youtube-transcribe-skill
This skill downloads subtitles from YouTube videos using yt-dlp and converts them into timestamped plain-text files. It handles multiple subtitle languages with configurable preferences, supports various YouTube URL formats including Shorts and live streams, and can retry with browser cookies when videos require authentication. Output is saved to your chosen directory with line counts reported.
youtube-transcribe-skill extracts YouTube video subtitles and transcripts as timestamped text files saved locally.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-27
youtube-transcribe-skill extracts YouTube video subtitles and transcripts as timestamped text files saved locally. This skill downloads subtitles from YouTube videos using yt-dlp and converts them into timestamped plain-text files. It handles multiple subtitle languages with configurable preferences, supports various YouTube URL formats including Shorts and live streams, and can retry with browser cookies when videos require authentication. Output is saved to your chosen directory with line counts reported.
Use it when
- Yes.
- youtube-transcribe-skill retrieves transcripts by downloading subtitles from YouTube videos and converting them into timestamped plain-text.
Verify before relying
Read SKILL.md below before installing (4 files). Open directory: indexed for reading, not audited.
Install
feiskyer/codex-settings/youtube-transcribe-skill · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I download YouTube subtitles with youtube-transcribe-skill?
youtube-transcribe-skill downloads subtitles from YouTube videos using yt-dlp and saves them as timestamped plain-text files to your chosen directory. Simply provide a YouTube URL—the skill handles standard videos, Shorts, and live streams—and it will extract and convert the captions into a searchable text file with line counts reported.
Can youtube-transcribe-skill extract captions from YouTube video URLs?
Yes. youtube-transcribe-skill extracts captions from YouTube video URLs in your preferred language. It supports multiple subtitle languages with configurable preferences, so you can specify which language captions to download if multiple options are available on the video.
What does youtube-transcribe-skill do to get transcripts from YouTube?
youtube-transcribe-skill retrieves transcripts by downloading subtitles from YouTube videos and converting them into timestamped plain-text format. It supports various YouTube URL formats and can retry with browser cookies when videos require authentication, making it useful for age-restricted or membership-required content.
Can I save YouTube video subtitles locally with this skill?
Yes. youtube-transcribe-skill saves YouTube subtitles locally as plain-text files to your chosen directory. The output includes timestamps for each subtitle line, making the saved transcripts searchable and easy to reference later.
Does youtube-transcribe-skill work with age-restricted videos?
youtube-transcribe-skill can retrieve transcripts from age-restricted or membership-required videos by retrying with browser cookies when needed. This allows you to access subtitles from videos that normally require authentication or special permissions.
What license does youtube-transcribe-skill use?
youtube-transcribe-skill is released under the MIT license, allowing free use, modification, and distribution with minimal restrictions.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
YouTube Transcript Extraction
Use the bundled scripts/transcribe_youtube.py wrapper for the primary workflow. It downloads subtitles with yt-dlp, selects the preferred language, converts WebVTT cues into timestamped plain text, and reports the output path and line count.
Requirements
- Install
yt-dlpand confirmyt-dlp --versionsucceeds. - Resolve the absolute directory containing this
SKILL.md; refer to it as<skill-dir>. - Keep the output in the user's current working directory unless they request another location.
The Python wrapper itself uses only the standard library. It can display --help without yt-dlp being installed.
Primary workflow
Run without browser cookies first:
python3 "<skill-dir>/scripts/transcribe_youtube.py" \
"<youtube-url>" \
--output-dir "$PWD"
The default language preference is Simplified Chinese, Traditional Chinese, other Chinese variants,
(truncated - see the full file via the links below)
File tree — 4 files
skills/youtube-transcribe-skill/SKILL.md
skills/youtube-transcribe-skill/agents/openai.yaml
skills/youtube-transcribe-skill/scripts/transcribe_youtube.py
skills/youtube-transcribe-skill/tests/test_transcribe_youtube.py
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Extract and save YouTube video subtitles or transcripts as timestamped text”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
This skill pulls transcripts and captions directly from YouTube videos, handling multiple languages and subtitle formats. It attempts fast extraction via command-line tools first, then falls back to browser automation if needed, saving results as timestamped text files.
Video Summarizer fetches videos from any platform supported by yt-dlp and automatically produces a complete package: the original video file, extracted audio, timestamped subtitles, plain-text transcript, and an AI-generated summary. It handles subtitle retrieval from the source first, then falls back to AI transcription when needed, with parallel processing for long files.
Pull transcripts and captions directly from YouTube videos using multiple extraction methods. Supports manual and auto-generated subtitles across languages, with output in VTT, SRT, or plain text formats for editing and accessibility.
YouTube Tools harnesses yt-dlp to download videos, playlists, and audio directly to your machine at zero cost. Extract transcripts in multiple languages, pull video metadata, or convert to MP3—all without authentication or subscription fees. Ideal for bulk research, course archiving, and offline access.
This skill transforms Bilibili video content into organized Markdown documents by downloading AI-generated Chinese subtitles via yt-dlp, parsing the transcript, and restructuring it with proper headings, code blocks, and tables. Perfect for converting technical tutorials and educational videos into searchable reference notes.
Media Downloader pulls video and audio from over 1500 websites using yt-dlp, letting you choose resolution (480p through 4K), grab subtitles in multiple languages, and download entire playlists. Customize output naming, handle authentication across platforms, and manage format selection with precise control.
More skills Youtube Transcript (unlicensed) · youtube-downloader (MIT)