A sophisticated tool for converting meeting audio into structured transcripts with speaker diarization, timestamps, and automated action-item extraction.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install meetingsummarizer
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 meetingsummarizer 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 SenseAudio Meeting Summarizer?
The SenseAudio Meeting Summarizer is a specialized integration designed to transform raw audio into highly organized documentation. As part of the Openclaw Skills library, it leverages official SenseAudio ASR endpoints to provide professional-grade transcription. The skill excels at speaker diarization, allowing users to distinguish between different voices in a conversation, making it ideal for multi-person meetings and interviews.
Beyond simple speech-to-text, this skill offers powerful post-processing features including sentiment analysis and timestamping at both the word and segment levels. It is built with a focus on efficiency and privacy, defaulting to local heuristic-based summarization to extract decisions and follow-up tasks without requiring additional external LLM credits. Whether handling recorded files or real-time streams, it provides a robust solution for maintaining accurate meeting records.
SenseAudio Meeting Summarizer Use Cases
- Creating detailed transcripts for board meetings and stakeholder discussions.
- Identifying specific action items and owners from recorded project syncs.
- Generating speaker-separated records for journalistic interviews and research sessions.
- Providing real-time transcription for live webinars and presentations using WebSocket streams.
- Analyzing the sentiment and engagement levels of participants throughout a discussion.
How SenseAudio Meeting Summarizer Works
- The skill first validates the audio asset, ensuring quality and checking if the file size exceeds the 10MB limit.
- For recorded audio, it utilizes the sense-asr-pro model via HTTP to perform high-accuracy transcription with diarization.
- For live scenarios, it establishes a WebSocket connection using the sense-asr-deepthink model to process streaming PCM audio.
- It applies timestamp granularities to segments and words to create a searchable timeline of the conversation.
- The tool processes the transcript text locally to identify linguistic patterns associated with decisions and follow-up tasks.
- Finally, it exports the structured data into formats such as Markdown notes, JSON transcripts, or CSV speaker statistics.
SenseAudio Meeting Summarizer Setup
To get started with this skill in your Openclaw Skills environment, ensure you have your API key and the necessary Python dependencies installed:
# Set your API key
export SENSEAUDIO_API_KEY="your_senseaudio_api_key"
# Install required dependencies
uv pip install requests websockets
Ensure that for real-time applications, your audio source is configured for 16000Hz mono PCM format.
SenseAudio Meeting Summarizer Data Schema & Taxonomy
The skill organizes transcription data into a structured format for easy parsing and integration:
| Attribute | Description | Data Type |
|---|---|---|
| text | The complete transcript text | String |
| segments | Array of objects containing speaker ID, text, and timestamps | Array |
| speaker | The unique identifier for a detected participant | String |
| sentiment | The emotional tone detected in a specific segment | String |
| start / end | Time markers for speech segments in seconds | Float |
| words | Detailed word-level timing data | Array |
SenseAudio Meeting Summarizer Advanced Features
- Support for high-concurrency WebSocket streaming for live meeting monitoring.
- Advanced speaker diarization with configurable max_speakers for improved accuracy in complex environments.
- Automated sentiment analysis to track participant reactions and meeting atmosphere.
- Heuristic-based local summarization that extracts action items without external LLM dependencies.
- Multi-language support and translation capabilities via sense-asr-pro parameters.
SKILL.md
Loading
Related Openclaw Skills
Gmail Label and Archive Recipe
A streamlined automation recipe for searching, labeling, and archiving Gmail threads to achieve inbox zero efficiently.
PowerPoint
A macOS-native automation skill to control Microsoft PowerPoint sessions, slides, and slideshow states using AppleScript.
SenseAudio Audiobook Generator
A professional-grade AI tool for converting long-form text and novels into immersive audiobooks with automated chapter management and multi-voice character dialogue.
SenseAudio AI Rapper
A professional AI music generation tool specifically optimized for creating rap lyrics and vocal-heavy hip-hop tracks via Openclaw Skills.
Evidence of Use (EOU) Patent Analysis
An automated patent analysis engine that identifies infringement leads and generates professional Evidence of Use (EOU) reports.
URL Preview
An automated tool for extracting and displaying rich metadata previews from shared HTTP/HTTPS links.
Featured*
