A professional Bilibili video processing agent that transcribes audio into text and generates high-quality structured summaries.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install bilibili-transcriber
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 bilibili-transcriber 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 Bilibili Transcriber?
Bilibili Transcriber is a powerful tool within the Openclaw Skills ecosystem designed to streamline video content consumption. It automatically extracts audio from Bilibili URLs or BV IDs, transcribes the speech into text using either cloud-based or local engines, and synthesizes the information into a structured Markdown summary.
By leveraging advanced AI models like Alibaba Paraformer (via DashScope) or local faster-whisper implementations, it provides developers and researchers with a fast, reliable way to index and understand video content without watching hours of footage. It is optimized for Chinese language processing and handles various edge cases like missing CC subtitles or offline requirements.
Bilibili Transcriber Use Cases
- Creating written archives of technical tutorials or lectures found on Bilibili.
- Generating time-stamped meeting notes or summaries for shared video resources.
- Extracting key insights and commands from developer-focused video content.
- Researching video topics efficiently by reading structured summaries instead of manual playback.
How Bilibili Transcriber Works
- The skill parses the provided URL or BV ID to extract video metadata including title, author, and duration.
- It checks for the existence of official CC subtitles via the Bilibili API as a primary source.
- If subtitles are unavailable, it downloads the audio track using yt-dlp.
- Audio is processed via one of two engines: Alibaba Paraformer (Cloud) for speed or faster-whisper (Local) for privacy and offline use.
- The transcribed text is analyzed to generate a structured Markdown report containing core viewpoints, detailed summaries, and key timestamps.
- The final output is displayed to the user or saved as a .md file in the local workspace.
Bilibili Transcriber Setup
To get started with this Openclaw Skills component, install the necessary dependencies and ensure ffmpeg is available on your system:
pip install faster-whisper yt-dlp dashscope requests
For system-level audio processing, install ffmpeg:
- macOS:
brew install ffmpeg - Windows:
winget install ffmpeg - Linux:
sudo apt install ffmpeg
Set your API keys if using cloud transcription:
export DASHSCOPE_API_KEY='your_api_key_here'
Bilibili Transcriber Data Schema & Taxonomy
The skill organizes transcription data and video metadata into a structured format used for summary generation:
| Field | Description |
|---|---|
| Video Title | The original title retrieved from Bilibili |
| Creator | The UP owner of the video content |
| Duration | Total runtime of the video |
| Core Viewpoints | 3-5 bullet points of primary arguments |
| Detailed Summary | 300-500 words organized by timeline or theme |
| Timestamps | Critical events marked as [MM:SS] |
| Target Audience | Identified persona for whom the video is relevant |
Bilibili Transcriber Advanced Features
- Singleton Model Caching: Keeps models in memory after the first load for near-zero latency on subsequent requests.
- Automatic Device Detection: Prioritizes CUDA-enabled GPUs and automatically falls back to CPU if hardware acceleration is unavailable.
- Quantization Optimization: Uses int8 quantization by default to increase processing speed by 4-5x compared to standard whisper models.
- Batch Processing Support: Use the batch_transcribe function to process multiple audio files simultaneously with a single model instance.
- Dual-Engine Flexibility: Seamlessly switch between high-speed cloud transcription and private local processing.
SKILL.md
Loading
Related Openclaw Skills
Audit System Skill
A specialized inspection framework for identifying logic errors, security risks, and UX friction in automated systems.
Claw Reliability
A professional-grade observability suite for monitoring AI agent tool invocations, LLM latency, and operational costs in real-time.
Face Transform
A comprehensive AI-powered facial transformation suite for analysis, editing, and stylistic modification of portrait images.
Suno Music Generation
A professional AI music production skill that leverages the Suno API to generate full songs, lyrics, and stems from simple text prompts.
War Room Skill
A high-stakes coordination protocol for managing multi-agent teams during production outages and critical system failures.
HTML to Markdown
A versatile utility to transform HTML code, local files, or live web pages into clean Markdown formatting for AI agents and developers.
Featured*
