Google’s DeepMind team has developed video-to-audio (V2A) technology that can generate audio for videos. DeepMind has a history of groundbreaking achievements in AI, including creating general AI systems and defeating world champions in games like Go and StarCraft. The V2A technology uses generative AI models to train itself to generate corresponding audio for videos by examining the pixel data and identifying associated noises. It can also accept text prompts to refine the audio output in real time. This technology brings us closer to being able to produce entire videos or commercials from scratch using AI.
Keywords
DeepMind, AI marketing, video-to-audio technology, generative AI models, audio generation, video generation, AI breakthroughs
Takeaways
- DeepMind has a history of groundbreaking achievements in AI, including defeating world champions in games like Go and StarCraft.
- The video-to-audio (V2A) technology developed by DeepMind can generate audio for videos by examining pixel data and identifying associated noises.
- The V2A technology can accept text prompts to refine the audio output in real time.
- This technology brings us closer to being able to produce entire videos or commercials from scratch using AI.
Links:
https://deepmind.google/discover/blog/generating-audio-for-video
https://deepmind.google/technologies/veo
