Digital Human
Introduction
The Digital Human service creates digital human mouth shapes, facial expressions, and body movements according to the voice or text entered by the user.
The service can provide visual interaction effects between the digital human and a customer by rendering motions provided by the Digital Human service in real time.
The Digital Human service provided by LG AI Platform has the following features:
| Feature | Description |
|---|---|
| Creation of mouth shape and facial expression based on voice/text |
Creates mouth shapes and facial expressions based on the input voice, thereby giving a lively expression as if a person is actually speaking. Interoperates with the TTS (Text to Speech, voice synthesis) function to support text input as well. |
| Creation of body movement based on voice/text |
Expresses various body movements based on input voice and text. |
| Real-time motion creation function and generated motion streaming supported |
Supports real-time motion creation and streaming function for real-time interaction between a digital human and a user. |
| Multiple connections supported |
Multiple connections are possible to create actions simultaneously even when requested by multiple users. |
Structure
The Digital Human service receives audio data or text as input value and outputs real-time video streaming data.
Example of Uses
The Digital Human service can be applied to TV, signages, and products equipped with displays.
Previously, the service has been provided to users through guidance text or voice, but the digital human service can be used to interact with users in real time lively as if talking to a real person.
In addition, the service can be used to approach users in a more friendly way by providing a digital human instead of a chatbot on the web/mobile.