create-video

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Create Video

生成视频

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.

通过文本提示生成完整视频。只需描述你的需求，AI会自动完成脚本撰写、虚拟形象选择、视觉制作、旁白录制、节奏把控和字幕添加等工作。

Authentication

身份验证

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."}'

所有请求均需携带

X-Api-Key

请求头。请设置

HEYGEN_API_KEY

环境变量。

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

工具选择

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.

如果HeyGen MCP工具可用（

mcp__heygen__*

），优先使用这些工具而非直接调用HTTP API——它们会自动处理身份验证和请求格式。

任务	MCP工具	备选方案（直接调用API）
通过提示生成视频	`mcp__heygen__generate_video_agent`	`POST /v1/video_agent/generate`
检查视频状态 / 获取视频链接	`mcp__heygen__get_video`	`GET /v2/videos/{video_id}`
列出账号下的视频	`mcp__heygen__list_videos`	`GET /v2/videos`
删除视频	`mcp__heygen__delete_video`	`DELETE /v2/videos/{video_id}`

若没有可用的HeyGen MCP工具，请按照参考文档中的说明直接调用HTTP API。

Default Workflow

默认工作流

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_agent
```
with prompt and config (duration_sec, orientation, avatar_id)
Call
```
mcp__heygen__get_video
```
with 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.md
```
GET /v2/videos/<id>
```
— see video-status.md

请始终遵循prompt-optimizer.md中的指南，构建包含场景、时长和视觉风格的提示词。

使用MCP工具时：

参考prompt-optimizer.md → visual-styles.md编写优化后的提示词
调用
```
mcp__heygen__generate_video_agent
```
，传入提示词和配置参数（duration_sec、orientation、avatar_id）
使用返回的video_id调用
```
mcp__heygen__get_video
```
，轮询视频状态并获取下载链接

不使用MCP工具时（直接调用API）：

参考prompt-optimizer.md → visual-styles.md编写优化后的提示词
调用
```
POST /v1/video_agent/generate
```
——详见video-agent.md
调用
```
GET /v2/videos/<id>
```
——详见video-status.md

Quick Reference

快速参考

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

任务	MCP工具	参考文档
通过提示生成视频	`mcp__heygen__generate_video_agent`	prompt-optimizer.md → visual-styles.md → video-agent.md
检查视频状态 / 获取下载链接	`mcp__heygen__get_video`	video-status.md
上传提示词参考文件	—	assets.md

When to Use This Skill vs Avatar Video

本技能与Avatar Video技能的适用场景对比

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"		✓

本技能适用于基于提示词的视频创作——只需描述需求，其余工作由AI完成。

如果用户需要对特定虚拟形象、精确脚本、逐场景语音/背景配置或多场景合成进行精准控制，请使用avatar-video技能。

用户需求	本技能	Avatar Video技能
“帮我做一个关于X的视频”	✓
“制作一个产品演示视频”	✓
“我想要虚拟形象Y准确说出Z内容”		✓
“制作包含不同背景的多场景视频”		✓
“用于合成的透明背景WebM视频”		✓

Reference Files

参考文件

Core Workflow

核心工作流

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

references/prompt-optimizer.md - 编写高效提示词的指南（核心工作流+规则）
references/visual-styles.md - 20种命名视觉风格及完整规格
references/prompt-examples.md - 完整的生产级提示词示例+可直接使用的模板
references/video-agent.md - Video Agent API端点详情

Foundation

基础文档

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

references/video-status.md - 轮询模式与下载链接说明
references/webhooks.md - Webhook端点与事件说明
references/assets.md - 上传图片、视频、音频作为参考文件的指南
references/dimensions.md - 分辨率与宽高比说明
references/quota.md - 积分体系与使用限制说明

Best Practices

最佳实践

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_sec
```
for predictable length
Lock avatar if needed — Use
```
config.avatar_id
```
for 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

优化提示词——平庸结果与专业级结果的差距完全取决于提示词质量，请务必使用提示词优化工具
指定时长——使用
```
config.duration_sec
```
参数确保视频时长符合预期
按需锁定虚拟形象——使用
```
config.avatar_id
```
参数保证多段视频的虚拟形象一致性
上传参考文件——帮助Agent更好地理解你的品牌/产品
迭代优化提示词——根据生成结果不断完善提示词，Video Agent非常适合快速迭代