About krillinai-subtitle
A KrillinAI CLI skill for generating source-language, target-language, and bilingual subtitles from video media. It covers caption selection, transcription fallback, and optional video preparation.
Key features
- 01Platform captions with Whisper fallback
- 02Local files and supported media links
- 03Source and target language selection
- 04Bilingual and single-language SRT outputs
- 05Optional video preparation and dry-run
Use cases
- 01Create subtitles from a YouTube video
- 02Translate captions for a local video
- 03Prepare a video for later rendering
Install
Copy the command and run it in a terminal.
$
npx skills add https:/ / github.com/ krillinai/ opencreator --skill krillinai-subtitleAfter installing, type/krillinai-subtitlein Claude Code to confirm it loaded.
Details
From the project READMEKrillinAI Subtitle
Use this skill for the subtitle stage. Read skills/krillinai-cli/references/cli-contract.md first for binary location, execution working directory, configuration, and JSON behavior.
Command
(cd "$KRILLINAI_CWD" && "$KRILLINAI_CLI" subtitle "<input>" \
--origin-lang en \
--target-lang zh_cn \
--workdir "$WORKDIR" \
--caption-source any \
--prepare-video)
Inputs
- YouTube URL: prefer
--caption-source any; platform captions are used first, then Whisper fallback. - Local file: use
local:/abs/path/video.mp4or a path accepted by the CLI. - Bilibili or other yt-dlp supported links: use when media download works; platform caption behavior may differ, so expect transcription fallback.
Important Flags
| Flag | Use |
|---|---|
--origin-lang | Source language, such as en, zh, ja |
--target-lang | Target language, such as zh_cn |
--workdir | Dedicated task directory |
--caption-source any | Prefer platform captions, fallback to transcription |
--caption-source whisper | Force transcription |
--prepare-video | Require the original video for later render stages |
--bilingual-top=true | Put target language on top in bilingual SRT |
--subtitle-style-file | Merge a JSON subtitle-style override |
--dry-run | Validate without downloads or AI calls |
Outputs
After a real run, read paths from krillinai_manifest.json. Main files:
origin_language_srt.srttarget_language_srt.srtbilingual_srt.srtshort_origin_mixed_srt.srtorigin_video.mp4when media preparation produced or required videoorigin_audio.mp3when transcription preparation produced audio
subtitle --dry-run validates command shape but does not write a manifest or output files.
Verification
- Require terminal JSON with
"ok": true. - Confirm
krillinai_manifest.jsonexists under--workdir. - Spot-check
bilingual_srt.srtordering andshort_origin_mixed_srt.srtreadability. - When
--prepare-videowas requested, require a non-emptyorigin_videooutput. - For Agent integration details, read
skills/krillinai-cli/references/cli-contract.md.
Comments
Markdown supported