# Vorch-Streamer: Extending Human Audio-Visual Generation to Real-Time Long-Form Streaming

arXiv: https://arxiv.org/abs/2608.05663 · HTML: https://mlsanity.com/paper/2608.05663/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 6 Aug 2026.

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [Latte: Latent Diffusion Transformer for Video Generation](https://mlsanity.com/paper/2401.03048/) (2024)
- [Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models](https://mlsanity.com/paper/2402.17177/) (2024)
- [From Slow Bidirectional to Fast Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2412.07772/) (2024)
- [VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness](https://mlsanity.com/paper/2503.21755/) (2025)
- [LongLive: Real-time Interactive Long Video Generation](https://mlsanity.com/paper/2509.22622/) (2025)
- [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://mlsanity.com/paper/2601.03233/) (2026)
- [SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction](https://mlsanity.com/paper/2310.20700/) (2023)
- [Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation](https://mlsanity.com/paper/2602.02214/) (2026)
- [Seedance 2.0: Advancing Video Generation for World Complexity](https://mlsanity.com/paper/2604.14148/) (2026)
- [Qwen3-TTS Technical Report](https://mlsanity.com/paper/2601.15621/) (2026)
- [Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation](https://mlsanity.com/paper/2510.01284/) (2025)
- [LEO: Generative Latent Image Animator for Human Video Synthesis](https://mlsanity.com/paper/2305.03989/) (2023)
- [StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars](https://mlsanity.com/paper/2512.22065/) (2025)
- [OmniForcing: Unleashing Real-time Joint Audio-Visual Generation](https://mlsanity.com/paper/2603.11647/) (2026)
- [Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation](https://mlsanity.com/paper/2604.23632/) (2026)
- [SoulX-FlashTalk: Real-Time Infinite Streaming of Audio-Driven Avatars via Self-Correcting Bidirectional Distillation](https://mlsanity.com/paper/2512.23379/) (2025)
- [Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models](https://mlsanity.com/paper/2606.25041/) (2026)
- [Consistent and Controllable Image Animation with Motion Linear Diffusion Transformers](https://mlsanity.com/paper/2508.07246/) (2025)
- [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)

## Abstract (arXiv)

Real-time long-form avatar audio-video generation requires causal, continuous synthesis while maintaining audiovisual synchronization and visual consistency. Adapting a pretrained bidirectional model to this setting presents two key dilemmas. First, autoregressively reusing generated blocks as context creates exposure bias, causing errors and visual drift to accumulate over long rollouts. Second, a global speech utterance does not indicates a causal generator which portion should be spoken next when only limited local audio-video context is available. We present Vorch-Streamer, a post-training framework that addresses these challenges and enables real-time long-form Text-to-Audio-Video (T2AV) streaming. We construct a synthetic corpus of 80K avatar clips spanning 12-21 seconds and first train a causal generator with mixed Teacher Forcing and Diffusion Forcing. We then apply long-horizon Self Forcing with DMD distillation, exposing the model to its own rollout distribution while preserving the quality of the pretrained bidirectional teacher. To explicitly control speech progression, an external language model predicts discrete 25-Hz speech-planning tokens, whose continuous features condition the audio diffusion branch and align each causal block with the content it should speak. With bounded causal context and four-step denoising, Vorch-Streamer jointly generates audio and video from text at 27.12 FPS, exceeding the 24-FPS real-time playback rate while maintaining competitive audio-lip synchronization and strong identity preservation over long-form generation.