heygen

Generate HeyGen AI avatar videos from prompts, scripts, and uploaded assets.

Updated Apr 2, 2026
One-click install
npx skills add https://github.com/gyalamanch001a/pur-new --skill heygen-gyalamanch001a
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: heygen
Source: https://github.com/gyalamanch001a/pur-new/tree/main/.agents/skills/heygen
Command: npx skills add https://github.com/gyalamanch001a/pur-new --skill heygen-gyalamanch001a

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill removes the friction of producing AI presenter videos by turning prompts, scripts, and assets into ready-to-use HeyGen video workflows.

Core Features & Use Cases

  • Prompt-to-video generation: Create avatar-led videos from a single idea or a structured scene plan.
  • Avatar and voice control: Select public avatars, use default voices, or match voices manually for natural narration.
  • Photo avatars and templates: Generate talking photos from uploaded images or synthetic portraits, then reuse templates for scalable production.
  • Production workflows: Manage backgrounds, captions, dimensions, webhooks, polling, and Remotion compositing for finished video delivery.
  • Use case: Build product demos, executive updates, social clips, training explainers, and data-heavy presentations with consistent branding.

Quick Start

Use the heygen skill to create a polished avatar video from your script and preferred style, then follow the reference guides for avatars, voices, and video generation details.

Frequently Asked Questions about heygen

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

FAQPage Schema
How do I generate AI avatar videos from a script?

AI avatar video generation transforms your prompts, scripts, and uploaded assets into ready-to-use HeyGen video workflows. You submit a structured scene plan or single idea along with valid avatar IDs and matching voice settings to produce polished video outputs.

Can I use photo avatars and talking photos for video generation?

Photo avatars support video generation by creating talking photos from uploaded images or synthetic portraits. You provide a valid talking-photo ID and matching voice settings to animate the selected image into a narrated video.

Do I need webhooks or polling to complete asynchronous video generation?

Asynchronous video generation requires either webhooks or polling to detect completion status. You configure webhook endpoints or implement polling loops to receive the final composited video output once the rendering finishes processing.

Does Remotion compositing work with HeyGen avatar video templates?

Remotion compositing integrates with HeyGen avatar video templates to finalize production workflows. You apply Remotion compositing to combine generated avatar scenes, backgrounds, and captions into a finished, ready-to-use video output.

What are the limitations when matching voices and dimensions for avatar videos?

Avatar video generation requires valid avatar or talking-photo IDs alongside exactly matching voice and dimension settings. If the voice and dimension configurations do not match, the asynchronous rendering will fail to produce the final video output.

How do I add captions and backgrounds to AI presenter videos?

You add captions and backgrounds to AI presenter videos by configuring scene-based production settings during generation. You define background elements and enable caption layers alongside valid avatar and voice selections to render polished, branded video outputs.