video-subtitles_skill

This skill generates movie-style subtitles from video or audio, supports Hebrew and English transcription, translation, and optional burn-in into video.

Python

2.5k

GitHub Stars

2

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill openclaw/skills --skill video-subtitles

_meta.json283 B
SKILL.md2.2 KB

Overview

This skill generates movie-style SRT subtitles from video or audio files, with strong Hebrew and English transcription support and optional translation. It can produce timestamped SRT files, plain transcripts, or hardcode (burn) subtitles into video for universal playback on platforms like WhatsApp. The tool auto-detects language and picks the best model, using ivrit.ai for Hebrew and Whisper for English.

How this skill works

The skill transcribes input audio using ivrit.ai for Hebrew and OpenAI Whisper large-v3 for English, or auto-selects the model based on detected language. It formats output into natural subtitle breaks (max 42 chars/line, 1–7s per cue), can translate Hebrew to English, and writes SRT files. Optionally it uses ffmpeg to burn subtitles into the video creating a hardcoded MP4 that displays across all players.

When to use it

Create accurate Hebrew or English captions for uploaded videos
Produce SRT files for accessibility, SEO, or editing workflows
Hardcode subtitles for platforms that don’t support soft subtitles (e.g., WhatsApp, Instagram stories)
Translate Hebrew dialogue into English for multilingual audiences
Generate plain transcripts for indexing, notes, or content repurposing

Best practices

Preprocess audio quality where possible (reduce noise, normalize levels) to improve transcription accuracy
Force the input language when auto-detection fails using the --lang flag
Use --srt for editable subtitles and --burn when hardcoding is required for playback compatibility
Verify and lightly proofread critical translations or timestamps before publishing
Install ffmpeg-full for reliable burn-in rendering and allow model downloads (≈3GB) on first run

Example use cases

Add captions to marketing videos for social media and increase engagement
Create an English subtitle track for Hebrew interviews or talks
Hardcode subtitles into a video for WhatsApp shareability
Generate plain transcripts for episode show notes or search indexing
Produce SRT files to import into editors or subtitle platforms

FAQ

The skill supports Hebrew (ivrit.ai) and English (OpenAI Whisper). It can auto-detect language or you can force it with --lang.

How do I make subtitles appear on all devices?

Use the --burn option to hardcode subtitles into the video with ffmpeg; burned-in subtitles are always visible regardless of player.