Event ·Multi-source

阿里发布实时语音交互对话模型Qwen-Audio-3.0-Realtime,声称更聪明

阿里巴巴发布Qwen-Audio-3.0-Realtime实时语音交互对话模型,提供推理更强的Plus版本和速度更快的Flash版本。模型在S2S语音指令遵循公开基准VStyle上取得SOTA效果,并在Artificial Analysis子项综合排名第一,超越OpenAI GPT-Realtime-2。支持动态工具调用(如路线规划、信息查询)、音色克隆以及情感感知生成,能根据语境调整语气、节奏和情感。适用于智能客服、教育培训、娱乐互动等场景。

Current read

阿里新模型Qwen-Audio-3.0-Realtime能实时语音对话、调用工具、感知情绪,语音指令和综合排名都超过了GPT-Realtime-2。

11 sources76° AI heatLast updated 2026/7/15 03:00:22

Evidence

11 sources
Related source 2lmarena.ai
View source
Related source 4Greg Brockman
View source
Related source 5arXiv: OpenAI
View source
Related source 6shao__meng
View source
Related source 7AI Engineer
View source
Related source 8AWS Machine Learning Blog
View source
Related source 9Sam Altman
View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.