Alibaba's Tongyi platform launches Qwen-Audio-3.0-Realtime, a real-time voice interaction model.

Alibaba's Tongyi Labs launched the real-time voice interaction model Qwen-Audio-3.0-Realtime (formerly Fun-Realtime-AudioChat), which supports context-based dynamic adjustment of tone and emotion, timbre cloning, voiceprint-level background filtering, and multimodal duplex dialogue. It ranked first in the Artificial Analysis speech inference sub-item, surpassing GPT-Realtime-2.