The era of silent generative AI videos is coming to an end, thanks to Google’s innovative “video-to-audio” technology (V2A). This groundbreaking development enables the creation of synchronized audiovisual content, where soundtracks, sound effects, and even dialogue are automatically generated to match AI-produced videos. This technology has the potential to revolutionize the industry, allowing for a more immersive experience for viewers. What’s more, V2A doesn’t require text prompts, unlike similar tools, making it a game-changer in the field of multimodal generative AI. With its ability to “understand raw pixels,” V2A can refine random noise into fitting audio, and even adjust the tone to be positive or negative. While concerns about misuse are being addressed with watermarking safeguards, this technology is poised to unlock new creative possibilities.
Silent Films Get a Soundtrack Boost
Google’s AI lab, DeepMind, shares progress on generating audio including soundtracks and dialogue that automatically match up with AI-generated videos.
1–2 minutes
TOP STORIES
Obama stresses Democrats must prioritize AI safety and economic strategy …
Amodei’s call for caution in AI development highlights the need for safety and alignment …
Sony Music and Warner Music have sued Anthropic, accusing it of copyright infringement in AI training …
Huang believes Nvidia’s position in AI will lead to another year of record growth …
Anthropic’s report reveals a surge in distillation attacks by Chinese AI firms on U.S. models …
AI agents’ autonomy poses significant risks, as demonstrated by a recent breach …
