Qwen Alibaba Cloud: Qwen3 ASR Flash Realtime

Qwen streaming speech recognition model for live audio over an OpenAI-realtime-style WebSocket. Transcribes incrementally, segmenting speech either with server-side voice activity detection or with client-committed turns, and returns a detected language and an always-on emotion label with every result. Streaming sibling of the batch model qwen3-asr-flash.