Qwen has released Qwen3.8-LiveTranslate, a real-time simultaneous interpretation model built on a new Interleave architecture. It also adds real-time speaker diarization with stable voice cloning, synchronized bilingual display, and long-context disambiguation for names and terms.
Qwen has released Qwen3.8-LiveTranslate, a real-time simultaneous interpretation model built on a new Interleave architecture.
The model understands 60 languages, speaks 29, and is available now as a WebSocket API on Alibaba Cloud Model Studio and QwenCloud.
It also adds real-time speaker diarization with stable voice cloning, synchronized bilingual display, and long-context disambiguation for names and terms.
The page is ready to read now. The fuller skim-friendly version will appear here automatically.
Qwen has released Qwen3.8-LiveTranslate, a real-time simultaneous interpretation model built on a new Interleave architecture. It also adds real-time speaker diarization with stable voice cloning, synchronized bilingual display, and long-context disambiguation for names and terms. The model understands 60 languages, speaks 29, and is available now as a WebSocket API on Alibaba Cloud Model Studio and QwenCloud.
Open the app view to save this story, compare related coverage, and continue from the same source.