Alibaba releases a neural network for simultaneous video translation
Alibaba has unveiled Qwen3.5-LiveTranslate-Flash, a model that translates video and audio simultaneously. It handles 60 input languages and 29 output languages with a latency of 2.8 seconds. The model clones the speaker's voice and reads their facial expressions and on-screen text, which makes the translation sound natural and lively. On the FLEURS and CoVoST2 benchmarks, it outperformed the main competitors.
AI-processed from MarkTechPost; edited by Hamidun News
Alibaba has released Qwen3.5-LiveTranslate-Flash, a neural network for simultaneous speech and video translation in real time. It accepts 60 input languages with a latency of just 2.8 seconds.
What is Qwen3.5-LiveTranslate, and what is it for?
It is a model that translates video and audio at the same time. It sees the speaker on screen, hears the speech and converts it into speech in the target language, keeping the output in sync, natural-sounding and emotionally expressive.
How many languages does the
Qwen video translation network support? It translates from 60 input languages and delivers output in 29 languages, with a latency of just 2.8 seconds.
What is the latency of Alibaba's AI translator?
Qwen3.5-LiveTranslate-Flash has a latency of just 2.8 seconds when translating video and speech.
How many languages does the translator support?
It translates from 60 input languages and delivers output in 29 languages.
How many languages does Alibaba Qwen3.5 translate into?
From 60 input languages into 29 output languages.
- Nov 1, 2026Pika Labs releases open video model H3 Flex: 6 steps instead of 50
- Nov 1, 2026Google's StreamVibe video agent beats other models by 10.7% on response timing and quality
- Oct 31, 2026AI cartoon series: a 24-second episode built ten ways, the best cost 162 credits
- Oct 31, 2026Anthropic: Fold Subagents Back Into a Single Loop — One Customer's Tasks Ran Twice as Fast
Key Questions Answered
What is Qwen3.5-LiveTranslate, and what is it for?
It is a model that translates video and audio at the same time. It sees the speaker on screen, hears the speech and converts it into speech in the target language, keeping the output in sync, natural-sounding and emotionally expressive.
How many languages does the Qwen video translation network support?
It translates from 60 input languages and delivers output in 29 languages, with a latency of just 2.8 seconds.
What is the latency of Alibaba's AI translator?
Qwen3.5-LiveTranslate-Flash has a latency of just 2.8 seconds when translating video and speech.
How many languages does the translator support?
It translates from 60 input languages and delivers output in 29 languages.
Test Frontier LLMs & Autonomous Agents in One Workspace
Run Claude Opus 5.5, GPT-6, Gemini 3.1, and DeepSeek side-by-side in Nomad AI (nomadnet.ai) — unified model routing, deep research, and multimodal workflows under one subscription.
The AI world, distilled — once a week
Seven stories that actually mattered, hand-picked. No noise, no reposts, no press releases.
Done! Check your inbox for a confirmation.