Models

腾讯开源音频模型 AuK,可生成语音但中文发音像老外

Why we picked it

腾讯开源的音频模型 AuK,能生成语音,但中文发音像老外,挺有意思的。

腾讯开源了音频模型 AuK,能生成和编辑语音。测试用它翻译视频时,音色还原不错,但中文发音像老外说中文。作者在推特上分享了一个用 AuK 生成比尔盖茨说中文的视频,并询问是否参数设置不当。

Image · 宝玉
Original · 宝玉

测试了下 AuK,用它翻译了个视频,音色还原的挺好的,但是这中文说的太像老外说中文了😂 来听听比尔盖茨说中文 是我参数用的不对吗? @TencentHunyuan

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Models" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include AuK, audio generation, speech models, Tencent.

Source attribution: curated from 宝玉 (@dotey).