audio-summary for Openclaw

A specialized tool for extracting audio from video files and generating automated, AI-powered transcriptions and summaries.

alanoo7
v1.0.0
Mar 8, 2026
0
1.3k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install audio-summary

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install audio-summary 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-summary?

The audio-summary skill is a developer-focused utility designed to transform video content into concise, actionable text summaries. By leveraging the power of ffmpeg for media processing and advanced LLMs like qwen3-asr-flash, this skill automates the tedious task of manual transcription. As a part of the Openclaw Skills collection, it provides a seamless bridge between raw media files and structured documentation, making it easier to manage large volumes of video data.

The tool is optimized for efficiency, utilizing specific audio compression techniques to stay within model token and file size limits while maintaining high transcription accuracy. It is particularly effective for users who need to quickly digest meetings, tutorials, or presentations within a CLI-driven workflow.

audio-summary Use Cases

  • Transcribing and summarizing recorded video meetings or webinars for quick review.
  • Converting educational video content into text-based study notes.
  • Extracting key insights from interviews or podcasts without listening to the entire recording.
  • Streamlining documentation workflows by generating text summaries directly from video demos.

How audio-summary Works

  1. The user provides a path to a video file (e.g., MP4) via the command line.
  2. The skill utilizes ffmpeg to extract the audio track, converting it to a 16k mono compressed format to optimize for API processing.
  3. The compressed audio is sent to the qwen3-asr-flash model for high-speed speech-to-text conversion.
  4. The model processes the transcription and generates a segmented summary of the content.
  5. The final output is saved automatically as a text file in the same directory as the source video.

audio-summary Setup

To use this Openclaw Skills extension, ensure you have the necessary dependencies installed on your system.

Prerequisites

  • ffmpeg must be installed and accessible in your system PATH.
  • The openai Python SDK must be installed in your environment.
  • An active Alibaba Bailian API KEY is required and should be configured within the script.

Usage

Run the following command in your terminal:

python .openclaw/workspace/skills/audio-summary/audio_summary_skill.py "C:\Path\To\Your\Video.mp4"

audio-summary Data Schema & Taxonomy

The skill manages data by generating temporary audio files and permanent text outputs based on the source media:

File Type Description Location
Input Video Source media (e.g., .mp4) User-defined path
Temp Audio 16k mono compressed audio Generated during runtime
Output Summary [VideoName]_summary.txt Same directory as input video

Metadata including transcription segments and summary blocks are handled internally via the qwen3-asr-flash API response.

audio-summary Advanced Features

  • Intelligent audio compression supporting up to 48k bitrates to allow processing of 5-8 minute videos in a single pass.
  • Automatic 16k mono downsampling to adhere to strict 6MB Base64 API limits.
  • Segmented content summarization for improved readability of long-form media.
  • Direct filesystem integration for organized output management within Openclaw Skills.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*