OpenParable
Skip to content
← Back to skills

Krillinai Subtitle

Documents
krillinai-subtitle

Krillinai Subtitle is an Agent Skill for documents published in the krillinai/KrillinAI repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Use when generating subtitles with KrillinAI CLI from a YouTube link, Bilibili/local video, or existing media, including platform caption download, Whisper fallback, translation, bilingual SRT, and short vertical subtitle output.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/krillinai/KrillinAI/blob/HEAD/skills/krillinai-subtitle/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/krillinai-subtitle, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

KrillinAI Subtitle

Use this skill for the subtitle stage.

Command

./build/krillinai-cli subtitle "<input>" \
  --origin-lang en \
  --target-lang zh_cn \
  --workdir tasks/demo \
  --caption-source any

Build the CLI first if needed:

go build -o build/krillinai-cli ./cmd/cli

Inputs

  • YouTube URL: prefer --caption-source any; platform captions are used first, then Whisper fallback.
  • Local file: use local:/abs/path/video.mp4 or 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

FlagUse
--origin-langSource language, such as en, zh, ja
--target-langTarget language, such as zh_cn
--workdirDedicated task directory
--caption-source anyPrefer platform captions, fallback to transcription
--caption-source whisperForce transcription
--bilingual-top=truePut target language on top in bilingual SRT
--dry-runValidate without downloads or AI calls

Outputs

Read paths from krillinai_manifest.json. Main files:

  • origin_language_srt.srt
  • target_language_srt.srt
  • bilingual_srt.srt
  • short_origin_mixed_srt.srt
  • origin_video.mp4
  • origin_audio.mp3

Verification

  • Confirm stdout JSON has "ok": true.
  • Confirm krillinai_manifest.json exists under --workdir.
  • Spot-check bilingual_srt.srt ordering and short_origin_mixed_srt.srt readability.
  • For Agent integration details, read skills/krillinai-cli/references/cli-contract.md.