Models73°
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
Why we picked it
阿里刚发的Qwen-Audio-3.0-Realtime，实时语音四项升级，又快又聪明，做语音交互项目的可以试试。
阿里发布Qwen-Audio-3.0-Realtime实时语音大模型，升级了实时语音识别、语音唤醒、语音合成、情绪识别四项核心功能。
Body
该模型在语音识别延迟上进一步降低，支持更自然的语音交互。相比上一代，Qwen-Audio-3.
0-Realtime在唤醒准确率和合成自然度上有显著提升。
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 US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Qwen-Audio-3.0-Realtime, 阿里, 实时语音, 语音识别.
Source attribution: curated from 量子位 (@量子位的朋友们).
