Alibaba Qwen Team Releases Qwen3.8-LiveTranslate: A Real-Time Interpretation Model That Cuts Average Lag to 2.3 Seconds Across 60 Languages

Qwen introduced the Qwen3.8-LiveTranslate simultaneous translation model with Interleave architecture, cutting average LAAL latency from 2.8 to 2.3 seconds. It understands 60 languages, voices 29, supports speaker diarization and bilingual output, and is available via Alibaba Cloud Model Studio and QwenCloud.

• Average translation latency cut from 2.8 to 2.3 seconds (18%)
• Understands 60 languages, voices 29, other 31 text-only
• One hour of speech translation in Singapore costs about $1.54
• Context 53,248 tokens, limit 10 requests and 100k tokens per minute