Alibaba has launched Qwen Audio 3.0 Realtime, a new speech-to-speech model. The Plus variant of this model has achieved the top position on the Artificial Analysis Speech to Speech Index, surpassing GPT-Realtime-2.1 High. This release marks a significant advancement for Alibaba's Qwen model family in the field of real-time audio processing. AI
IMPACT Sets new SOTA on speech-to-speech benchmarks, challenging existing real-time audio models.
RANK_REASON Frontier-lab model release with system card [lever_c_demoted from frontier_release: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
