Qwen
Qwen @Alibaba_Qwen · x · 2026-09-19 · ★★★ · archived
Cited as a source by: 2026-09-23-qwen-audio-3-1, qwen3-8-livetranslate
Summary
Archived text
Meet Qwen3.8-LiveTranslate, Qwen's next-generation real-time simultaneous interpretation model! 📢
Built on an Interleave architecture, it improves faithfulness, fluency, and conciseness while reducing average lagging (LAAL) from 2.8s to 2.3s across 60 languages.
New capabilities: 🙌
- Real-time speaker diarization — distinguishes speakers in multi-party speech and preserves each speaker's voice through more stable voice cloning.
- Synchronized bilingual display — source and translation on screen together.
- Long-context disambiguation — leverages conversation history to clarify names and terminology for consistent translations.
Let's try Qwen3.8-LiveTranslate! 🥳
Media: https://pbs.twimg.com/media/HSj7AQWaEAAxZrB.jpg?name=orig
views 294378 · likes 2691 · reposts 299 · replies 111 (at fetch time)
Archived 2026-09-29 via fxtwitter (unofficial).
Archived text
Meet Qwen3.8-LiveTranslate, Qwen's next-generation real-time simultaneous interpretation model! 📢
Built on an Interleave architecture, it improves faithfulness, fluency, and conciseness while reducing average lagging (LAAL) from 2.8s to 2.3s across 60 languages.
New capabilities: 🙌
- Real-time speaker diarization — distinguishes speakers in multi-party speech and preserves each speaker's voice through more stable voice cloning.
- Synchronized bilingual display — source and translation on screen together.
- Long-context disambiguation — leverages conversation history to clarify names and terminology for consistent translations.
Let's try Qwen3.8-LiveTranslate! 🥳
Media: https://pbs.twimg.com/media/HSj7AQWaEAAxZrB.jpg?name=orig
views 294378 · likes 2691 · reposts 299 · replies 111 (at fetch time)
Archived 2026-09-29 via fxtwitter (unofficial).
Related events
- Alibaba launches Qwen-Audio-3.1 five-model voice stack and cuts audio API prices up to 95% 2026-09-23
All posts · id: x-alibaba_qwen-2101206705111757253