Great, Google Veo 3 AI Model Now Can Create Images Of Speaking

JAKARTA Since its launch last May on Google I/O, Veo 3 has become a popular Artificial Intelligence (AI) model because of its capabilities. This AI model can make very realistic high-quality videos.

Veo 3 can also make images into videos. That way, images in the photo gallery that were previously silent can now be made to move. Even though it is very sophisticated, Google is not satisfied with these features.

Google announced an update for its video-making tool, namely the ability to add speech to moving images. In fact, this addition of speech is supported by sound and sound effects in the background.

"To maximize Flow, starting this week, you can add a greeting to your clip on Flow when using Frames to Video. This feature allows you to use your own image to use as the initial frame of video clips," Google said.

The Frames to Video feature is introduced in Veo 3 Fast, thus providing users with more flexibility in managing their credit. For now, the audio creation feature on images in Flow is still in the experimental or trial phase.

It should be noted that the availability of Flow is also still limited. Therefore, Google will expand the availability of Flow and Google AI Ultra to 76 new countries. This means that Flow will be available in more than 140 countries worldwide with the Google AI Pro or Ultra package.