Synthesia, a company focused on using artificial intelligence for good, has created ENACT, a native dubbing feature that uses generative AI to seamlessly translate video content into various languages. The program synchronizes the lip movements of an actor with that of a voice actor speaking a specific language, thereby lifting the barriers of language and allowing content creators further reach.
ENACT enables translation without the creative casualty of dubbing or subtitling, resulting in a seamless experience for the viewer. Native dubbing is a new method of translating video content that utilises AI to synchronise the lip movements of an actor to a new dialogue track. …Our goal is to remove the language barrier from video and allow content from both YouTube influencers and high-end productions to reach a much larger audience than today.
Happy to announce that @synthesiaIO is moving out of stealth. We do exciting native movie dubbing with cutting edge deep learning technology, empowering storytellers with AI :)https://t.co/W48vxRLpHOhttps://t.co/KHzHfSWvO7
No more bad lip sync on TV!#deeplearning #vfx #AI pic.twitter.com/sxZPBK6OJP
— Matthias Niessner (@MattNiessner) November 15, 2018