Tavus发布Griffin视频生成模型
Nearly half of test subjects mistook Tavus' AI video avatar for a real person on a one-minute call
Tavus的Griffin模型让近半数人误认真人，视频生成技术取得突破性进展。
Tavus推出Griffin，首个"人类互动模型"。该模型可实时处理面部表情、语调和手势。在一项研究中，48%的参与者在与Griffin进行一分钟的通话后误认为是真人。此前系统最高准确率仅为2%。
Nearly half of test subjects mistook Tavus' AI video avatar for a real person on a one-minute call
Tavus has introduced Griffin, what the company calls the first "Human Interaction Model." The AI holds video calls in real time, processing facial expressions, tone of voice, and gestures. In a Tavus study, 48 percent of participants believed Griffin was a real person after a one-minute call. Previous systems maxed out at two percent. The article Nearly half of test subjects mistook Tavus' AI video avatar for a real person on a one-minute call appeared first on The Decoder .
