Search
According to the official website of Tavus, an AI video company based in San Francisco, USA, its newly released model, Griffin-Lite, has performed exceptionally well in tests. After organizing 54 participants for a one-minute video call, 26 of them, accounting for 48%, mistakenly believed that they were talking to a real person, whereas only 2.4% of participants made this judgment with the previous generation system. Tavus claims that Griffin-Lite is the first real-time video conversation model to pass the 'video Turing test' and defines it as a 'human interaction model.' Unlike traditional voice assistants, Griffin-Lite can respond in real-time when both parties are speaking simultaneously, whether agreeing or interrupting, just like in a real human conversation.
-
C114 Communication Network -
Communication Home
