PulseAugur
EN
LIVE 09:21:59
中文(ZH) 又快又聪明,阿里发布Qwen-Audio-3.0-Realtime:实时语音大模型四项功能升级

Alibaba releases Qwen-Audio-3.0-Realtime with enhanced voice AI capabilities

Alibaba has launched Qwen-Audio-3.0-Realtime, an upgraded real-time conversational voice model. This new version enhances intelligence, agent tool utilization, empathetic dialogue, and full-duplex interaction capabilities. The model comes in a "Plus" version for stronger reasoning and a "Flash" version for speed, aiming for applications in customer service, education, and companionship. Previous preview versions of the model have achieved top rankings on benchmarks like Artificial Analysis and VoiceBench. AI

IMPACT Enhances real-time voice AI capabilities, potentially improving user experience in conversational agents and customer service applications.

RANK_REASON Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=2 ai=1.0]

Read on 量子位 (QbitAI) →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Alibaba releases Qwen-Audio-3.0-Realtime with enhanced voice AI capabilities

COVERAGE [2]

  1. 量子位 (QbitAI) TIER_1 中文(ZH) · 量子位的朋友们 ·

    Fast and Smart, Alibaba Releases Qwen-Audio-3.0-Realtime: Four Functional Upgrades for Real-time Speech Large Model

  2. 雷峰网 (Leiphone) TIER_1 中文(ZH) ·

    Fast and Smart, Alibaba Releases Qwen-Audio-3.0-Realtime: Four Functional Upgrades for Real-time Speech Large Model

    <p style="text-align: center;"><img src="https://static.leiphone.com/uploads/new/images/20260715/6a56fce820bda.png?imageView2/2/w/740" /></p><p>7月15日,阿里巴巴发布实时语音交互对话模型Qwen-Audio-3.0-Realtime,在智商、Agent 工具调用、共情对话和双工交互流畅度四条主线上同步升级,力求“又快又聪明”。模型包括推理更强的Plus 版本和速度更快的Flash 版本,适用于智能客服、教育培训…