view reply Project Page: https://jixiaozhong.github.io/Sonic/ComfyUI: https://github.com/smthemex/ComfyUI_Sonic
view post Post 3734 Researchers developed Sonic AI enabling precise facial animation from speech cues ๐ง Decouples head/expression control via audio tone analysis + time-aware fusion for natural long-form synthesis See translation 1 reply ยท ๐ 7 7 ๐ฅ 6 6 ๐ 2 2 ๐ง 1 1 ๐ 1 1 + Reply
OpenOmni: Large Language Models Pivot Zero-shot Omnimodal Alignment across Language with Real-time Self-Aware Emotional Speech Synthesis Paper โข 2501.04561 โข Published Jan 8 โข 16 โข 4
DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation Paper โข 2502.03930 โข Published 18 days ago โข 1