Actions15
Overview
The "Create Video" operation of the HeyGen node allows users to generate AI-powered videos composed of one or more scenes. Each scene can feature a character (either an avatar or a talking photo) with customizable voice input and background settings. This node is useful for creating personalized video content such as marketing videos, educational materials, or social media clips where dynamic characters speak text, play audio, or remain silent.
Typical use cases include:
- Generating videos with avatars that speak custom text using text-to-speech voices.
- Creating talking photo videos with pre-recorded audio or silence.
- Producing multi-scene videos with different characters and backgrounds.
- Automating video creation workflows with callback notifications when videos are ready.
Properties
| Name | Meaning |
|---|---|
| Caption | Whether to add captions to the video. Only supported if the voice input is text. Default is false. |
| Title | Title of the generated video. |
| Callback ID | A custom identifier string for callback purposes, allowing correlation of callbacks with requests. |
| Callback URL | An optional URL to receive a notification when the video generation is complete. |
| Folder ID | Specifies the destination folder ID where the video will be saved. |
| Video Dimensions | The width and height of the output video in pixels. Defaults to 1280x720 if not specified. |
| Video Input Scenes | A collection of one or more scenes describing the video content. Each scene includes: |
| - Character Type: "Avatar" or "Talking Photo". | |
| - Avatar ID or Talking Photo ID depending on character type. | |
| - Voice Type: "Text", "Audio", or "Silence". | |
| - For Text voice: Voice ID, input text, and voice speed (0.5 to 1.5). | |
| - For Audio voice: URL of the audio file. | |
| - For Silence voice: Duration in seconds (1-100). | |
| - Background Type: "Color", "Image", or "Video". | |
| - Background Color (hex), Image URL, or Video URL depending on background type. |
Output
The node outputs JSON data representing the response from the HeyGen API after requesting video generation. This typically includes metadata about the created video such as its ID, status, and possibly URLs to access the video once ready.
No binary data output is produced by this operation.
Dependencies
- Requires an API key credential for authenticating with the HeyGen API.
- The node makes HTTP POST requests to the HeyGen API endpoint
/video/generatewith versionv2. - Optional callback URLs require external endpoints capable of receiving HTTP notifications.
Troubleshooting
Error: "At least one video input scene is required"
This error occurs if no scenes are provided in the "Video Input Scenes" property. Ensure you add at least one scene with valid character and voice settings.Invalid or missing Avatar ID / Talking Photo ID
If the character IDs are incorrect or missing, the API may reject the request. Verify that the IDs correspond to existing avatars or talking photos in your HeyGen account.Voice input errors
When using text-to-speech, ensure the voice ID is valid and the input text is non-empty. For audio voice type, verify the audio URL is accessible and properly formatted.Callback URL issues
If you specify a callback URL but do not receive notifications, check that the URL is publicly accessible and correctly handles incoming requests.Dimension values out of range
Providing invalid width or height values may cause API errors. Use reasonable pixel dimensions (e.g., 1280x720).
Links and References
- HeyGen API Documentation (general reference for API endpoints and parameters)
- n8n Documentation (for general usage of n8n nodes and credentials)