Google's new AI tech update generates soundtracks for videos

Google has announced a significant update to its AI video-to-audio technology, which now includes the capability of generating synchronized soundtracks, sound effects, and dialogue for videos.

This advancement, termed "synchronized audiovisual generation," enables the creation of audio that perfectly aligns with the characters and tone of a video.

Unlike traditional video-to-audio tools that often rely on text prompts, Google's new technology can interpret raw video pixels to generate appropriate audio. This allows for the production of an unlimited variety of soundtracks for any given video input, making it a versatile tool for enhancing archival material, silent films, and other types of footage.

The technology is currently being refined for safety and accuracy before its public release. It is part of DeepMind, Google's AI research lab, which has been at the forefront of many AI advancements.

The new tool promises to revolutionize the way generated movies and videos are brought to life, overcoming the limitation of silent outputs seen in many current systems.

You can watch some test clips showcasing this technology's capabilities below.