
Omnicaptions Translate
Translates caption files to other languages with context awareness instead of mechanical line-by-line conversion. Uses Claude by default (no API needed), or you can opt into Gemini. The context window approach means it processes 30 lines at a time with 5 lines before and after for reference, so split dialogue and pronoun usage actually make sense. Handles bilingual output if you want original plus translation side by side. Works with SRT, VTT, ASS and other formats. The workflow guidance is solid: convert LaiCut's word-level JSON to SRT first since translation only needs segment text, saving you 90% file size.
- skills.sh installs
- 193
- GitHub stars
- 24
- last updated
- Aug 21, 2026
Install
$ npx -y skills add lattifai/omni-captions-skills --skill omnicaptions-translate --agent claude-codeInstalls into .claude/skills of the current project.
Files
Caption Translation
Default: Claude native translation (no API key needed)
Use Gemini API only when user explicitly requests it.
Default Workflow (Claude)
- Read the caption file
- Translate using Claude's native ability
- Write output with
_Claude_{lang}suffix
Gemini API (Optional)
Use CLI when user requests Gemini:
omnicaptions translate input.srt -l zh --bilingual
Output: input_Gemini_zh.srt
When to Use
- Translate SRT/VTT/ASS to another language
- Generate bilingual captions (original + translation)
- Translate YouTube video transcripts
- Need context-aware translation (not line-by-line)
When NOT to Use
- Need transcription (use
/omnicaptions:transcribe) - Just format conversion without translation (use
/omnicaptions:convert)
Setup
pip install omni-captions-skills --extra-index-url https://lattifai.github.io/pypi/simple/
API Key
Priority: GEMINI_API_KEY env → .env file → ~/.config/omnicaptions/config.json
If not set, ask user: Please enter your Gemini API key (get from https://aistudio.google.com/apikey):
Then run with -k <key>. Key will be saved to config file automatically.
Sponsors
Details
- Repository
- github.com/lattifai/omni-captions-skills
- Categories
- Backend & APIs, Automation & Workflows
- First seen
- Jun 3, 2026