✦ Agent Skill

Dub a video into another language in the speaker's voice

Have your AI agent dub a video line by line into another language, in your own voice

Author CWYZLevel Intermediate
5.0
$5.00one-time, yours to keep
Become a member, use every skill for freeMembers also publish their own skills and tutorials.

Sign in to copy the install prompt or download the files.

Use when the user wants to dub a video into another language while keeping the original speaker's voice. Transcribes the original locally with timestamps, translates line by line to fit each line's duration, synthesizes each line in the original speaker's cloned voice with F5-TTS, places each line back at its original time point (speeding up by at most 1.25x), then swaps in the new audio track and generates subtitles. Includes a Chinese polyphone replacement table. Everything runs locally for free. The official F5-TTS model only supports Chinese and English, and its pretrained model is not licensed for commercial use.

Updated Nov 14, 2026

Skill name

video-dub

Output

Works with

Claude CodeCodexAny agent that reads SKILL.md

Access

$5.00, free for members

Related tutorials and cases

Tutorial

Let Your AI Agent Dub Your Video in Your Own Voice

Beginner tutorial: Use our own local method for bilingual videos to have your AI agent transcribe the original with timestamps, translate each line to fit its duration, clone the original voice with F5-TTS to synthesize line by line and place each line back at its original time, then swap in the new audio track and subtitles. Covers how to fix misread Chinese polyphones, with 3 prompts you can copy and paste.

Tutorial

Free AI Voiceover in Your Own Voice, Right on Your Computer

Beginner tutorial: Download Booth, a free open-source app, and make AI voiceovers on your own computer with the ZONOS3-Mini model. Start with preset voices to tune emotion and speed, generate several takes per line and keep the best one, then clone your own voice and let your AI agent voice a whole script in batches. Your scripts and recordings stay on your computer, with no sign-up or subscription. Includes 2 copy-ready prompts.

Tutorial

Let Your AI Agent Upscale AI Videos to HD

Intermediate tutorial: pick a route for your computer, draft a low-res test clip with the open-weight MiniMax H3, then let your AI agent install the open-source ReCaVSR upscaler, choose a model for your GPU memory, and upscale shot by shot to 2K-plus before stitching the film together. Mac and no-GPU paths included, with two copy-paste prompts.

Tutorial

Let Your AI Agent Make Explainer Animation Videos on Your Own Computer for Free

Beginner tutorial: Install Remotion's official Agent Skills so your AI agent can build an explainer animation on your own computer, storyboard it first, preview it scene by scene, and export an MP4 only when you say so, free for individuals and companies of up to three people, includes 3 copy-ready prompts

Similar skills

All skills

What you get

  • A video in a new language with the original voice
  • Matching new subtitles
  • Pronunciation fixes for Chinese polyphonic characters

Good for

  • People who want to make bilingual Chinese-English versions of their own videos
  • Creators who don't want to pay for dubbing services

Not for

  • Languages other than Chinese and English
  • Projects meant for commercial use (the pretrained models can't be used commercially)

About this skill

Lets your AI agent dub a video into another language while keeping the original speakers' voices. It transcribes on your own machine, translates sentence by sentence, clones the original voice to synthesize the new lines, then puts them back at the original timestamps, swaps in the new audio track and generates subtitles. All local and free.

What you need

  • ffmpeg
  • Python 3, plus two open-source tools: faster-whisper for transcription and F5-TTS for cloning a voice. The models take up several GB of disk space
  • One video with a clean 5 to 10 second clip of one person speaking, with no background noise
  • No API key needed. Everything runs on your own computer, and it costs nothing
  • The official F5-TTS model only supports Chinese and English, and it cannot be used commercially

FAQ

Can I clone anyone's voice?

No. Only clone a voice you have the right to use: your own, or the voice of someone who has agreed to it.

Can I dub into Japanese or Spanish?

The default model only supports Chinese and English. For other languages, switch to a different open-source model. The other steps stay the same.

What if the translated sentence is longer than the original and does not fit?

It speeds the audio up to 1.25 times at most. If it still does not fit, it lists that sentence so you can shorten it. It will not squeeze the audio in or cut words to make it fit.

What if a word with multiple readings is pronounced wrong?

Swap the word for a different character with exactly the same pronunciation, then generate the audio again. The subtitles still show the correct character.

Can I use it commercially?

The default voice model cannot be used commercially. If you need commercial use, tell your AI agent. It will suggest a model that allows commercial use.

This is an outline. The full SKILL.md comes with the install: sign in, then copy the prompt or download.

REVIEWS

5.0

0 reviews

Rate this skill

No reviews yet.

Used this skill? Be the first to rate it.

Done with this one? Mark it to track your path.Sign in
Save it for laterSign in
Questions about this piece?Ask AI about this