Rule: D-iD Avatar from Audio (AI Interpolator D-iD)
Last updated on
15 March 2024
Base data:
Summary:
The D-iD Avatar from Audio rule will take an image or image url and a audio field of someone talking and generate a video of a talking face of this.
Module needed:
AI Interpolator D-iD (part of D-iD module)
Field types to populate:
File field (core file module).
Base Fields types to use as context:
- File
Extra Requirements:
You need a paid D-iD account.
Elevenlabs Field works great together with it, even if its not needed.
Extra Settings:
Expression
This is the expression the person should use while talking.
Avatar Type
You can choose an image field as avatar here or a fixed url.
Image Url
If you choose Image url, you can specify and internal uri or an external url.
Image Field
You can choose an image field on the entity type.
Extra Advanced Settings:
None
Possible example use cases:
- You want to generate a personalized welcome message to anyone registering on your website.
- You want to answer FAQs with a video of yourself talking about it.
Help improve this page
Page status: No known problems
You can:
You can:
- Log in, click Edit, and edit this page
- Log in, click Discuss, update the Page status value, and suggest an improvement
- Log in and create a Documentation issue with your suggestion