dvcrn 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.
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 guidelines to structure prompts with scenes, timing, and visual styles.
With MCP tools:
- Write an optimized prompt using prompt-optimizer.md → visual-styles.md
- Call
mcp__heygen__generate_video_agentwith prompt and config (duration_sec, orientation, avatar_id) - Call
mcp__heygen__get_videowith the returned video_id to poll status and get the download URL
Without MCP tools (direct API):
- Write an optimized prompt using prompt-optimizer.md → visual-styles.md
POST /v1/video_agent/generate— see video-agent.mdGET /v2/videos/<id>— see video-status.md
Quick Reference
| Task | MCP Tool | Read |
|---|---|---|
| Generate video from prompt | mcp__heygen__generate_video_agent |
prompt-optimizer.md → visual-styles.md → video-agent.md |
| Check video status / get download URL | mcp__heygen__get_video |
video-status.md |
| Upload reference files for prompt | — | 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 - Writing effective prompts (core workflow + rules)
- references/visual-styles.md - 20 named visual styles with full specs
- references/prompt-examples.md - Full production prompt example + ready-to-use templates
- references/video-agent.md - Video Agent API endpoint details
Foundation
- references/video-status.md - Polling patterns and download URLs
- references/webhooks.md - Webhook endpoints and events
- references/assets.md - Uploading images, videos, audio as references
- references/dimensions.md - Resolution and aspect ratios
- references/quota.md - Credit system and usage limits
Best Practices
- Optimize your prompt — The difference between mediocre and professional results depends entirely on prompt quality. Always use the prompt optimizer
- Specify duration — Use
config.duration_secfor predictable length - Lock avatar if needed — Use
config.avatar_idfor consistency across videos - Upload reference files — Help the agent understand your brand/product
- Iterate on prompts — Refine based on results; Video Agent is great for quick iterations