Alibaba Qwen real-time speech interpreter that translates live audio or video with speaker labeling and voice cloning.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
Qwen 3.8 Live Translate is a real-time interpretation model from Alibaba's Qwen team. It translates live audio or video streams, separates and labels individual speakers, and can clone voices so the translated speech keeps the speaker's voice characteristics.
According to a creator summary, it supports 60 input languages and 29 spoken output languages. Alibaba's claims, as relayed by that summary, are that it leads competing systems on win rate, latency and error rate. These benchmark claims were not independently verified here.
It is offered through an API and an online demo. The official blog page content could not be retrieved in detail, so pricing, licensing, and weight availability are not confirmed.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Real-time AI interpreter that translates live audio or video, separates and labels speakers, and clones voices. It supports 60 input languages and 29 spoken output languages. It leads competitors on win rate, latency and error rate, and is available via API with an online demo.
Closest neighbours by meaning, not just by category.
Model · Alibaba
Alibaba Qwen model for live speech translation across 60 languages that uses visual context and streams translations early.
Model · Tencent
Tencent Hunyuan's real-time Chinese-English speech-to-speech simultaneous translation model with voice cloning.
Model · Google
Google's real-time speech translation model that preserves the speaker's voice, intonation and pacing across 70+ languages.
Model · Alibaba
Alibaba's proprietary multimodal agentic model in the Qwen 3.7 series, aimed at long-horizon coding and tool-use tasks.
Model · Alibaba
Alibaba's Qwen3.8 Flash Next: a 125B-parameter MoE language model with about 6B active parameters, previewing Qwen 4 design.
Model · Alibaba
Alibaba's real-time audio-visual interactive character video model that renders speech and free-form actions.
