Create a video from a text prompt using Video Agent. Returns a session resource with session_id for tracking and video_id for polling status via GET /v3/videos/. Files can be provided as asset_id (from POST /v3/assets), HTTPS URL, or base64-encoded content. Supported types: image (png, jpeg), video (mp4, webm), audio (mp3, wav), and pdf.
HeyGen API key. Obtain from your HeyGen dashboard.
Request body for creating a video from a prompt using Video Agent v3.
All configuration is flat (no nested config object). Files use the type-discriminated AssetInput union for flexible asset inputs.
The message/prompt for video generation (1-10000 characters)
1 - 10000Specific avatar ID to use
Specific voice ID to use for narration
Style ID from GET /v3/video-agents/styles. Applies a curated visual template to the generated video.
Video orientation. If not provided, auto-detected from content.
landscape, portrait Optional file attachments (max 20 files)
20Asset input via publicly accessible HTTPS URL.
Webhook URL for completion/failure notifications
Optional callback ID included in webhook payload
When enabled, disables memory injection and extraction for this session
Successful response
Response from creating a video agent session.
Designed as a session resource for future extensibility — GET /v3/video-agents/{session_id} can return the same shape enriched with more fields (messages, video URL, etc.).