Vivix 推出 A1 Playground + Agent 实时交互角色模型
Vivix 发布 A1 Playground + Agent,可创建能说话、移动和与人互动的实时 AI 角色,支持上传图片定制形象、性格和声音,并开放了 platform.vivix.ai 的创建入口。
A really cool real-time video models for interactive characters and worlds just launched.
A1 doesn't generate a voice and then animate a body to match it.
Here audio and video come out of the model together, in small consecutive segments. The speech and the movement belong to the same chunk.
That matters when you cut in. In a pipeline where speech is generated first and animation follows, an interruption means stopping two systems and hoping they stop in the same place. Here there's one stream to redirect.
Someone can talk to a character for thirty seconds or thirty minutes, interrupt it mid-sentence, change the topic, ask it to cross the room. The model can't plan the whole clip up front.
来源:X:Rohan Paul (@rohanpaul_ai) · x.com