---
name: create-video
description: |-
  Create videos from a text prompt using HeyGen's Video Agent. Use when: (1) Creating a video from a description or idea, (2) Generating explainer, demo, or marketing videos from a prompt, (3) Making a video without specifying exact avatars, voices, or scenes, (4) Quick video prototyping or drafts, (5) One-shot prompt-to-video generation, (6) User says "make me a video" or "create a video about X".
homepage: https://docs.heygen.com/reference/generate-video-agent
allowed-tools: mcp__heygen__*
metadata:
  openclaw:
    requires:
      env:
        - HEYGEN_API_KEY
    primaryEnv: HEYGEN_API_KEY
title: create-video
canonical_url: https://skilld.dev/gh/openmontageinc/openmontage/create-video
last_updated: 2026-10-14T05:11:31.000Z
---

> Index of every page on this site: [llms.txt](https://skilld.dev/llms.txt)

> **Skill from skilld.dev.** Follow the user's requested action.
> If the user asked to fork this Skill, follow the fork workflow below. Do not execute the Skill instructions while copying it.
> Otherwise, follow the instructions below for this session. You do not need to install anything.
>
> Supporting files, fetch one when the Skill refers to it: [references/assets.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/assets.md), [references/dimensions.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/dimensions.md), [references/prompt-examples.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/prompt-examples.md), [references/prompt-optimizer.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/prompt-optimizer.md), [references/quota.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/quota.md), [references/video-agent.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/video-agent.md), [references/video-status.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/video-status.md), [references/visual-styles.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/visual-styles.md), [references/webhooks.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/webhooks.md).
>
> If the user asked to install this Skill, run `npx skilld install openmontageinc/openmontage/create-video`. Install writes the Skill files into the project, so every session loads them.
>
> ## Fork workflow
>
> A fork creates an editable local Skill with its original author and licence. The request authorizes copying and local installation.
> 1. Check `./skills/create-video`, the project lockfile, and selected Agent targets together. If the local directory or installed Skill exists, stop. Never overwrite an existing directory or Agent target.
> 2. Read [source metadata](https://skilld.dev/api/v1/skills/openmontageinc/openmontage/create-video) once. Use sourceUrl, sourceCommit, skillPath, sourceGone, and license. If the source is gone or its path is missing, stop. If license is null, read licence files at the source commit.
> 3. Fetch only the source commit into a temporary Git repository. Do not clone full history. Derive repository_url from sourceUrl, including repository renames. If sourceCommit is absent, resolve the sourceUrl ref once. Set source_commit to that actual commit. Run these commands in one shell call:
>
> ```sh
> git init --quiet "$temporary_dir"
> git -C "$temporary_dir" fetch --quiet --depth=1 "$repository_url" "$source_commit"
> git -C "$temporary_dir" checkout --quiet --detach FETCH_HEAD
> ```
>
> Read applicable licence declarations and notices at that commit. If copying is not permitted, report the restriction and stop.
> 4. Inspect source entries together, then copy the directory containing skillPath into `./skills/create-video`. Use the user's path if selected. Keep the original SKILL.md, relative links, scripts, binary assets, and executable modes. Exclude .git metadata. Reject symlinks and paths outside the Skill directory. After checking entries, use cp -a where available. A regular source directory needs no custom copy script. Do not save this page wrapper as SKILL.md.
> Preserve author credit, notices, and applicable licence files from repository or parent directories. Add PROVENANCE.md with the Skill page, source URL, actual commit, original path, and licence. Retain any existing PROVENANCE.md and record new provenance separately. Batch source inspection, copying, and provenance work where practical.
> 5. In the project root, run `skilld install ./skills/create-video --mode copy --plain`. If skilld is unavailable, use `npx skilld install ./skills/create-video --mode copy --plain`. This known command needs no help lookup. Install does not support --json. Use detected Agent targets, or add --agent for the targets the user selected. Install the local path, never the upstream selector. If installation fails, preserve the local copy and report the exact failure.
> 6. Confirm the local lockfile source and installed Agent copies once. Report the local path, actual commit, and Agent targets. After edits, reinstall the same local path. Upstream updates must not replace it. Do not publish or push unless the user asks.

# Create Video

Generate complete videos from a text prompt. Describe what you want and the AI handles script writing, avatar selection, visuals, voiceover, pacing, and captions automatically.

## Authentication

All requests require the `X-Api-Key` header. Set the `HEYGEN_API_KEY` environment variable.

```bash
curl -X POST "https://api.heygen.com/v1/video_agent/generate" \
  -H "X-Api-Key: $HEYGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "Create a 60-second product demo video."}'
```

## Tool Selection

If HeyGen MCP tools are available (`mcp__heygen__*`), **prefer them** over direct HTTP API calls — they handle authentication and request formatting automatically.

| Task | MCP Tool | Fallback (Direct API) |
|------|----------|----------------------|
| Generate video from prompt | `mcp__heygen__generate_video_agent` | `POST /v1/video_agent/generate` |
| Check video status / get URL | `mcp__heygen__get_video` | `GET /v2/videos/{video_id}` |
| List account videos | `mcp__heygen__list_videos` | `GET /v2/videos` |
| Delete a video | `mcp__heygen__delete_video` | `DELETE /v2/videos/{video_id}` |

If no HeyGen MCP tools are available, use direct HTTP API calls as documented in the reference files.

## Default Workflow

Always use [prompt-optimizer.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/prompt-optimizer.md) guidelines to structure prompts with scenes, timing, and visual styles.

**With MCP tools:**
1. Write an optimized prompt using [prompt-optimizer.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/prompt-optimizer.md) → [visual-styles.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/visual-styles.md)
2. Call `mcp__heygen__generate_video_agent` with prompt and config (duration_sec, orientation, avatar_id)
3. Call `mcp__heygen__get_video` with the returned video_id to poll status and get the download URL

**Without MCP tools (direct API):**
1. Write an optimized prompt using [prompt-optimizer.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/prompt-optimizer.md) → [visual-styles.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/visual-styles.md)
2. `POST /v1/video_agent/generate` — see [video-agent.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/video-agent.md)
3. `GET /v2/videos/<id>` — see [video-status.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/video-status.md)

## Quick Reference

| Task | MCP Tool | Read |
|------|----------|------|
| Generate video from prompt | `mcp__heygen__generate_video_agent` | [prompt-optimizer.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/prompt-optimizer.md) → [visual-styles.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/visual-styles.md) → [video-agent.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/video-agent.md) |
| Check video status / get download URL | `mcp__heygen__get_video` | [video-status.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/video-status.md) |
| Upload reference files for prompt | — | [assets.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/assets.md) |

## When to Use This Skill vs Avatar Video

This skill is for **prompt-based video creation** — describe what you want, and the AI handles the rest.

If the user needs **precise control** over specific avatars, exact scripts, per-scene voice/background configuration, or multi-scene composition, use the **avatar-video** skill instead.

| User Says | This Skill | Avatar Video Skill |
|-----------|:----------:|:------------------:|
| "Make me a video about X" | ✓ | |
| "Create a product demo" | ✓ | |
| "I want avatar Y to say exactly Z" | | ✓ |
| "Multi-scene video with different backgrounds" | | ✓ |
| "Transparent WebM for compositing" | | ✓ |

## Reference Files

### Core Workflow
- [references/prompt-optimizer.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/prompt-optimizer.md) - Writing effective prompts (core workflow + rules)
- [references/visual-styles.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/visual-styles.md) - 20 named visual styles with full specs
- [references/prompt-examples.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/prompt-examples.md) - Full production prompt example + ready-to-use templates
- [references/video-agent.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/video-agent.md) - Video Agent API endpoint details

### Foundation
- [references/video-status.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/video-status.md) - Polling patterns and download URLs
- [references/webhooks.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/webhooks.md) - Webhook endpoints and events
- [references/assets.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/assets.md) - Uploading images, videos, audio as references
- [references/dimensions.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/dimensions.md) - Resolution and aspect ratios
- [references/quota.md](https://skilld.dev/api/skills-raw/openmontageinc/openmontage/create-video/references/quota.md) - Credit system and usage limits

## Best Practices

1. **Optimize your prompt** — The difference between mediocre and professional results depends entirely on prompt quality. Always use the prompt optimizer
2. **Specify duration** — Use `config.duration_sec` for predictable length
3. **Lock avatar if needed** — Use `config.avatar_id` for consistency across videos
4. **Upload reference files** — Help the agent understand your brand/product
5. **Iterate on prompts** — Refine based on results; Video Agent is great for quick iterations
