Actions15
Overview
The "Create WebM Video" operation of the HeyGen node allows users to generate a WebM video featuring an AI avatar. The avatar can be customized by selecting a specific pose and style, and the input for the avatar's speech can be provided either as text or as an audio file. This operation is useful for creating personalized avatar videos for marketing, presentations, tutorials, or social media content where a talking avatar is needed.
For example, you could create a WebM video where an avatar speaks a promotional message by providing the text input, or you could supply an audio recording for the avatar to lip-sync in the video.
Properties
| Name | Meaning |
|---|---|
| Avatar Pose ID | The identifier of the avatar's pose to use in the video (e.g., "Vanessa-invest-20220722"). |
| Avatar Style | The visual style of the avatar. Options: Normal, Circle, Close Up, Voice Only. |
| Input Method | How the avatar's speech input is provided. Options: Text (avatar speaks provided text), Audio (avatar uses provided audio). |
| Input Text | The text that the avatar will speak in the video. Used only if Input Method is Text. |
| Voice ID | The voice identifier used for text-to-speech synthesis when Input Method is Text. |
| Input Audio | URL of the audio file to use as input for the avatar's speech. Used only if Input Method is Audio. |
| Video Dimensions | Width and height of the output WebM video in pixels. Defaults to 1280x720 if not specified. |
Output
The node outputs JSON data representing the response from the HeyGen API after requesting the creation of the WebM video. This typically includes metadata about the generated video such as its ID, status, and URLs to access the video once ready.
No binary data is output directly by this operation; instead, the output JSON contains references (such as URLs) to the generated video files.
Dependencies
- Requires an active connection to the HeyGen API with valid API authentication credentials.
- The node expects the user to provide either text or audio input depending on the selected input method.
- Network access is required to upload audio files via URL and to communicate with the HeyGen API endpoints.
Troubleshooting
- Missing or invalid input: If neither text nor audio input is properly provided according to the selected input method, the API request may fail. Ensure that the correct input fields are filled.
- Invalid Avatar Pose ID or Voice ID: Using incorrect or unsupported IDs may cause errors or unexpected results. Verify these IDs against available resources in HeyGen.
- API Authentication Errors: If the API key or credentials are missing or invalid, requests will fail. Confirm that the HeyGen API credentials are correctly configured in n8n.
- Network Issues: Failures in reaching the HeyGen API or fetching audio files from URLs can cause errors. Check network connectivity and URL validity.
- Dimension Values: Providing non-numeric or unreasonable width/height values might cause errors or poor video quality. Use sensible pixel dimensions.
Common error messages usually relate to invalid parameters or authentication failures and can be resolved by verifying inputs and credentials.
Links and References
- HeyGen Official Website
- HeyGen API Documentation (for detailed API usage and resource IDs)
- WebM Video Format - Information about the WebM video format used for output