Video Translate Skill – AI Video Translation, Dubbing & SRT Subtitles

Video Translate Skill is an AI-powered video translation workflow that translates sound from video into another language, generates timed SRT subtitles, creates dubbed speech with text-to-speech (TTS), and merges the new audio track back into the video, all in one automated pipeline.

Built on SoulDub** AI**, it translates local MP4 videos with original-voice dubbing, so the dubbed speech keeps the feel of the original speaker. When processing is finished, you can download:

• the translated video

• target-language subtitles (SRT)

• bilingual SRT subtitles

Table of Contents

• What is Video Translate Skill?

• Features

• Installation

• Requirements

• Usage

• How It Works

• Output Files

• Configuration & Privacy

• Use Cases

• FAQ

What is Video Translate Skill?

Video Translate Skill is an automated AI video translator for creators, educators, and teams who need multilingual video content. Instead of transcribing, translating, subtitling, recording voice-overs, and editing by hand, you provide a local MP4 file and the skill handles the whole workflow: speech recognition, translation, subtitle timing, TTS dubbing, and audio merging.

Features

• AI video translation – translates spoken content from one language into another.

• Original-voice dubbing – powered by SoulDub AI to keep the speaker's vocal character.

• Timed subtitle generation – produces accurate SRT subtitles synced to the speech.

• Bilingual SRT subtitles – source and target language displayed together, ideal for language learning and review.

• Text-to-speech (TTS) dubbing – generates natural-sounding speech in the target language.

• Automatic audio merging – replaces the original audio track with the dubbed one.

• Local MP4 support – works directly with MP4 files on your machine.

Installation

Install the skill for your AI agent with one command:

npx skills add jiabaogithub/souldub-skills --skill souldub-video-translate

Requirements

• Python 3.11 or later

• uv

• Internet connection

• A SoulDub API key

• Read access to the source video and write access to the output folder

Set your API key

Use either method:

# ~/.souldub/souldub.config.yaml
souldub_api_key: "YOUR_API_KEY"

export SOULDUB_API_KEY="YOUR_API_KEY"

Check authentication:

uv run scripts/video_translation.py auth status

Usage

After installation, just tell your agent the video path and the target language, for example:

Translate /path/to/video.mp4 into English with original-voice dubbing.

The agent will ask for any missing information, start the task, report progress, and return the output paths.

How It Works

1. Input – provide a local MP4 video and choose the target language.

2. Translate – the spoken audio is recognized and translated into the target language.

3. Subtitle – timed SRT subtitles are generated, including a bilingual version.

4. Dub – TTS creates the dubbed speech, with original-voice dubbing via SoulDub AI.

5. Merge – the new audio track is merged back into the video.

6. Download – get the translated video and subtitle files.

Output Files

By default, files are saved as result.mp4, translated.srt, and bilingual.srt in a souldub_outputs/ folder next to the source video.

Configuration & Privacy

• Installed skill files are treated as read-only; runtime state is stored in your platform's user state directory.

• Outputs are written to souldub_outputs/ beside the source video by default.

• The skill does not persist API keys, pre-signed upload URLs, media gateway URLs, or temporary signed parameters.

Use Cases

• Video localization for global product launches and marketing

• Course and tutorial translation for online education

• Cross-border content distribution on YouTube, TikTok, and more

• Multilingual subtitles for accessibility and language learning

FAQ

What does Video Translate Skill do? It translates the speech in a video into another language, generates SRT subtitles, creates AI dubbing with TTS, and merges the new audio into the video.

Which video format is supported? Local MP4 videos.

Can I keep the original speaker's voice? Yes. The skill uses SoulDub AI for original-voice dubbing.

What subtitle formats do I get? Target-language SRT and bilingual SRT.

If you find Video Translate Skill useful, please give the repository a ⭐ so more people can discover this AI video translation tool.