create-video

Generate complete videos from text prompts using the HeyGen Video Agent API.

1|Updated Aug 28, 2026
One-click install
npx skills add https://github.com/mooch10/mochiptos --skill create-video-mooch10
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: create-video
Source: https://github.com/mooch10/mochiptos/tree/main/frontend/.agents/create-video
Command: npx skills add https://github.com/mooch10/mochiptos --skill create-video-mooch10

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Creating videos traditionally requires scripting, avatar selection, scene composition, and editing. This Skill automates the entire pipeline by turning a single text prompt into a finished video through HeyGen's Video Agent, which handles script writing, visuals, voiceover, pacing, and captions automatically. ## Core Features & Use Cases - Prompt-to-Video Generation: Submit an optimized text prompt to the Video Agent API (or the mcp__heygen__generate_video_agent MCP tool) and receive a complete video with configurable duration, orientation, and avatar. - Production-Grade Prompt Engineering: Built-in prompt optimizer with 20 named visual styles, scene-by-scene layering rules, motion vocabulary, and ready-to-use templates for briefings, ads, and reports. - Status Polling and Asset Management: Poll video status, retrieve download URLs, upload reference images/audio, manage webhooks, and check credit quota. - Use Case: A marketing manager needs a 60-second product demo for social media. They describe the product and tone, the Skill structures an optimized prompt with scenes and visual style, submits it to HeyGen, and returns the downloadable video URL. ## Quick Start Ask the AI to create a 60-second landscape video introducing your product using the HeyGen Video Agent with an optimized prompt.

Frequently Asked Questions about create-video

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

FAQPage Schema
How do I generate a video from a text prompt with HeyGen?▼

Send an optimized prompt to POST /v1/video_agent/generate with your X-Api-Key header, optionally setting config.duration_sec, orientation, and avatar_id. The API returns a video_id, which you poll via GET /v2/videos/{video_id} until the status is completed.

When should I use Video Agent vs the standard HeyGen video API?▼

Use Video Agent for quick prompt-based generation where the AI handles scripting and scenes. Use the standard v2/video/generate API when you need precise control over specific avatars, exact scripts, per-scene configuration, or multi-scene composition.

How long does HeyGen video generation take?▼

Video generation typically takes 5-15 minutes, but can exceed 20 minutes during peak load or for longer scripts. Set polling timeouts of 15-20 minutes and consider webhooks for production systems instead of continuous polling.

What video dimensions and aspect ratios does HeyGen support?▼

HeyGen supports 720p and 1080p in landscape (16:9), portrait (9:16), and square (1:1) formats. Custom dimensions are allowed between 128px and 4096px per side, and both width and height must be even numbers.

Why does my Video Agent prompt produce poor quality videos?▼

Poor results usually come from layout language like screen coordinates, unnamed visual styles, B-roll scenes under 5 seconds, or content written as lists instead of narratives. Use the prompt optimizer guidelines with named styles, layered motion graphics, and scene rotation.

How do I check my remaining HeyGen API quota?▼

Call GET /v2/user/remaining_quota with your X-Api-Key header to retrieve remaining and used credits. Check quota before generating videos, since 1080p videos consume roughly 1.5x the base credit rate of 720p.