Google has announced the launch of advanced updates to its video creation platform, allowing users to generate digital avatars that highly accurately mimic their appearance and voices based on personal photos and audio recordings. This step aims to transform the platform from a mere traditional presentation tool into a comprehensive environment for AI-powered visual production. By integrating multimodal processing models, users can now convert text and reference images into professional videos, with advanced options provided for editing backgrounds, lighting, and adding visual effects in sequential steps, without the need to entirely re-create the video with every modification.
Google Launches a Feature to Create Speaking Digital Clones for Users to Enhance AI Video Production
a
admin
Author
Published
1 min
Read time