Download videos, audio, and subtitles from YouTube and other supported sites using yt-dlp. Choose resolution and output filenames, extract MP3 audio, or inspect titles, durations, and other video details without downloading the media.
Download video and audio from YouTube and 1000+ sites using yt-dlp. No API keys needed. Use when: (1) Downloading a video from YouTube or other sites, (2) Extracting audio from a video URL, (3) Downloading subtitles/captions from a video, (4) Getting video metadata without downloading.
Run score Not tested
See how to installThis skill helps you use yt-dlp to save video, audio, and subtitles from a video URL. It supports more than 1,000 sites, including YouTube. You can choose resolutions such as 720p or 1080p, extract audio as MP3, and retrieve subtitles in multiple languages. Output locations and filenames can use details such as the title, uploader, and upload date. It also provides steps for checking titles, durations, and available formats without saving the video itself.
Use it when you need a video at a particular resolution or want only its audio or subtitles. It also helps you inspect available formats before downloading and choose one that suits your intended use.
You need to install yt-dlp. If video and audio are separate streams, merging them also requires ffmpeg. No API key is needed. If a site change causes retrieval to fail, the skill provides steps for checking whether yt-dlp needs an update.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI checked the SKILL.md for operations that need care and for setup requirements. The score comes only from actually running the skill (hands-on test).
Not counted in the score. Rated by AI (OpenAI Codex) as of Oct 23, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
Download video and audio from URLs using yt-dlp directly. No wrapper scripts needed.
brew install yt-dlp or pip install yt-dlpbrew install ffmpeg or apt install ffmpeg (required for merging video+audio streams)Update yt-dlp periodically to keep up with site changes: yt-dlp -U or pip install -U yt-dlp.
yt-dlp "URL" -o "%(title)s.%(ext)s" --merge-output-format mp4
# 720p
yt-dlp "URL" -f "bestvideo[height<=720]+bestaudio/best[height<=720]" --merge-output-format mp4
# 1080p
yt-dlp "URL" -f "bestvideo[height<=1080]+bestaudio/best[height<=1080]" --merge-output-format mp4
yt-dlp "URL" -x --audio-format mp3 --audio-quality 0
# Download video with English subtitles
yt-dlp "URL" --write-subs --sub-langs en --merge-output-format mp4
# Download video with multiple subtitle languages
yt-dlp "URL" --write-subs --sub-langs "en,es,fr" --merge-output-format mp4
# Download only subtitles (no video)
yt-dlp "URL" --write-subs --sub-langs en --skip-download
yt-dlp "URL" --dump-json --no-download
yt-dlp "URL" -F
yt-dlp "URL" -o "./downloads/%(title)s.%(ext)s" --merge-output-format mp4
| Quality | Format flag |
|---|---|
| Best | -f "bestvideo+bestaudio/best" (default) |
| 1080p | -f "bestvideo[height<=1080]+bestaudio/best[height<=1080]" |
| 720p | -f "bestvideo[height<=720]+bestaudio/best[height<=720]" |
| 480p | -f "bestvideo[height<=480]+bestaudio/best[height<=480]" |
| Worst | -f "worstvideo+worstaudio/worst" |
Common variables for -o templates:
| Variable | Description |
|---|---|
%(title)s | Video title |
%(ext)s | File extension |
%(id)s | Video ID |
%(uploader)s | Channel/uploader name |
%(upload_date)s | Upload date (YYYYMMDD) |
%(duration)s | Duration in seconds |
%(resolution)s | Video resolution |
--merge-output-format mp4 to avoid ending up with .webm or .mkv files.--no-download with --dump-json for metadata-only queries -- no files written to disk.yt-dlp -U).-f "bestvideo[height<=720]+bestaudio" to save bandwidth when full resolution is not needed.--dump-json output includes title, duration, uploader, view_count, description, formats, subtitles, and much more.pip install yt-dlp) and ensure your PATH includes pip's bin directory.yt-dlp -U to update. Sites change frequently and yt-dlp ships fixes regularly.No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Create 3D objects from text or images, choose catalog assets for repeated scenery, and inspect the results in Blender. The workflow checks geometry, materials, scale, and ground contact while recording asset sources and generation costs.
Generate background music and songs with lyrics using ACE-Step 1.5, with controls for duration, tempo, and musical key. You can also restyle reference audio and separate vocals or individual instruments from mixed tracks.
Build voice assistants and conversational characters with ElevenLabs. Configure voices, language models, and external tools, then connect conversations to a website widget or use Twilio integration for outbound phone calls.
Generate video clips from text descriptions or reference images through multiple API services. Compare available providers by cost and task needs, choose aspect ratios, track generation progress, and refine existing clips through conversational editing with Gemini Omni.
Create AI video clips from text or reference images, choosing among providers to match the task and budget. Supports vertical social videos, product photo animation, and conversational editing of existing clips with Gemini Omni Flash.
Generate and edit images and videos through Atlas Cloud using one API key across multiple model families. Choose supported models for each task, download the results, and retain details about the model, inputs, and estimated cost.