Multi-language video subtitle translation and automatic dubbing skill (supports English, Chinese, Japanese, Spanish, French, German, Korean, etc.).
1 installs
Design & media
VMEG Audio/Video Translation, Subtitle Translation, and Dubbing
Try itUse when the user needs video/audio/subtitle translation, material and task management, script editing, or export via VMEG in an AI coding assistant or OpenClaw agent. Requires VMEG Remote MCP (OAuth or vmeg_sk API Key). Tool usage follows MCP server instructions.
What it does
Use when the user needs video/audio/subtitle translation, material and task management, script editing, or export via VMEG in an AI coding assistant or OpenClaw agent. Requires VMEG Remote MCP (OAuth or vmeg_sk API Key). Tool usage follows MCP server instructions.
The skill document
VMEG Media Translation
Call vmeg_* tools via VMEG Remote MCP (https://www.vmeg.ai/api/mcp).
Authentication
Choose one (see references/oauth.md):
- OAuth — browser login and project selection in the client (recommended for individuals)
- API Key —
Authorization: Bearer vmeg_sk_xxx(recommended for scripts/automation)
Instruction priority
- MCP server instructions (highest) — injected automatically after connecting. Follow strictly; do not override with this Skill.
- This Skill — when to enable, connection prerequisites, platform doc routing, install/troubleshooting entry points.
- references/tools.md — read only when the user asks what tools exist or what they do (quick reference, no parameter details).
- install / setup / oauth / README — read only when the user asks about install, OAuth, API Key, or MCP connection failures.
Platform detection and doc routing (Agent must read)
- Detect current platform from the runtime (e.g. Cursor →
cursor; Claude Code →claude-code; OpenClaw →openclaw). If unclear, ask the user; do not guess. - Read only one setup file:
references/setup-{platform}.md(see table below). Do not read allsetup-*.mdfiles. - MCP UI operations — do not rely on hardcoded shortcuts or menu paths in this Skill. Instead:
- Search MCP or Model Context Protocol in the current agent's Command Palette / Settings
- Or read that platform's official docs / built-in help (e.g. cursor-guide in Cursor; OpenClaw Control UI
/settings/mcp) - Optionally read the user's local MCP config (e.g.
~/.cursor/mcp.json,~/.openclaw/openclaw.json) to verify setup
- VMEG-specific content (endpoint, OAuth/API Key, config examples, presigned upload): read the current platform's setup file + setup-common.md + oauth.md.
| Current platform | Read |
|---|---|
| Cursor | setup-cursor.md |
| Claude Code | setup-claude-code.md |
| Windsurf | setup-windsurf.md |
| Codex | setup-codex.md |
| Gemini CLI | setup-gemini-cli.md |
| Antigravity | setup-antigravity.md |
| QoderWork | setup-qoderwork.md |
| WorkBuddy | setup-workbuddy.md |
| OpenClaw | setup-openclaw.md |
Prerequisites
Remote MCP must be configured and tools available. If vmeg_* tools are not callable, do not guess business parameters; follow routing above, read setup + oauth, and guide the user to connect in the current platform's MCP settings.
Coding Agent supplement (fallback when MCP instructions do not cover)
When the user provides a local video/audio absolute path (OAuth: presigned upload recommended):
- Use that path; do not scan the whole filesystem
- Compute file MD5 (
md5sum/certutil -hashfile) - Call
vmeg_initiate_material_upload(fileHash+extName) - If not deduplicated:
curl -X PUT --upload-file @/path/to/file.ext ""(no VMEG Bearer) - Call
vmeg_complete_material_upload; use returnedmaterialIdfor create-task tools
API Key alternative: one-shot curl -F to /api/mcp/material/upload (Bearer vmeg_sk_...)
When to read which doc
| Scenario | Action |
|---|---|
| Translation, materials, tasks, editing, export | Follow MCP server instructions + call MCP tools |
| User asks what tools exist / what VMEG can do | Read tools.md; invocation details still from instructions |
| MCP not connected / auth failed / how to install | install.md + platform routing: matching setup-*.md + setup-common.md + oauth.md |
| Day-to-day business | Do not read install / setup / oauth / README / tools.md |
Related skills
Use when user asks to translate videos, dub video content, or localize videos into other languages. Translate videos with AI-powered dubbing using iFlytek (X...
3 installs
Create multilingual voice-over audio from prepared scripts for videos, product launches, e-learning, training libraries, creator content, and international campaigns. This AI multilingual dubbing workflow organizes every market and segment, helps choose a locale-ready voice, pilots pronunciation and timing, and delivers reviewable narration by language. Use it for AI video dubbing audio, AI video translation audio, video localization voice-over, training video localization, global marketing narration, text to speech in multiple languages, or Chinese, English, and Japanese dubbing. Receive narration tracks organized by language, market, and segment, ready for localization editing, lip-sync production, training libraries, and campaign assembly.
Download a foreign-language movie/video (or take a local file), transcribe and translate it to English with WhisperX, and recreate the video with English subtitles. Use on requests like "get English subs for this", "translate this movie", "subtitle this YouTube film". Fully local: yt-dlp → WhisperX → ffmpeg.
Generate timecoded SRT subtitles from local video or audio files. Use when a user wants a local low-cost subtitle workflow, asks to transcribe local media in...
18 installs1 stars
video translation, video dubbing, subtitle translation, translate video to Chinese, add subtitles to video, AI dubbing, srt translation, 视频翻译, 视频配音, 字幕翻译 — transcribes a video with word-level timings, translates the subtitles, then burns them in and optionally lays down a fitted dub track. Composes the dlazy fun-asr, LLM and TTS tools with ffmpeg locally; delivers a finished mp4 plus srt files, not a script.