# Motion-Omni: End-to-End Joint Speech and Full-Body Motion for Spoken Dialogue

arXiv: https://arxiv.org/abs/2609.04250 · HTML: https://mlsanity.com/paper/2609.04250/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 60 of its 68 references that are in the map.
- First posted on arXiv 28 Aug 2026.

## Builds on (most cited first, 30 of 60)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild](https://mlsanity.com/paper/2008.10010/) (2020)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities](https://mlsanity.com/paper/2305.11000/) (2023)
- [AI Choreographer: Music Conditioned 3D Dance Generation with AIST++](https://mlsanity.com/paper/2101.08779/) (2021)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens](https://mlsanity.com/paper/2407.05407/) (2024)
- [Seed-TTS: A Family of High-Quality Versatile Speech Generation Models](https://mlsanity.com/paper/2406.02430/) (2024)
- [CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models](https://mlsanity.com/paper/2412.10117/) (2024)
- [GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot](https://mlsanity.com/paper/2412.02612/) (2024)
- [Kimi-Audio Technical Report](https://mlsanity.com/paper/2504.18425/) (2025)
- [FaceFormer: Speech-Driven 3D Facial Animation with Transformers](https://mlsanity.com/paper/2112.05329/) (2021)
- [VoiceBench: Benchmarking LLM-Based Voice Assistants](https://mlsanity.com/paper/2410.17196/) (2024)
- [Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity](https://mlsanity.com/paper/2009.02119/) (2020)
- [VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction](https://mlsanity.com/paper/2501.01957/) (2025)
- [Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models](https://mlsanity.com/paper/2211.09707/) (2022)
- [Generating Holistic 3D Human Motion from Speech](https://mlsanity.com/paper/2212.04420/) (2022)
- [LLaMA-Omni: Seamless Speech Interaction with Large Language Models](https://mlsanity.com/paper/2409.06666/) (2024)
- [SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization](https://mlsanity.com/paper/2212.10465/) (2022)
- [CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training](https://mlsanity.com/paper/2505.17589/) (2025)
- [Qwen3-TTS Technical Report](https://mlsanity.com/paper/2601.15621/) (2026)

## Abstract (arXiv)

An avatar that holds a conversation should decide what to say and to move while saying it, yet these abilities live in separate model families: spoken dialogue models produce speech without motion, and co-speech motion models produce motion only from audio handed to them. The standard remedy is a cascade that first generates the spoken response and then runs a motion model over the finished audio, which requires a second full inference pass and precludes any joint optimisation between the two. We present Motion-Omni, an end-to-end framework in which a spoken dialogue model natively outputs explicit facial expression together with hand, upper-body and lower-body motion, generated directly from the hidden states that produce the speech. Joint training is not optional here: with the speech pathway frozen, motion remains misaligned with the audio, and co-adapting the LLM, Speech Generator and Motion Generator under both objectives is what recovers alignment while retaining spoken-dialogue ability. Supervision comes from a scalable, model-agnostic pipeline that pseudo-labels consistent-voice speech responses with a replaceable motion teacher, yielding 422,856 quality-ranked pairs (1,402 hours). We further release SwDA-500 and, to our knowledge, the first public evaluation protocol for stochastic open-ended full-body spoken dialogue, matching audio across motion systems while unifying rendering, automatic metrics, human evaluation, and latency measurement. Instantiated with a Qwen2.5-7B-Instruct backbone, Motion-Omni-Q7 matches the same-audio teacher cascade to within 2% on reference-free motion metrics while responding 5.4 x faster (RTF=0.78, faster than real time), surpasses all non-teacher cascades on beat correlation and diversity, and reaches a 2.62% word error rate, the lowest among the omni-modal systems compared.