Actions23
- Asset Actions
- Avatar Actions
- List Actions
- Lipsync Actions
- OAuth Actions
- Video Actions
- Video Agent Actions
Video → Create Avatar Video
AI-generatedSummary
Creates a HeyGen avatar video from one scene, using text-to-speech or an audio URL, then returns HeyGen’s API response for the video request.
Inputs
- Authentication — Choose OAuth2 (default) or the legacy API key credential.
- Video Input Scenes (required) — Provide exactly one scene per request. Choose Avatar or Talking Photo and supply its corresponding Avatar ID or Talking Photo ID. For text voice, set Input Text and Voice ID; for audio voice, set Audio URL. Silence voice type is not supported by this operation.
- Video Dimensions — Set output width and height; defaults are 1280 × 720. The request derives a 9:16 aspect ratio when height exceeds width, otherwise 16:9, and uses 1080p when height is at least 1080, otherwise 720p.
- Caption — Enable captions; defaults to false. The UI notes captions support text input.
- Additional Fields — Optionally set Title, Callback ID, Callback URL, or Folder ID. Test defaults to false; enabling it requests a watermarked test video that does not consume credits.
Output shape
A list of n8n items, one per input item, each containing the HeyGen API response in its json field.
The node submits a POST request to HeyGen’s v3 /videos endpoint. It requires exactly one scene; zero or multiple scenes cause an error. With Continue On Fail enabled, failures are returned as {"error": "…"} in the item’s json instead.