# 腾讯混元开源语音模型 AuK，统一语音生成与编辑并推出 4 步推理的 AuK-Flash

- 来源：Tencent Hy (@TencentHunyuan)
- 发布时间：2026-09-10 18:33
- AIHOT 分数：58
- AIHOT 链接：https://aihot.news/items/cmtvezm9702p2ronb8a6nyhdv
- 原文链接：https://x.com/TencentHunyuan/status/2097996926876795197

## AI 摘要

腾讯混元发布开源语音基础模型 AuK，支持统一语音生成与编辑，可通过自然语言指令加参考音频实现零样本 TTS、指令控制生成、内容与音色/风格/情感编辑、去口音、语速音调控制、增强去噪及多说话人和音乐分离。

## 正文

🚀 AuK is officially here. Nano banana🍌 for audio

An open-source foundation model for unified speech generation and editing.
Natural-language instructions + reference audio. One interface.
Zero-shot TTS. Instruction-controlled generation. Content editing. Whisper-conversion. De-accent. Timbre/style/emotion edit. Speed/Pitch control. Enhancement, denoising, multi-speaker and music separation.
Also releasing AuK-Flash: 4-step inference. ~4.5× faster under matched conditions.
Code, weights, and demo are live. Try it and share your feedback.

🤗 Paper & upvote: https://huggingface.co/papers/2609.08936
⭐ GitHub & star: https://github.com/Tencent-Hunyuan/AuK