D-ID launches new high-quality avatars capable of real-time conversations
AI video platform D-ID announced today that it is releasing two new types of avatars — Express and Premium+ — for content creation. Companies are chasing
Companies are chasing the golden goose of creating AI avatars that are more humanlike and can potentially offload video creation for enterprise use cases in areas like marketing, sales, and customer support. With different generative models, it is easier to give little text input and little visual data to create videos for business purposes that don’t look entirely out of place. D-ID’s new models are an effort to make it more competitive in this landscape.
Express avatars can be trained with roughly one minute of video and replicate users’ head movements during speech. Premium+ is the company’s marquee model, which might need at least a few minutes of recording for training, but can reproduce an AI avatar for videos with hands and torso. The company’s idea is that with hands and torso movements, the avatar feels more human-like in interaction with other users.
The company said that the Premium+ models are capable of real-time interaction that might be good for use cases like webinar and translation.
The company plans to engage these avatars for enterprise use cases such as creating sales leads, customer engagement, and personalized marketing campaigns.
“We believe the best way to interact with AI models is face-to-face; that is why we are creating these new hyper-realistic avatars and a natural user interface,” D-ID CEO Gil Perry told TechCrunch over a call.