We present EmbodiedHead, a speech-driven talking-head framework that equips LLMs with real-time visual avatars for conversation. A practical embodied avatar must achieve real-time generation, unified listening-speaking behavior, and high rendered visual quality simultaneously. Our framework couples the first Rectified-Flow Diffusion Transformer (DiT) for this task with a differentiable renderer, enabling diverse, high-fidelity generation in as few as four sampling steps. Prior listening-speaking methods rely on dual-stream audio, introducing an interlocutor look-ahead dependency incompatible with causal user--LLM interaction. We instead adopt a single-stream interface with explicit per-frame listening-speaking state conditioning and a Streaming Audio Scheduler, suppressing spurious mouth motion during listening while enabling seamless turn-taking. A two-stage training scheme of coefficient-space pretraining and joint image-domain refinement further closes the gap between motion-level supervision and rendered quality. Extensive experiments demonstrate state-of-the-art visual quality and motion fidelity in both speaking and listening scenarios.

翻译：我们提出EmbodiedHead，一种由语音驱动的说话头框架，可为大型语言模型提供用于对话的实时视觉虚拟形象。一个实用的具身虚拟形象必须同时实现实时生成、统一的听与说行为以及高渲染视觉质量。为此，我们的框架首次将整流流扩散Transformer（DiT）与可微渲染器耦合用于此任务，仅需四个采样步即可生成多样且高保真的结果。先前的听与说方法依赖双流音频，引入了与因果式用户-LLM交互不兼容的对话者前瞻性依赖。我们转而采用单流接口，结合显式的逐帧听与说状态条件控制和流式音频调度器，在抑制倾听期间虚假嘴部运动的同时实现无缝话轮转换。通过系数空间预训练与联合图像域精调的两阶段训练方案，进一步弥合了动作级监督与渲染质量之间的差距。大量实验证明，该方法在说话和倾听场景中均实现了最先进的视觉质量与动作保真度。