
VideoCaptioner Subtitles
Transcribe video speech, polish and translate subtitles, and burn them into video
- Repository
- HKUDS/CLI-Anything
- Stars
- 58,084
- Licence
- Apache-2.0
- Files
- 1 file
What it does
Once installed, the agent can run a command-line video captioning tool. It can turn speech in a video into subtitle files, clean up and translate those subtitles into one of about 38 languages, and either attach them to the video or permanently burn them into the picture. It can also render a single preview frame to check subtitle wording against an approved script before the final export.
Great for
- Creators who want quick subtitles and translations for short videos
- Marketers localising a promotional video into several languages
- Students or researchers transcribing lecture recordings
Skip it if
- Sensitive or confidential recordings, because the optional whisper-api and online translators send content to external services (the file does not say what they retain)
- Users who cannot install Python 3.10-3.12 and FFmpeg, since setup will fail without them
- Work needing guaranteed subtitle styling control, since the skill says advanced style flags depend on the installed backend version
Try asking
- “Transcribe interview.mp4 into English subtitles and burn them into the video”
- “Translate my subtitles.srt into Japanese using the free Bing translator”
- “Run the full pipeline on this clip and output a hard-subtitled version”
- “Render a single preview frame from video.mp4 to check the subtitles against my script”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.
cli-anything-videocaptioner.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip cli-anything-videocaptioner.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip cli-anything-videocaptioner.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Run the styles command first to confirm which style options your installed backend supports before relying on them
- Use the --json flag so the agent can parse output paths reliably
- Start with the default free bijian transcription and Bing translator to test the workflow without any API keys
What's inside
- SKILL.md
Redistributed unmodified from HKUDS/CLI-Anything under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.