Atmee v2 发布：单图加10秒音频生成实时数字人视频
一个做实时数字人的模型 Atmee v2，一张图加10秒音频就能生成会说话的角色，官方说比 Seedance 2.5 快50倍，适合做教学或客服视频智能体。
Atmee v2 是一款面向实时视频智能体的头像模型，只需 1 张图片加 10 秒音频即可生成任意角色。官方称其速度最高比 Seedance 2.5、Wan 3.0 这类视频模型快 50 倍，成本低 10-100 倍。模型支持表情、手势等上下文表现，可用于直播视频通话、纯语音或视频生成场景。创始人 Chen-Ping Yu 曾创办被 Google 收购的 AR 公司，认为面对面交互是继文本和语音之后更自然的 AI 接口。
Huge market about to unlock here! Atmee v2 is a real-time avatar model for live video agents. It creates any character from one image and 10 seconds of audio. They report that it runs up to 50x faster than video models like Seedance 2.5 and Wan 3.0. Text and voice work well today. Talking to an agent face-to-face feels a lot more natural, especially for tutors, coaches, and support agents. Chen-Ping Yu @yuchenping After Google acquired my AR startup, I started thinking about the next interface, this time for AI. Text and voice work fine, just like DOS did before the Mac. But nothing’s more intuitive than face to face. After two years of research, today we’re launching Atmee v2: a real-time avatar model that makes live video agents feel truly life-like. • Any character from 1 image + 10s of audio • Contextual expressions, gestures, even interacting with the environment • Live video calls, voice only, or video generation At its core, Atmee v2 is a video foundation model, it can render anything, but it’s built to excel at characters, which is what video models like Seedance 2.5 and Wan 3.0 are mostly used for. In comparison: Atmee v2 • Up to 50x faster • 10-100x cheaper Build tutors, sales coaches, support agents, companions, game characters, even whole living worlds. The interface after text and voice starts today. Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 7 🔄 0 ❤️ 6 👀 1579 📊 6 ⚡
