create-video

Generate videos from text prompts using HeyGen API.

46.2k|5.7k|Updated Mar 29, 2026
One-click install
npx skills add https://github.com/calesthio/OpenMontage --skill create-video
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-video
Source: https://github.com/calesthio/OpenMontage/tree/main/.agents/skills/create-video
Command: npx skills add https://github.com/calesthio/OpenMontage --skill create-video

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Create complete videos from a plain-language prompt without manually writing detailed scene-by-scene configurations, selecting avatars, or orchestrating rendering steps. The skill automates script writing, avatar selection, visuals, voiceover, pacing, captions, asset referencing, and status polling so you can move from idea to finished video quickly.

Core Features & Use Cases

  • Generate videos from a single optimized prompt using HeyGen Video Agent for quick prototyping, explainer videos, product demos, and marketing clips.
  • Prefer HeyGen MCP tools when available for authentication and request formatting, with direct API fallbacks for generate, status, list, and delete operations.
  • Support for uploading and referencing assets (images, audio, video), choosing dimensions/orientation, checking quota, and using webhooks or polling for completion.
  • Use-case examples: rapid one-shot promotional video from a brief, 60–90 second product demo, or quick social clips for testing creative concepts.

Quick Start

Generate a 60-second product demo by prompting: create a 60-second product demo video that highlights feature X in a professional tone and use HEYGEN_API_KEY for authentication.

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 without manual scene configuration?

Text-to-video generation automates script writing, avatar selection, visuals, voiceover, and pacing from a single prompt. You provide a plain-language description, and the skill handles rendering steps to produce a finished video.

What do I need to set up before using HeyGen for prompt-to-video generation?

Prompt-to-video generation requires a HEYGEN_API_KEY for authentication. You can use HeyGen MCP tools or direct API calls for requests, and optionally upload assets like images or audio before generating.

Can I use my own images and audio when creating videos from text?

Yes, asset uploading and referencing is supported for images, audio, and video. You can upload custom assets, choose dimensions or orientation, and reference them within your text prompt to include them in the final video.

When should I use one-shot text-to-video instead of scene-by-scene editing?

Use one-shot text-to-video for rapid prototyping, explainer videos, product demos, and marketing clips when exact avatar or per-scene control is not required. It moves you from idea to finished video quickly without manual orchestration.

How does video status polling work after sending a generation request?

Video status polling checks the rendering progress after you submit a generation request. The skill supports polling or webhooks to monitor completion, allowing you to retrieve the final video once the rendering is finished.

Does prompt-to-video generation support quota checks and video deletion?

Yes, quota checks are supported to verify usage limits before generation. Direct API fallbacks also provide list and delete operations, allowing you to manage generated videos and monitor available rendering quota.