HeyGen Video Agent API
HeyGen's flagship agent: give it a prompt and it produces a complete video end-to-end — writing the script, choosing the avatar, and composing scenes. Attach reference files (images, docs) to ground the output.
$0.126/s on Varosity credits ($0.120/s with your own key). Clips up to 600s with native audio.
no heygen account needed · no subscription · failed renders never billed
Best for
- prompt → finished video
- agent writes script, picks avatar & scenes
- accepts reference files
Trade-offs
- least granular control
- longer render
Call it from your code
One Varosity key works for every model. Video renders are async — the response has a jobId; poll GET /api/v1/jobs/{jobId} until status is "succeeded", then read outputUrl.
curl -X POST https://varosity.ai/api/v1/video/generate \
-H "Authorization: Bearer $VAROSITY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "cinematic aerial of a coastal road at golden hour, slow push-in",
"modelId": "heygen-video-agent",
"aspectRatio": "16:9",
"durationSec": 5
}'Or ask your agent
Connect Claude, Cursor, or any MCP client to https://varosity.ai/api/mcp with your key, then say:
"Use Varosity with heygen-video-agent to make a 5-second clip of …"Agent setup guide
Alternatives to HeyGen Video Agent
- D-ID AI Presentertalking avatars from any photo · text-to-presenter$0.053/s
- HeyGen Avatar (Digital Twin)studio-grade lip sync · Avatar IV / Avatar V motion engines$0.084/s
- HeyGen Photo Avatar (Avatar IV)animate ANY photo as the speaker · Avatar IV motion engine$0.084/s
- HeyGen Video Translatemultilingual lip-sync dubbing · preserves original speaker appearance$0.105/s
- OmniHuman 1.5talking avatars · from single photo$0.084/s
- HeyGen Cinematic Avatarprompt-driven cinematic shots · blends 1–3 avatar looks into a scene$0.105/s