Alibaba's Qwen team has released Qwen3.5-LiveTranslate-Flash, a real-time multimodal translation model that significantly reduces latency to 2.8 seconds. This new model expands language support to 60 input languages and 29 output languages, while also incorporating visual cues like lip movements to improve accuracy in noisy environments. A standout feature is its ability to clone the original speaker's voice in real-time for translated output, creating a more natural listening experience. AI
影响 Enhances real-time multilingual communication by reducing latency and improving accuracy through multimodal input and voice cloning.
排序理由 Model release from a major AI lab (Alibaba) with significant performance improvements and new capabilities. [lever_c_demoted from frontier_release: ic=2 ai=1.0]
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
