heygen

Generates AI avatar videos through the HeyGen API using prompts or scene-level configuration.

Updated Sep 1, 2026
One-click install
npx skills add https://github.com/zamansepeti43/c-rak-agent --skill heygen-zamansepeti43
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: heygen
Source: https://github.com/zamansepeti43/c-rak-agent/tree/main/video-engine/.agents/skills/heygen
Command: npx skills add https://github.com/zamansepeti43/c-rak-agent --skill heygen-zamansepeti43

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Creating talking-head videos, explainers, and presentations traditionally requires cameras, actors, and editing. This Skill connects to the HeyGen API so you can generate AI avatar videos programmatically, either from a single text prompt or with precise control over avatars, voices, scripts, and scenes. Note: This Skill is deprecated. Use create-video for prompt-based generation or avatar-video for precise avatar/scene control instead. ## Core Features & Use Cases - Prompt-Based Video Generation: Send an optimized prompt to the Video Agent API and receive a finished video, with guidance on structuring scenes, timing, and visual styles. - Precise Scene Control: Build multi-scene videos with specific avatar IDs, voice IDs, backgrounds, captions, text overlays, and dimensions via the v2 video generation endpoint. - Asset & Avatar Management: Upload images, videos, and audio, create talking-photo avatars from portraits, and poll video status to retrieve download URLs. - Use Case: A marketing team needs a 60-second product announcement video. The Skill helps write an optimized prompt, submits it to the HeyGen Video Agent, polls the status endpoint, and returns the downloadable video URL. ## Quick Start Ask the AI to generate a short HeyGen avatar video from a text prompt and return the download link once rendering completes.

Frequently Asked Questions about heygen

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

FAQPage Schema
How do I generate a video with the HeyGen API?

Send a POST request to /v1/video_agent/generate with an optimized prompt for one-shot generation, or use POST /v2/video/generate with explicit avatar_id, voice_id, and scene configuration for precise control. Both require the X-Api-Key header.

How do I check HeyGen video status and get the download URL?

Poll GET /v2/videos/{video_id} with your API key until the status shows completion. The response includes the video download URL once rendering finishes.

When should I use Video Agent versus v2 video generate?

Use the Video Agent for most requests since it handles scenes and styling from a prompt. Use v2 video generate only when you need exact scripts, specific voice IDs, different avatars per scene, or precise per-scene timing.

Can I create a talking avatar from my own photo?

Yes. Upload the image to the asset endpoint to get an image_key, create a photo avatar group, wait for processing to complete, then use the returned ID as talking_photo_id in video generation.

What are the limitations of HeyGen asset uploads?

Uploaded assets are limited to 10MB per file. Supported types include JPEG, PNG, MP4, WebM, MP3, and WAV. Images should match target video dimensions, and assets may be deleted after inactivity.