Vivix Labs 发布实时视频模型 A1 和 A1 Playground + Agent，可创建能对话、移动、玩游戏的直播 AI 角色。模型将音频和视频作为同一个小片段流一起生成，语音和动作属于同一分块，因此用户可在对话中打断角色、变换话题或让其走动，无需协调两个独立系统。入口：https://platform.vivix.ai/vivix-a1-model/
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.
Create your own character. Call the shots. Live. Introducing A1 Playground + Agent: build a live AI character that talks, moves, and plays with you. Create yours: https://platform.vivix.ai/vivix-a1-model/ Their look. Their personality. Their voice. Your choice. Describe who you have in mind, upload a picture, and let our Agent bring them to life. And they do a lot more than talk. 💃 Full-body performance. From air guitar to victory dances. 🚶 Move around the scene. Walk and talk. Pace while making a point. 🛍️ Interact with objects. Pick up products, show them off, and pitch them. 🎮 Play web games together. Deal cards, keep score, and play along. Solve a mystery with Sherlock Holmes, then interrupt him for a dance break. Take a walk with Socrates. Hand him a protein shake and debate the meaning of gains. Give Snape a bottle of shampoo. Ask for the most enthusiastic sales pitch of his life. Who will you bring to life?在 X 查看被引用的帖子
来源：Rohan Paul · x.com