Help Center/ MetaStudio/ FAQs/ About the Service/ FAQs Related to MetaStudio Virtual Avatars
Updated on 2025-08-22 GMT+08:00

FAQs Related to MetaStudio Virtual Avatars

See Table 1.

Table 1 FAQs related to virtual avatars

No.

Question

Answer

1

Is face swap supported?

No.

2

Is clothes swap supported?

No.

3

Can actions be added?

An action can be added only when both of the following conditions are met:

Action insertion is now allowed only for video production, as shown in Figure 1. on a virtual avatar card indicates that this virtual avatar supports action insertion. Note that the audio duration should be long enough so the virtual avatar can perform the inserted action in a timely manner.

4

Do virtual avatars speak as instructed by the input text or speech?

Virtual avatars in videos and livestreams can speak as instructed by the input text or audio.

5

Is semantic understanding of knowledge bases supported?

No. Semantic understanding is a capability of knowledge bases, not of virtual avatars.

Virtual avatars perform intelligent interaction with users by answering their questions. The answers are given by the large language model (LLM) or knowledge base.

6

Are text to speech (TTS) and automatic speech recognition (ASR) supported?

TTS is supported but ASR (speech to text) is not. If you need ASR, try ASR services such as Speech Interaction Service (SIS).

Figure 1 Video production