VideoCaptioner skill
VideoCaptioner transcribes speech, translates subtitles and burns them into video with a single command from Claude Code.
- 16,511 ★ on the repository
- Last commit
- GPL-3.0
Extended access
Why this level
- Audio and text go to third-party recognition and translation services.
- The skill runs `videocaptioner` and `ffmpeg` on local files.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/videocaptionerDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Audio and text go to third-party recognition and translation services.
- The skill runs `videocaptioner` and `ffmpeg` on local files.
This is third-party code. Review the repository files before installing.
What it does
VideoCaptioner, a desktop app and CLI for subtitles, takes video from speech to a finished clip. Speech recognition, segmentation and text cleanup, translation and burning styled subtitles in are combined in the `videocaptioner process` command. The `skills/SKILL.md` skill lets Claude Code call only `videocaptioner`, `ffprobe` and `ffmpeg -ss`. The `bijian` and `jianying` recognizers and Bing or Google translation are free, while model-based cleanup and translation need a key. Soft and hard subtitle modes, styles such as `anime` and a rounded background are available.
Who it is for. Video creators and editors who produce subtitles and translations and want the agent in a terminal to take over the routine.
Good fit when
- A Chinese clip needs English subtitles burned into the picture.
- A call recording must become an `.srt` transcript file.
- Finished subtitles are translated into several languages with the original beside them.
- Subtitles are recolored to brand colors on a rounded background.
- An online video is downloaded and subtitled at once.
Not a fit when
- Only editing without subtitles is needed.
- The recording holds confidential speech that cannot go to external recognition services.
- A legally exact translation is needed with no human review.
Example request
Make English subtitles for video.mp4 with free tools and burn them into the clip at high quality.Limitations
The last commit in the repository dates to September 2026. FFmpeg must be installed to burn subtitles in. The free `bijian` and `jianying` recognizers rely on third-party services that may stop working, and your audio is sent to them. Model cleanup and translation need an `OPENAI_API_KEY` and spend tokens. The GPL-3.0 license requires opening the source of distributed derivative works. Documentation is in Chinese.
How to disable. Delete the `~/.claude/skills/videocaptioner` directory. Remove the program with `pip uninstall videocaptioner`.
FAQ
How do I add the skill to Claude Code?
Create `~/.claude/skills/videocaptioner` and copy `skills/SKILL.md` there. Then call `/videocaptioner transcribe video.mp4 --asr bijian`.
Is an API key needed?
Not for `bijian`/`jianying` recognition or Bing and Google translation. A key is needed for subtitle cleanup, re-segmentation and model translation.
What is needed to burn subtitles into video?
FFmpeg, which `brew install ffmpeg` installs on macOS. Without burning you can still get an `.srt` or `.ass` file.
How do I get only a subtitle file?
Run `videocaptioner transcribe video.mp4 --asr bijian -o output.srt`. For an `.ass` file with no video build, add `--format ass --no-synthesize` to `videocaptioner process`.
Can subtitles be bilingual?
Yes. The `--layout target-above` option puts the translation above the original and `--layout target-only` keeps the translation only.
Discussion
No questions or reviews yet.
Related
SkillsA Codex and Claude Code skill: subtitles and a summary from a Douyin, Xiaohongshu, Bilibili or YouTube link or a local file
A Claude Code skill that downloads a YouTube video, splits it into semantic chapters, cuts chosen clips, translates subtitles and burns bilingual ones in
A skill that transcribes video, lets you review captions in a browser and burns in Chinese and English captions.
An agent edits short talking-head videos: transcript, subtitles, B-roll and export for Xiaohongshu, Douyin and WeChat Channels
QwenASRMiniTool turns audio and video into SRT subtitles on your own computer, and Claude Code drives it via the qwenasr skill.
A video editing skill for Claude Code and Codex: the agent cuts pauses and filler words, grades color, burns subtitles and adds animated overlays
README in short
Sections on the desktop version and CLI, language model setup and installing the Claude Code skill by copying a file.