大模型
www.aibase.com ·
千问发布 Qwen3.8-LiveTranslate 同声传译大模型：原文译文同屏，字均延迟降至 2.3 秒
阿里千问推出实时语音翻译模型 Qwen3.8-LiveTranslate，采用 Interleave 统一架构，将字均延迟（LAAL）从 2.8 秒降至 2.3 秒。模型在原有 60 种语言支持基础上新增三项能力：实时说话人分离、原文与译文同屏显示、长上下文消歧以提升人名和术语准确率。底层为基于 Hybrid MoE 的 Thinker–Talker 双模块设计，Thinker 将视频、音频、原文和译文按时间顺序组织为单一因果序列完成理解与翻译，Talker 再结合译文与源音频合成保留原说话人音色的语音。
AI推荐理由 内容给出 Qwen3.8-LiveTranslate 的具体技术细节：Interleave 统一架构、Thinker–Talker 双模块、Hybrid MoE，以及字均延迟从 2.8 秒降至 2.3 秒、支持 60 种语言、新增说话人分离与原文译文同屏等，信息密度较高，对实时语音翻译方向有参考价值。但来源为 AIbase 的转述性报道，非官方首发，缺少可验证的评测数据与独立复现，延迟数字仅来自文章自述，需保留不确定性。
72
正文
Qwen3.8-LiveTranslate Launch: Real-time Translation Large Model with Synchronous Original and Translated Text, Delay Reduced to 2.3 Seconds per Character
AIbase基地
Published inAI News · 3 min read · Sep 20, 2026
5
Qwen3.8-LiveTranslate, the new real-time speech translation model from Alibaba Qwen, reimagines real-time simultaneous interpretation with a unified Interleave architecture. This enhances accuracy, fluency, and conciseness, reducing the average latency per character (LAAL) from 2.8 seconds to 2.3 seconds—this 0.5-second reduction directly determines whether the listening experience feels natural for a field where "a second's delay makes you fall behind."
Building on its support for 60 languages, the new model adds three key pieces that make real-time interpretation truly practical. First, it enables real-time speaker separation, assigning each sentence to the correct person, with more stable voice replication, eliminating issues like confusion between speakers or audio cross-talk. Second, it displays source and translated text simultaneously, allowing listeners to follow along as they listen. Third, it improves long-context disambiguation, enabling the model to understand current content based on previous context, significantly improving accuracy for names and terminology, which are most prone to errors.
The foundation is a Thinker–Talker dual-module design based on Hybrid MoE, using Interleave to connect streaming understanding, text output, and speech generation into one pipeline. The Thinker organizes video, audio, original text, and translation into a single causal sequence, arranging them in time order and generating end-to-end results, completing both "understanding" and "translation" within the same sequence. The Talker then takes the translated text and source audio to synthesize the translation into speech that retains the original speaker's voice—that is, the voice of the speaker remains the same.
This article is from AIbase Daily
Scan to view
Welcome to the [AI Daily] column! This is your daily guide to exploring the world of artificial intelligence. Every day, we present you with hot topics in the AI field, focusing on developers, helping you understand technical trends, and learning about innovative AI product applications.
—— Created by the AIbase Daily Team
© Copyright AIbase Base 2024, Click to View Source -