TalkingMachines: Real-Time Audio-Driven FaceTime-Style Video via Autoregressive Diffusion Models

In this paper, we present TalkingMachines -- an efficient framework that transforms pretrained video generation models into real-time, audio-driven character animators. TalkingMachines enables natural conversational experiences by integrating an audio large language model (LLM) with our video generation foundation model. Our primary contributions include: (1) We adapt a pretrained SOTA image-to-video DiT into an audio-driven avatar generation model of 18 billion parameters; (2) We enable infinite video streaming without error accumulation through asymmetric knowledge distillation from a bidirectional teacher model into a sparse causal, autoregressive student model; (3) We design a high-throughput, low-latency inference pipeline incorporating several key engineering optimizations such as: (a) disaggregation of the DiT and VAE decoder across separate devices, (b) efficient overlap of inter-device communication and computation using CUDA streams, (c) elimination of redundant recomputations to maximize frame-generation throughput. Please see demo videos here -this https URL

@article{low2025_2506.03099,
  title={ TalkingMachines: Real-Time Audio-Driven FaceTime-Style Video via Autoregressive Diffusion Models },
  author={ Chetwin Low and Weimin Wang },
  journal={arXiv preprint arXiv:2506.03099},
  year={ 2025 }
}