> ## Documentation Index
> Fetch the complete documentation index at: https://heygen-1fa696a7.mintlify.app/llms.txt
> Use this file to discover all available pages before exploring further.
# Training & Onboarding Videos
> Produce corporate training and employee onboarding videos at scale via the HeyGen API. Update scripts and regenerate in minutes when policy or process changes.
## The Problem
Corporate training content is expensive to produce, goes stale fast, and doesn't scale across languages. A single compliance training video can cost $5,000–$15,000 to produce professionally — and needs to be re-recorded every time a policy changes.
## How It Works
```
Training docs/policies → LLM structures into video modules → Video Agent renders → Translate for global teams
```
Generate training videos from your existing materials. When the source document updates, regenerate the video. Need it in 10 languages? Use Video Translation.
## Build It
Break content into modules. Each module becomes a separate video — this keeps videos short (2–5 minutes) and makes updates surgical.
```python theme={null}
modules = [
{
"title": "Data Privacy Basics",
"source": "policies/data-privacy.pdf",
"duration": "3 minutes",
"style": "professional, clear, reassuring",
},
{
"title": "Handling Customer Data",
"source": "policies/data-handling.md",
"duration": "4 minutes",
"style": "professional, specific, example-driven",
},
{
"title": "Reporting a Breach",
"source": "policies/breach-response.md",
"duration": "2 minutes",
"style": "urgent but calm, step-by-step",
},
]
```
Use an LLM to convert each training document into a structured video prompt. The LLM acts as an instructional designer.
```python theme={null}
import anthropic
client = anthropic.Anthropic()
def generate_training_prompt(module, content):
message = client.messages.create(
model="claude-sonnet-4-20250514",
max_tokens=1500,
messages=[{
"role": "user",
"content": f"""You are an instructional designer creating a training
video from a policy document. Convert this into a HeyGen Video Agent prompt.
Structure the video as:
1. Introduction (10s) — What this training covers and why it matters
2. Key concepts (60-70% of duration) — Break into 2-4 clear sections
with specific examples and scenarios employees will recognize
3. Do's and Don'ts (15s) — Quick visual checklist
4. Summary + quiz teaser (10s) — Recap key points, prompt to take the quiz
Requirements:
- Tone: {module['style']}
- Duration: {module['duration']}
- Use text overlays for key terms and definitions
- Include scenario-based examples ("Imagine you receive an email from...")
- Make it engaging — this isn't a lecture, it's a conversation
Training document:
{content}
Output ONLY the Video Agent prompt."""
}],
)
return message.content[0].text
# Generate prompt for each module
for module in modules:
with open(module["source"]) as f:
content = f.read()
module["video_prompt"] = generate_training_prompt(module, content)
```
Submit each module to Video Agent. Space them out for rate limits.
```python theme={null}
import requests
import time
HEYGEN_API_KEY = "your-api-key"
for module in modules:
resp = requests.post(
"https://api.heygen.com/v3/video-agents",
headers={
"X-Api-Key": HEYGEN_API_KEY,
"Content-Type": "application/json",
},
json={
"prompt": module["video_prompt"],
# Optional: attach policy document for visual context
# "files": [{"type": "url", "url": "https://..."}]
},
)
module["video_id"] = resp.json()["data"]["video_id"]
print(f"Submitted: {module['title']} → {module['video_id']}")
time.sleep(5)
```
Then poll for completion — see [Video Agent docs](/docs/video-agent) for the polling pattern.
Once your English videos are ready, translate them for every region in one batch.
```python theme={null}
languages = ["es", "fr", "de", "ja", "zh", "pt", "ko"]
for module in modules:
resp = requests.post(
"https://api.heygen.com/v2/video_translate",
headers={
"X-Api-Key": HEYGEN_API_KEY,
"Content-Type": "application/json",
},
json={
"video_url": module["video_url"],
"output_languages": languages,
},
)
module["translations"] = resp.json()
print(f"Translating {module['title']} into {len(languages)} languages")
```
See [Video Translation docs](/docs/video-translate) for speed vs precision mode and all supported languages.
## Training Categories
This workflow applies to any training content:
| Category | Source material | Key considerations |
| --------------------------------- | ------------------------------------- | ---------------------------------------------------- |
| **Compliance** (HIPAA, GDPR, SOX) | Regulatory docs, policies | Must be accurate, auditable, up-to-date |
| **Onboarding** | Employee handbook, culture docs | Warm and welcoming tone, company-specific |
| **Software training** | Help docs, screenshots | Attach screenshots as file inputs for visual context |
| **Safety** | Safety procedures, SOPs | Clear, step-by-step, scenario-based |
| **Sales enablement** | Product knowledge, objection handling | Conversational, example-heavy |
## Keeping Videos in Sync
The biggest advantage of generated training videos: **when the policy changes, regenerate the video.**
```
Policy doc updated → Detect change (git diff, CMS webhook, manual trigger)
→ Re-run the same pipeline
→ New video replaces the old one
→ Re-translate if needed
```
No re-recording, no scheduling a film crew, no editing. Just re-run the pipeline.
## Variations
* **Interactive follow-up:** After the pre-rendered training video, launch a [Live Avatar AI Tutor](/cookbook/live-avatar/ai-tutor) for Q\&A and knowledge checks
* **Manager versions:** Generate a shorter executive summary version alongside the full training
* **Assessment-ready:** End each video with key questions that feed into your LMS quiz system
***
## Next Steps
Deep dive into translating videos across languages.
Add interactive Q\&A after training with a Live Avatar tutor.