VideoCaptioner - AI video subtitling & burn-in

Name: VideoCaptioner - AI video subtitling & burn-in
Rating: 90 (1 reviews)
Author: weifeng2333

Trust Score 90/100

AI-powered video captioning: transcribe, optimize, translate, and burn styled subtitles into videos (ASS/rounded modes).

triggers:subtitletranscribesubtitle translateburn subtitlessrtvideo caption

VideoCaptioner CLI

AI-powered video captioning: transcribe speech -> optimize subtitles -> translate -> burn into video with beautiful styles.

Features

Transcription to SRT/JSON using free engines (bijian/jianying) or whisper variants.
Subtitle optimization and LLM-assisted re-segmentation/translation.
Burn subtitles into video with ASS or rounded box styles; many presets and style overrides.
Full pipeline (process) or stepwise (transcribe, subtitle, synthesize).

Usage examples

Transcribe: videocaptioner transcribe video.mp4 --asr bijian -o output.srt
Translate and burn: videocaptioner process video.mp4 --asr bijian --translator bing --target-language en --subtitle-mode hard -o output.mp4
High-quality styled subtitles: use --style anime or --render-mode rounded.

Requirements & notes

ffmpeg required for video synthesis.
Some features (LLM optimization/translation) require an OPENAI_API_KEY.
Works for audio-only files as well.

When to use

Add or improve subtitles for videos, translate subtitles, or generate styled burned-in subtitles for publishing.

Audit Summary

VideoCaptioner is a CLI wrapper skill for adding AI-powered subtitles to videos — transcription, translation, optimization, and burn-in. No bundled scripts; the skill delegates entirely to the pip-installable videocaptioner CLI. SKILL.md is well-written with 10 common scenarios, a command reference, style docs, and exit codes. Clean security posture with scoped allowed-tools and no hardcoded secrets.

Watch Out

Requires ffmpeg installed separately (brew install ffmpeg on macOS)
Free ASR engines (bijian/jianying) only support Chinese & English
LLM features (optimization, re-segmentation) require OPENAI_API_KEY

Notes

No scripts to run — pure CLI wrapper skill. Scoped Bash tool access is a good security practice. Skill is well-documented and practical.

Information

Repository: weifeng2333

Trust Score

Overall90

Security100

Code Quality82

Architecture75

Usefulness80

Related Skills

Generate Multilingual Sentences with Contextual Definitions

Produce multiple example sentences using a target word in varied meanings, translate them into a target language, and show the contextual meaning of the word fo

NotebookLM Research Agent

End-to-end research-to-content pipeline: ingest sources into Google NotebookLM, run deep cited research, generate downloadable artifacts, and produce polished c

Voice Memo Organizer

Locate, transcribe (local whisper.cpp), summarize and index Apple Voice Memos into a searchable archive with titles, themes and key quotes.

FFmpeg Guide

Comprehensive FFmpeg reference for encoding, converting, streaming, filtering, and analyzing audio/video — command examples, common patterns, and troubleshootin

Provide Raw YouTube Video ID

Return only a valid existing YouTube video ID string (no URL, no commentary) — useful for tools that need raw IDs for downstream operations.

Thesis & Paper Writing Assistant

End-to-end assistance for undergraduate and master's thesis writing: outline review, structure imitation, references, polishing, translation, and anti-AIGC de-b

YouTube Tools (yt-dlp)

Free, local YouTube operations using yt-dlp: download videos/audio, extract transcripts/subtitles, and fetch metadata (no API keys).

ScrollClaw — Assemble

Assemble UGC video campaigns: stitch A-roll, orchestrate audio, run post-production, then add mobile-friendly captions.

Back to Skills