Qwen3.8-LiveTranslate model released
Meet Qwen3.8-LiveTranslate, Qwen's next-generation real-time simultaneous interpretation model! 📢 ...
For users needing real-time translation, this new model from Alibaba offers lower lag and better speaker separation compared to previous versions.
Alibaba's Qwen3.8-LiveTranslate model is a new real-time simultaneous interpretation tool. It reduces average lagging from 2.8 seconds to 2.3 seconds across 60 languages. The model features real-time speaker diarization and synchronized bilingual display. It also uses long-context disambiguation to improve translation consistency.
Meet Qwen3.8-LiveTranslate, Qwen's next-generation real-time simultaneous interpretation model! 📢 ...
Meet Qwen3.8-LiveTranslate, Qwen's next-generation real-time simultaneous interpretation model! 📢 Built on an Interleave architecture, it improves faithfulness, fluency, and conciseness while reducing average lagging (LAAL) from 2.8s to 2.3s across 60 languages. New capabilities: 🙌 - Real-time speaker diarization — distinguishes speakers in multi-party speech and preserves each speaker's voice through more stable voice cloning. - Synchronized bilingual display — source and translation on screen together. - Long-context disambiguation — leverages conversation history to clarify names and terminology for consistent translations. Let's try Qwen3.8-LiveTranslate! 🥳 - Blo qwen.ai/blog?id=qwen3.… gUE - QwenClou qwencloud.com/models/qwen3.8… IWb 💬 33 🔄 39 ❤️ 381 👀 18096 📊 91 ⚡
