[Alibaba Releases Qwen-Audio-3.0-Realtime, Voice AI Actively Utilizes Tools to Perform Tasks] According to monitoring by Beating, Alibaba has launched the real-time voice model Qwen-Audio-3.0-Realtime. It can respond within milliseconds and actively utilize external tools such as maps, APIs, MCP, and knowledge bases during conversations. Users do not need to explicitly state 'use tools.' For example, if a user first asks about nearby Sichuan restaurants and then inquires which one has high ratings and is close by, the model will remember the previous query results and continue searching and answering. The model can also listen while speaking, allowing users to interrupt at any time. In noisy environments or during multi-person conversations, it attempts to identify the primary speaker to reduce interruptions caused by background noise. The voice adjusts its tone, pace, and emotion according to the context. The official release includes a more powerful Plus version and a faster-response Flash version, both of which are now available on Alibaba Cloud Bailian. [Original Link]