Qwen launches real-time translation model: 60-language simultaneous interpretation with 2.3s lag
airesearch12 · x · 2026-09-19
Qwen has dropped its next-gen real-time translation model, targeting simultaneous interpretation:
- Simultaneous interpretation across 60 languages
- Average translation lag cut from 2.8s to 2.3s
- Real-time speaker diarization for multi-person conversations
- Synchronized bilingual subtitles
- Long-context understanding for names and terminology
- Built on the new Interleave architecture
Related event: Qwen Releases LiveTranslate Real-Time Interpretation Model(2 posts)→
More from Multimodal
- Qwen Image 2.1 PR lands in ComfyUI, open weights look nearly certain — Altruistic_Heat_9531 · 2026-09-19
- Director's Console update adds model-specific prompt guides, goes MIT licensed — npittas · 2026-09-19
- Magnific founder's secret 6-month AI-generated series 'Backrooms Nemoris' premieres — Loo_Atreides · 2026-09-19
- Prompting AI video to look real: ask for a human's phone-camera mistakes, not perfection — socialwithaayan · 2026-09-19
- Flux 2 Klein struggles with style+palette transfer from reference images — wacomlover · 2026-09-19
- Dev spends two weeks having Astra 3D-model every object in a three.js scene — danbri · 2026-09-19