youtube-transcript
YouTube long video (>1 hour) full verbatim transcription and translation workflow. Use when user needs to (1) Extract subtitles from YouTube videos, (2) Translate English transcripts to Chinese, (3) Handle long videos that exceed session limits, (4) Process DownSub API responses and generate formatted documents.
Why use this skill?
Expert-grade YouTube transcription and translation for long videos. Extract verbatim transcripts, translate to Chinese, and generate key metrics automatically.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/qingliu1617-art/ytb-transcript-longWhat This Skill Does
The YouTube Long Video Transcript & Translation skill provides a robust, professional-grade workflow for extracting and processing high-volume YouTube content. Designed specifically for videos exceeding one hour, this skill automates the otherwise cumbersome process of verbatim transcription and high-quality Chinese translation. By leveraging the DownSub API for reliable subtitle retrieval and utilizing a sub-agent architecture to manage session memory limits, it ensures that long-form content is processed in manageable chunks without loss of context or detail.
The skill is built with an emphasis on accuracy and structure, automatically generating key metrics tables and executive summaries for every transcript. Whether you are analyzing a lengthy technical lecture, a financial deep-dive, or an hours-long interview, this tool ensures you receive a perfectly formatted, professionally structured Markdown document ready for immediate review or online sharing.
Installation
To install this skill, run the following command in your terminal or OpenClaw interface:
clawhub install openclaw/skills/skills/qingliu1617-art/ytb-transcript-long
Ensure you have configured your DownSub API bearer token in your environment secrets to avoid 401 authorization errors.
Use Cases
- Academic & Research: Transcribing hours of conference presentations or lectures for detailed note-taking and archival.
- Content Creation: Extracting insights from industry-leading long-form podcasts and interviews to generate blog content.
- Business Intelligence: Converting market analysis videos into actionable Chinese summaries and key metrics tables.
- Global Accessibility: Breaking down language barriers by translating English technical discourse into professional Chinese documentation.
Example Prompts
- "Translate this 2-hour technical deep dive into Chinese, create a key metrics table, and save it as a structured Markdown document."
- "Process the YouTube video at https://www.youtube.com/watch?v=EXAMPLE_ID, provide an executive summary, and generate a 500-line chunked transcript."
- "Extract the transcript from this long-form interview, translate it into Chinese, and summarize the key revenue and growth points mentioned."
Tips & Limitations
- Check Language: Always verify the
langfield in the API response. Avoid non-English tracks to prevent translation errors. - Manage Complexity: The tool automatically handles long videos through sub-agent spawning; avoid manually processing files larger than 1000 lines in the main session.
- Dependency check: If the
zhiyantool is unavailable, the system will gracefully fallback to providing local Markdown files. - Cost Control: Be mindful of the token usage when triggering sub-agents; the workflow is optimized to work within a 30-minute processing window or a defined cost limit.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-qingliu1617-art-ytb-transcript-long": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-write, file-read, external-api