Two modes, honest costs
Most 'AI video translation' tools sell you a dub whether you need one or not. Captions-only keeps your original audio and costs a fraction; the full dub exists for when sounding native actually matters.
Translate a video — captions or a full dub — from one message
Hand Claude a finished video and a target language. It comes back with translated word-by-word captions burned in — or, when the video needs to sound native, a full AI voice dub. Spanish, Japanese, Arabic and 16 more.
You type
Translate my latest video to Spanish — captions only is fine.
…and Claude drives the whole pipeline below on your machine.
Why this beats a blank script box
Word-timed, not subtitle-file-timed
The translation is re-timed against Whisper's word-level timestamps, so the burned-in captions land word by word with the speech — not drifting SRT blocks.
19 languages, one conversation
es, ja, ar, de, pt, hi, ko, zh and more. Rolling one short out to three markets is three chat messages — each an independent render you approve first.
How Claude translates and dubs a video
-
Point at the video
A file on disk works directly; a ViralMint-generated video is resolved via get_video to its local path.
-
Pick captions or dub
captions_only keeps your original voice and burns translated word-by-word captions over it — the cheap option. full_dub adds an AI voice speaking the translation, for when the video must sound native.
-
See the price first
Claude runs tool_cost_estimate before a full dub — dubbing bills the translation plus TTS per ~1,000 characters, and you approve before anything renders.
-
Get the localized mp4
tool_translate renders locally with Whisper-timed captions; wait_for_job hands back the finished file's path. One call per language for multi-language rollouts.
MCP tools it calls:
tool_translatetool_cost_estimateget_videowait_for_job Connect it in 4 steps
-
Install ViralMint
Download the free, open-source desktop app (macOS / Windows / Linux) and open it. It bundles the whole pipeline — yt-dlp, Whisper, FFmpeg — and the MCP server.
-
Open the in-app MCP page
It shows your loopback endpoint and a bearer token, with a ready-to-paste Claude Code command and a JSON config snippet for Cursor / Claude Desktop.
-
Add the server to your agent
Paste the command. Your client loads ViralMint's tools, the built-in workflow recipes (this skill is one) and read-only resources like your balance and recent videos.
-
Ask for the outcome
Type the prompt above. Claude runs the recipe end-to-end against the local app and hands you the finished mp4 — no clicking through the UI.
ViralMint skills vs typical agent video tools
| What matters | Typical paid agent tools | ViralMint |
|---|---|---|
| Agent tools / skills | Behind a paid tier | Free & open-source (AGPL) |
| Where it runs | Their cloud | Your machine (loopback MCP) |
| Your footage & data | Uploaded to their servers | Stays local — only AI calls leave |
| Pricing | Monthly subscription | Prepaid, pay-per-render at ~cost |
| Output watermark | On free tiers | Never |
| Script quality | Prompt → generic script | Grounded in real breakouts + your data |
highlighted column = clearer fit.
FAQ
Frequently asked
What's the difference between captions-only and a full dub?
Captions-only keeps the original audio and burns translated word-by-word captions over it — best when the new audience just needs to read along, and much cheaper. Full dub additionally generates an AI voice speaking the translation (Gemini TTS voices), billed per ~1,000 characters on top.
Which languages are supported?
19: English, Spanish, French, German, Italian, Portuguese, Dutch, Polish, Russian, Japanese, Korean, Chinese, Arabic, Hindi, Turkish, Swedish, Danish, Norwegian and Finnish.
Does it work on videos I didn't make in ViralMint?
Yes — any local video file works. Claude passes the file path straight to the translate tool; only the rendering itself runs through ViralMint.
Can I make a fresh video directly in another language instead?
Yes, and it's often better: have Claude write the script in the target language and render it with the Topic → Viral Short skill. Translate & Dub is for localizing a video that already exists.
Make {skill.name.toLowerCase()} from a chat
Install the free ViralMint desktop app, connect it to Claude Code or Cursor, and run this skill — no subscription, no watermark, your footage never leaves your machine.