A sophisticated automation pipeline that downloads YouTube audio and captures real-time AI translations using the Doubao interface.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install byt-workflow
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 byt-workflow 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 byt-workflow?
Byt Workflow is a robust automation solution designed to bridge the gap between video content and textual translation. It acts as an orchestrator for several Openclaw Skills, providing a seamless transition from a raw YouTube URL to a finished translation file. By leveraging a multi-stage process, it ensures that creators and developers can localize content without manual intervention.
The skill is uniquely optimized for cross-platform environments, allowing users to initiate commands via WSL while executing GUI-heavy tasks on the Windows host. This integration highlights the power of using Openclaw Skills to handle complex workflows that require interaction with specific desktop applications like Doubao for high-quality translation capture.
byt-workflow Use Cases
- Creating bilingual transcripts for educational or research-based YouTube videos.
- Automating the extraction of audio and text for content localization pipelines.
- Streamlining the workflow for users who frequently translate foreign language media using AI tools.
- Archiving YouTube content with associated metadata and translated text files.
How byt-workflow Works
- The workflow begins by extracting and downloading the audio component of a YouTube video.
- It triggers the Doubao translation environment on the Windows desktop.
- The skill initiates audio playback, feeding the content into the translation engine.
- Real-time capture logic monitors and saves the translated output into a structured text format.
- Upon completion, the system returns a comprehensive JSON object mapping the locations of all generated assets.
byt-workflow Setup
To deploy this workflow, ensure your environment supports WSL to Windows communication and that you have the necessary Openclaw Skills installed.
# Execute the workflow via WSL calling the Windows Python environment
wsl -> python.exe scripts/workflow.py <youtube_url> [mode]
Note: The Windows desktop must remain visible and active (no RDP disconnects) as the skill relies on GUI automation to interact with the translation interface.
byt-workflow Data Schema & Taxonomy
The skill organizes its output in the Windows directory structure, typically under a works/ folder. Results are returned in the following schema:
| Attribute | Type | Description |
|---|---|---|
| success | boolean | Indicates if the entire workflow finished without errors |
| audio_path | string | The local Windows path to the downloaded MP3 file |
| translation_path | string | The local Windows path to the captured translation TXT file |
| duration | integer | The total length of the audio processed in seconds |
byt-workflow Advanced Features
- Multi-mode translation support including dual, single, chinese, and bilingual output formats.
- Integrated cross-platform execution logic specifically designed for Openclaw Skills users on Windows/WSL.
- Granular error handling that provides specific error codes for GUI-level failures.
- Extensible architecture allowing for the swapping of individual sub-skills like the audio player or capture agent.
SKILL.md
Loading
Related Openclaw Skills
XMind Generator & Reader
A chat-first skill to generate, read, and summarize XMind mind maps directly from your AI agent using the xmind-generator-mcp server.
Jadwal Sholat (Indonesian Prayer Times)
A specialized skill for retrieving Indonesian prayer schedules and location IDs using the api.myquran.com service.
paste-rs
A streamlined utility for uploading text, logs, and snippets to paste.rs with built-in secret redaction and local backups.
Jadwal Sholat (api.myquran.com)
A skill to fetch Indonesian prayer times including imsak, subuh, dzuhur, ashar, maghrib, and isya for any city or regency.
Trading Analyzer
A unified market analysis engine for cryptocurrency and stocks powered by multi-source financial data and technical indicators.
Feishu Leave Request
A browser automation skill that facilitates the end-to-end submission of leave requests within the Feishu (Lark) corporate ecosystem.
Featured*
