Tencent Hunyuan releases AuK code and weights on GitHub with ComfyUI and fine-tuning support

aigclink · x · 2026-09-11

Tencent Hunyuan has open-sourced AuK on GitHub: an open-source foundation model for speech generation and editing, with code and weights publicly available and demos on Hugging Face and ModelScope. The repo ships uv/Conda install, CLI inference, interactive Gradio demo, ComfyUI integration, Prompt Enhancer, Python API and fine-tuning, plus Day 0 support from SGLang-Omni. The 1.5B model unifies cloning, instruction-based synthesis, editing, enhancement and separation.

Original post →

More from Multimodal

Multimodal channel →