Generate SRT subtitles from video or audio files with Hebrew and English transcription support. Use when you need to create captions, transcripts, or hardcoded subtitles for social media and WhatsApp. Supports automatic language detection, translation between Hebrew and English, and burning subtitles directly into video files.
Trust score 76/100 (Trusted) · 61+ installs · 3 GitHub contributors · MIT license
Creating high-quality Hebrew subtitles for videos is frustrating. Generic transcription tools like vanilla Whisper struggle with Hebrew, and commercial captioning services are expensive and require uploading your file to an external server. This skill runs locally, uses the Hebrew-tuned ivrit.ai model, and can also burn subtitles directly into the video so they stay visible on WhatsApp and social media.
npx skills-il add openclaw/skills/ngutman/video-subtitles -a claude-codeThis is a community skill from an external source. The ZIP upload may not work on all platforms if the SKILL.md format is not fully compatible.
I have a Hebrew video called interview.mp4. Use the video-subtitles skill to produce an accurate SRT file, and explain what the command does.
I want to share lecture.mp4 on WhatsApp with captions that are always visible. Use the video-subtitles skill to burn the subtitles into the video.
I have a Hebrew talk and I want a version with English captions burned into the video. Use the video-subtitles skill to transcribe, translate, and burn them in.
I have a Hebrew podcast audio file episode12.mp3. Use the video-subtitles skill to produce a full plain-text transcript for uploading to a blog.
Implement Israeli web accessibility compliance per IS 5568 standard and WCAG 2.1 AA for Hebrew RTL applications. Use when user asks about Israeli accessibility law, "negishot" (accessibility), IS 5568, "teken negishot" (accessibility standard), "nachim" (disabilities), Hebrew screen reader support, RTL ARIA patterns, or accessibility audit for Israeli websites. Covers mandatory legal requirements under the Equal Rights for Persons with Disabilities Act, Hebrew screen reader compatibility, RTL-specific ARIA patterns, and penalties for non-compliance. Do NOT use for general WCAG guidance without Israeli context (use standard a11y resources instead).
Guide developers in using Hebrew NLP models and tools including DictaLM, DictaBERT, AlephBERT, and ivrit.ai. Use when user asks about Hebrew text processing, Hebrew NLP, "ivrit", Hebrew tokenization, Hebrew NER, Hebrew sentiment analysis, Hebrew speech-to-text, or needs to process Hebrew language text programmatically. Covers model selection, preprocessing, and Hebrew-specific NLP challenges. Do NOT use for Arabic NLP (different tools) or general English NLP tasks.
Process and extract data from scanned Israeli government forms using OCR. Supports Tabu (land registry), Tax Authority forms, Bituach Leumi documents, and other official Israeli paperwork. Use when user asks to OCR Hebrew documents, extract data from Israeli forms, "lesarek tofes", parse Tabu extract, read scanned tax form, or process Israeli government documents. Includes Hebrew OCR configuration, field extraction patterns, and RTL text handling. Do NOT use for handwritten Hebrew recognition (requires specialized models) or non-Israeli form processing.
Want to build your own skill? Try the Skill Creator · Submit a Skill