LaunchAI ModelsSeptember 20, 2026

Alibaba Qwen releases Qwen3.8-LiveTranslate real-time interpretation model

Qwen3.8-LiveTranslate cuts average interpretation lag to 2.3 seconds across 60 languages, returning translated text and speech while the speaker is still talking. It uses a new Interleave architecture and can optionally take in live video frames.

1 source

More stories today

Open the live feed