heygen-translate

Translates videos into target languages using voice cloning and lip-sync via Hugging Face API.

386|66|Updated Jan 22, 2026
One-click install
npx skills add https://github.com/heygen-com/skills --skill heygen-translate
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: heygen-translate
Source: https://github.com/heygen-com/skills/tree/main/heygen-translate
Command: npx skills add https://github.com/heygen-com/skills --skill heygen-translate

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires mcp__heygen__*, heygen, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill translates and dubs videos, maintaining the original presenter's face and voice while delivering the content in a new language, allowing for localization and accessibility.

Core Features & Use Cases

  • Video Translation: Convert existing videos into multiple languages with voice cloning and lip-sync technology.
  • Voice Cloning and Lip-Sync: Preserve the original speaker's voice and facial expressions.
  • Use Case: Use this Skill to create multilingual versions of your videos for a global audience, maintaining consistency in presentation and brand identity.

Quick Start

Translate and dub the video at the URL 'https://example.com/your-video.mp4' into Spanish (Spain).

Frequently Asked Questions about heygen-translate

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How does video translation with voice cloning and lip-sync work?

Video translation with voice cloning and lip-sync works by processing an input video, translating the spoken audio into a target language, and then synthesizing the original presenter's voice while aligning their lip movements to match the new audio track. This preserves the speaker's face and voice for multilingual distribution.

Do I need HeyGen API access to translate and dub my videos?

Yes, you need HeyGen Video Translation API access and authentication to translate and dub your videos. This Skill requires an active HeyGen connection to handle the voice cloning, language translation, and lip-sync processing operations.

Can I translate a video URL into multiple languages for global audiences?

Yes, you can translate a video URL into multiple languages for global audiences. By providing the video input URL and specifying target languages like Spanish (Spain), the Skill handles the language translation, voice cloning, and lip-sync to generate localized content.

What is the best way to maintain a presenter's face and voice during video localization?

The best way to maintain a presenter's face and voice during video localization is using voice cloning and lip-sync technology. This approach synthesizes the original speaker's vocal characteristics and aligns facial expressions to the translated audio, ensuring brand consistency across multilingual video content.

What video formats are supported for multilingual voice cloning and lip-sync processing?

The Skill processes video content provided via a publicly accessible URL, such as an MP4 file link. It uses this video input to perform the language translation, voice cloning, and lip-sync processing required for creating accessible, multilingual video outputs.

Are there limitations when translating long videos with lip-sync technology?

The metadata does not specify exact duration limitations for translating long videos with lip-sync technology. However, processing relies entirely on the HeyGen Video Translation API, so any constraints on video length, file size, or processing times would be defined by your specific HeyGen API plan.