Microsoft wants artificial intelligence to rewrite reality and make it look like you said it would.
Imagine you are watching a live interview where someone says something controversial. But instead of hearing their actual words, AI replaces them with something completely different. Their lips move in perfect sync, making it look like they've been saying it all along.
That's the idea behind a new Microsoft patent that describes technology that can change speech and lip movements in real time.
The system will analyze the person's voice and video, identify words that need to be changed and use artificial intelligence to replace them while adjusting their mouth movements to match. The result can look like a completely natural recording, even though the original speech has been altered.
The applications offered by Microsoft go far beyond simple video editing. The technology can translate someone's speech into another language with their lips matching the translation, remove profanity, correct misdiagnosis, and even eliminate filler words like "um." It can also rewrite statements using information gathered from online sources or create shorter videos where people appear to provide AI-written summaries.
But there is one particularly troubling possibility: two people watching the same live broadcast could hear and see completely different versions of what was said, depending on their personal preferences.
Think about that for a moment. You can watch an interview, discuss it with a friend, and find that you both saw different versions of the exact same conversation.
The technology can make video translation and editing much more powerful, but it also raises serious questions about censorship, misinformation and the future of trust in video evidence.