Actions22
- Video Actions
- Avatar Actions
- Voice Actions
- Template Actions
- Product Actions
- AI Script Actions
- File Actions
- Visual Style Actions
- Webhook Actions
Overview
The "Create from Avatar" operation under the Video resource allows users to generate AI-driven videos featuring a digital avatar. The avatar can either be a predefined "Jogg Avatar" or a custom user avatar identified by an ID. Users provide either a text script for the avatar to speak using a selected text-to-speech voice or supply an audio file URL for lip-syncing. The output video can have different background styles and aspect ratios, with optional captions and custom naming.
This node is beneficial in scenarios such as:
- Creating personalized marketing or educational videos with virtual presenters.
- Generating content where human-like avatars deliver scripted messages without needing live actors.
- Producing videos with transparent backgrounds for flexible post-production use.
Practical example: A marketer wants to create a promotional video where a branded avatar speaks a scripted message with captions enabled and exports it in portrait mode for social media stories.
Properties
| Name | Meaning |
|---|---|
| Avatar Type | Source type of the avatar. Options: "Jogg Avatar" or "Your Avatar". |
| Avatar ID | Numeric ID identifying the specific avatar to use. |
| Voice ID | ID of the text-to-speech (TTS) voice used for speech synthesis. |
| Screen Style | Background style of the output video. Options: "With Background", "Green Screen", "WebM (Transparent Background)". |
| Audio Source | Choose between providing a text script ("Text Script") or an audio file URL ("Audio File URL") as the audio input. |
| Script | Text content for the avatar to speak (used if Audio Source is "Text Script"). |
| Audio URL | URL of the audio file that the avatar will lip-sync to (used if Audio Source is "Audio File URL"). |
| Additional Options | Collection of optional settings:
|
Output
The node outputs JSON data representing the result of the video creation process. This typically includes metadata about the generated video such as its ID, URL, status, and any relevant processing details.
If binary data is output (not explicitly shown in the provided code), it would represent the actual video file or related media content.
Dependencies
- Requires an API key credential for authenticating requests to the JoggAI service.
- Depends on the external JoggAI API to perform avatar video generation, text-to-speech conversion, and video rendering.
- No additional environment variables are indicated beyond the API authentication.
Troubleshooting
Common Issues:
- Invalid or missing avatar ID may cause failures in video generation.
- Incorrect voice ID could lead to errors or default voice usage.
- Providing both script and audio URL incorrectly or leaving required fields empty might cause validation errors.
- Network or API authentication issues can prevent successful requests.
Error Messages:
- Errors related to "request failed" indicate problems communicating with the external API; verify API key validity and network connectivity.
- Validation errors for missing required parameters like avatar ID or voice ID require ensuring all mandatory inputs are correctly set.
- If the node throws errors about unsupported screen styles or aspect ratios, confirm that the selected options are valid.
Resolutions:
- Double-check all required properties before execution.
- Ensure the API key credential is correctly configured and active.
- Validate URLs and IDs against the source system or JoggAI dashboard.
- Use the "Continue On Fail" option to handle individual item errors gracefully during batch processing.
Links and References
- JoggAI Documentation (placeholder link based on
documentationUrlproperty) - Text-to-Speech voice options and guidelines (refer to JoggAI TTS documentation)
- Video aspect ratio standards and best practices for social media platforms