a structured Markdown document (.md) organized with the following metadata and content sections:
| Section | Description |
|---|---|
| Metadata | Includes Title, Date, Location, and Participant list. |
| Meeting Summary | A high-level overview of the discussion points. |
| Decision Items | A checklist of finalized resolutions or agreements. |
| Action Items | A table mapping tasks to owners and deadlines. |
| Full Transcript | A collapsible section containing the timestamped dialogue. |
Output files are named using the {input}_notes.md convention by default but can be customized via CLI flags.
Audio Note Taker Advanced Features
- Multi-agent integration allowing summaries to be passed to social-publisher for automatic blog post generation.
- Support for mixed-language recognition (e.g., Chinese and English) in a single recording.
- Custom model selection for summarization using the NOTE_TAKER_MODEL environment variable.
- Advanced speaker identification for complex group discussions and interviews.
- Flexible output formats including Markdown, JSON, and plain text to suit different workflows within Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
tra-extract-text
A high-performance web extraction skill that leverages the trafilatura CLI to convert web pages into clean, readable markdown or text formats.
UI Inspiration Library
A structured visual search system that archives UI screenshots and retrieves them based on style, page type, and use case.
WeCom AI Bot Setup
A streamlined utility to connect OpenClaw to Enterprise WeChat (WeCom) using the AI Bot WebSocket mode for seamless internal team automation.
Multi-Topic Deep Research
An intelligent tool that launches parallel agents to conduct deep, multi-topic research and generate structured knowledge bases.
Marketing Hooks
An AI-powered framework for creating attention-grabbing marketing hooks and structured content using psychological triggers and the Puzzle-Driven Model.
Official Writing
A specialized skill designed to automate and standardize the creation of Chinese government documents according to the GB/T 9704-2012 national standard.
Featured*
