video-downloadDownload videos from 1800+ websites and generate subtitles using Faster Whisper AI. Use when user wants to download videos from YouTube, Bilibili, Twitter, T...
Install via ClawdBot CLI:
clawdbot install upupc/video-downloadThis skill downloads videos from 1800+ websites and generates subtitles using Faster Whisper AI.
This skill supports downloading from virtually any video website thanks to yt-dlp. Some popular ones include:
Video Platforms:
Chinese Platforms:
International:
For the complete list of 1800+ supported sites, see: yt-dlp supported extractors
Local document about supported sites: references/supportedsites.md
Ensure the following Python packages are installed:
yt-dlp - For downloading videos from any supported siteffmpeg-python - For audio extractionfaster-whisper - For speech-to-text transcription (faster and more memory-efficient than openai-whisper). Note: The first run will download models from HuggingFace (default: small, ~3GB). A VPN is required for mainland China users.tqdm - For progress bar display during transcriptionInstall via pip:
pip install yt-dlp ffmpeg-python faster-whisper tqdmffmpeg must also be installed on your system
python scripts/video_parser.py '{"urls":["https://www.youtube.com/watch?v=VIDEO_ID"],"output":"./downloads"}'| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| urls | array | Yes | List of video URLs from any supported website |
| output | string | No | Output directory (default: "./downloads") |
| model | string | No | Faster Whisper model size: tiny, base, small, medium, large, large-v2, large-v3, turbo (default: "small") |
| transcribe | boolean | No | Whether to transcribe video to subtitle (default: true) |
| subtitle_format | string | No | Subtitle format: txt, srt, vtt, json (default: "txt") |
| download_subtitle | boolean | No | Download video's built-in subtitles if available (default: false) |
| overwrite_subtitle | boolean | No | Overwrite existing subtitle files (default: true, set to false to skip if exists) |
The skill will:
Output structure:
downloads/
└── Video Title/
├── Video Title.mp4
├── Video Title.wav
└── Video Title.txtpython scripts/video_parser.py '{"urls":["https://www.youtube.com/watch?v=dQw4w9WgXcQ"],"output":"./my_videos"}'python scripts/video_parser.py '{"urls":["https://www.bilibili.com/video/BV1xx411c7XD"],"output":"./downloads"}'python scripts/video_parser.py '{"urls":["https://www.tiktok.com/@username/video/1234567890"],"output":"./tiktok"}'python scripts/video_parser.py '{"urls":["https://www.youtube.com/watch?v=VIDEO1","https://www.bilibili.com/video/BV1xx","https://twitter.com/user/status/123"],"output":"./videos"}'python scripts/video_parser.py '{"urls":["https://www.twitch.tv//channel/clip/ClipName"],"output":"./clips"}'python scripts/video_parser.py '{"urls":["https://www.youtube.com/watch?v=VIDEO_ID"],"output":"./downloads","transcribe":false}'python scripts/video_parser.py '{"urls":["https://www.youtube.com/watch?v=VIDEO_ID"],"output":"./downloads","subtitle_format":"srt"}'python scripts/video_parser.py '{"urls":["https://www.youtube.com/watch?v=VIDEO_ID"],"output":"./downloads","subtitle_format":"vtt"}'python scripts/video_parser.py '{"urls":["https://www.youtube.com/watch?v=VIDEO_ID"],"output":"./downloads","download_subtitle":true}'python scripts/video_parser.py '{"urls":["https://www.youtube.com/watch?v=VIDEO_ID"],"output":"./downloads","model":"large"}'python scripts/video_parser.py '{"urls":["https://www.youtube.com/watch?v=VIDEO_ID"],"output":"./downloads","overwrite_subtitle":false}'brew install ffmpeg (macOS) or your system's package managerGenerated Mar 1, 2026
Video creators and marketers download videos from platforms like YouTube or TikTok to repurpose content, such as creating compilations or highlights. They use the subtitle generation feature to transcribe and translate videos for localization into different languages, enabling broader audience reach.
Educators and students download instructional videos from sources like Bilibili or Vimeo for offline access in areas with poor internet connectivity. The transcription capability converts video lectures into text notes, facilitating study and accessibility for learners with hearing impairments.
Business analysts download promotional videos from competitors' social media accounts, such as Facebook or Twitter, to analyze marketing strategies and content trends. Subtitles are generated to extract key messaging and keywords for automated sentiment analysis or report generation.
Legal and compliance teams download videos from platforms like Twitch or Instagram to archive content for regulatory audits or copyright enforcement. Transcription helps in indexing and searching video content for specific terms or violations, ensuring adherence to digital media laws.
Non-profits and accessibility advocates download videos from diverse sources like Netflix or BBC iPlayer to generate subtitles for deaf or hard-of-hearing users. This skill automates the creation of accessible content, reducing manual transcription costs and improving inclusivity in digital media.
Offer a free tier with basic video downloading and limited subtitle generation, while charging for advanced features like batch processing, custom model sizes, or priority support. Revenue is generated through subscription plans targeting individual creators and small businesses.
Provide the skill as an API service that other developers or companies can integrate into their applications, such as content management systems or e-learning platforms. Charge based on usage metrics like number of videos processed or transcription minutes.
License the technology to media companies or educational institutions for rebranding as their own internal tool. This includes customization options and dedicated support, generating revenue through one-time licensing fees or annual maintenance contracts.
💬 Integration Tip
Ensure ffmpeg is installed system-wide and use a VPN in restricted regions for model downloads to avoid failures.
Extract frames or short clips from videos using ffmpeg.
Download videos, audio, subtitles, and clean paragraph-style transcripts from YouTube and any other yt-dlp supported site. Use when asked to “download this video”, “save this clip”, “rip audio”, “get subtitles”, “get transcript”, or to troubleshoot yt-dlp/ffmpeg and formats/playlists.
Generate SRT subtitles from video/audio with translation support. Transcribes Hebrew (ivrit.ai) and English (whisper), translates between languages, burns subtitles into video. Use for creating captions, transcripts, or hardcoded subtitles for WhatsApp/social media.
Create AI videos with optimized prompts, motion control, and platform-ready output.
自动登录抖音账号，上传并发布视频到抖音创作者平台，支持视频标签管理和登录状态检查。
AI video generation workflow on Volcengine. Use when users need text-to-video, image-to-video, generation parameter tuning, or async task troubleshooting for video jobs.