Get the latest tech news
Google DeepMind’s new AI tool uses video pixels and text prompts to generate soundtracks
The soundtracks are pretty impressive.
In addition to using a text prompt to generate audio, DeepMind’s tool also takes into account the contents of the video. According to DeepMind, the tool can also generate an “unlimited” number of soundtracks for videos, allowing users to come up with an endless stream of audio options. DeepMind’s tool isn’t generally available just yet, as it will still have to undergo “rigorous safety assessments and testing.” When it does become available, its audio output will include Google’s SynthID watermark to flag that it’s AI-generated.
Or read this on The Verge
