lattifai avatar

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-code

Installs 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)

  1. Read the caption file
  2. Translate using Claude's native ability
  3. 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
1davila7 avatarsalesforce-developmentdavila7/claude-code-templatesExpert patterns for Salesforce platform development including Lightning Web Components (LWC), Apex triggers and classes, REST/Bulk APIs, Connected Apps, and Sal192skills.sh installs
2hoodini avatarnano-banana-prohoodini/ai-agents-skillsGenerate images with Google's Nano Banana Pro (Gemini 3 Pro Image). Use when generating AI images via Gemini API, creating professional visuals, or building ima189skills.sh installs
3aiskillstore avatarhook-developmentaiskillstore/marketplaceThis skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", 188skills.sh installs
4bobmatnyc avatarmcp-builderbobmatnyc/claude-mpm-skillsMCP (Model Context Protocol) server build and evaluation guide, including local conventions for tool surfaces, config, and testing188skills.sh installs
5charleswiltgen avataraxiom-swiftui-layout-refcharleswiltgen/axiomReference — Complete SwiftUI adaptive layout API guide covering ViewThatFits, AnyLayout, Layout protocol, onGeometryChange, GeometryReader, size classes, and iO187skills.sh installs
60xsardius avatarviem0xsardius/onchain-typescript-skillsTypeScript patterns for low-level EVM blockchain interactions using Viem. Use when writing Node scripts, CLI tools, or backend services that read/write to Ether186skills.sh installs