Models · MarkTechPost ·

Alibaba Qwen Team Introduces Qwen3.5-LiveTranslate-Flash: Real-Time Multimodal Interpretation Across 60 Languages at 2.8-Second Latency

Alibaba Qwen Team Introduces Qwen3.5-LiveTranslate-Flash: Real-Time Multimodal Interpretation Across 60 Languages at 2.8-Second Latency

Alibaba’s Qwen team released Qwen3.5-LiveTranslate-Flash, a real-time multimodal translation model that processes audio and video together. It supports 60 input languages and speech output in 29 languages, with features including voice cloning, lip-reading, on-screen text understanding, and keyword configuration.

Read the full story at MarkTechPost →