On July 15, 2026, Alibaba rolled out its latest innovation—the real-time voice interaction dialogue model, Qwen-Audio-3.0-Realtime. This model represents a significant leap forward, featuring simultaneous upgrades across four key dimensions: intelligence quotient, Agent tool invocation, empathetic dialogue, and the fluency of duplex interaction. Notably, the model introduces two distinct versions: a more robust Plus variant boasting enhanced reasoning capabilities, and a swift Flash version tailored for rapid response. These versions are ideally suited for a variety of scenarios, including intelligent customer service, education and training, entertainment interaction, and emotional companionship. Alibaba is committed to delivering a voice interaction experience that is not only swift but also highly intelligent.
