# Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation

arXiv: https://arxiv.org/abs/2604.23632 · HTML: https://mlsanity.com/paper/2604.23632/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 34 of its 52 references that are in the map.
- First posted on arXiv 26 Apr 2026.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Improved Distribution Matching Distillation for Fast Image Synthesis](https://mlsanity.com/paper/2405.14867/) (2024)
- [A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild](https://mlsanity.com/paper/2008.10010/) (2020)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness](https://mlsanity.com/paper/2503.21755/) (2025)
- [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://mlsanity.com/paper/2601.03233/) (2026)
- [EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions](https://mlsanity.com/paper/2407.08136/) (2024)
- [Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound](https://mlsanity.com/paper/2502.05139/) (2025)
- [Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer](https://mlsanity.com/paper/2412.00733/) (2024)
- [FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds](https://mlsanity.com/paper/2407.01494/) (2024)
- [Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency](https://mlsanity.com/paper/2409.02634/) (2024)
- [JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization](https://mlsanity.com/paper/2503.23377/) (2025)
- [Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation](https://mlsanity.com/paper/2512.04678/) (2025)
- [OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation](https://mlsanity.com/paper/2506.18866/) (2025)
- [Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation](https://mlsanity.com/paper/2510.01284/) (2025)
- [Sonic: Shifting Focus to Global Audio Perception in Portrait Animation](https://mlsanity.com/paper/2411.16331/) (2024)
- [Learning Few-Step Diffusion Models by Trajectory Distribution Matching](https://mlsanity.com/paper/2503.06674/) (2025)
- [LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision](https://mlsanity.com/paper/2412.09262/) (2024)
- [Distribution Matching Distillation Meets Reinforcement Learning](https://mlsanity.com/paper/2511.13649/) (2025)
- [Diff2Lip: Audio Conditioned Diffusion Models for Lip-Synchronization](https://mlsanity.com/paper/2308.09716/) (2023)
- [One-step Diffusion Models with f-Divergence Distribution Matching](https://mlsanity.com/paper/2502.15681/) (2025)
- [MOVA: Towards Scalable and Synchronized Video-Audio Generation](https://mlsanity.com/paper/2602.08794/) (2026)
- [INFP: Audio-Driven Interactive Head Generation in Dyadic Conversations](https://mlsanity.com/paper/2412.04037/) (2024)
- [Speech Driven Video Editing via an Audio-Conditioned Diffusion Model](https://mlsanity.com/paper/2301.04474/) (2023)
- [OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers](https://mlsanity.com/paper/2505.21448/) (2025)

## Built on by (most cited first, 13 of 13)

- [Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models](https://mlsanity.com/paper/2606.25041/) (2026)
- [Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation](https://mlsanity.com/paper/2609.11638/) (2026)
- [StreamChar: Long-Horizon Streaming Character Audio-Video Generation with Decoupled Orchestration](https://mlsanity.com/paper/2605.25659/) (2026)
- [Wan-Streamer v0.2: Higher Resolution, Same Latency](https://mlsanity.com/paper/2607.04443/) (2026)
- [Video = World + Event Stream](https://mlsanity.com/paper/2607.15038/) (2026)
- [Ripple: Real-Time Streaming Audio-Video Generation With Cross-Modal Recurrent Memory](https://mlsanity.com/paper/2607.26818/) (2026)
- [Omni-LiveAvatar: Minute-Level Real-Time Streaming Joint Audio-Video Avatar Generation](https://mlsanity.com/paper/2608.13602/) (2026)
- [OmniMate: Open-Ended Real-Time Streaming Audio-Visual Generation for Interactive Avatars](https://mlsanity.com/paper/2607.23023/) (2026)
- [Vorch-Streamer: Extending Human Audio-Visual Generation to Real-Time Long-Form Streaming](https://mlsanity.com/paper/2608.05663/) (2026)
- [The Missing Temporal Link: Temporal Context Routing for Script-Driven Audio-Video Generation](https://mlsanity.com/paper/2609.02367/) (2026)
- [Vorch-Human: Unified Multi-Task Human-Centric Generation via Long-Horizon Continuation](https://mlsanity.com/paper/2609.26117/) (2026)
- [Joint and Cross-Modal Video-Audio Generation and Editing: A Unified Formulation and Design Taxonomy](https://mlsanity.com/paper/2609.34381/) (2026)
- [Hear the World in Stereo: Learning Dynamic Spatial Correspondence for Immersive Joint Video-Audio Generation](https://mlsanity.com/paper/2609.38748/) (2026)

## Abstract (arXiv)

Real-time text-driven joint audio-video avatar generation requires jointly synthesizing portrait video and speech with high fidelity and precise synchronization, yet existing audio-visual diffusion models remain too slow for interactive use and often degrade noticeably after aggressive acceleration. We present Hallo-Live, a streaming framework for joint audio-visual avatar generation that combines asynchronous dual-stream diffusion with human-centric preference-guided distillation. To reduce articulation lag in causal generation, we introduce Future-Expanding Attention, which allows each video block to access synchronous audio together with a short horizon of future phonetic cues. To mitigate the quality loss of few-step distillation, we further propose Human-Centric Preference-Guided DMD (HP-DMD), which reweights training samples using rewards from visual fidelity, speech naturalness, and audio-visual synchronization. On two NVIDIA H200 GPUs, Hallo-Live runs at 20.38 FPS with 0.94 seconds latency, yielding 16.0x higher throughput and 99.3x lower latency than the teacher model Ovi. Despite this speedup, it retains strong generation quality, reaching comparable VideoAlign overall score and Sync Confidence score while outperforming other accelerated baselines in the overall quality-efficiency trade-off. Qualitative results further show robust generalization across photorealistic, multi-speaker, and stylized scenarios. To the best of our knowledge, Hallo-Live is the first framework to combine streaming dual-stream diffusion with preference-guided distillation for real-time, text-driven audio-visual generation.