{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/qwen3-8-livetranslate/","md":"https://postcutoff.com/m/qwen3-8-livetranslate/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"qwen3-8-livetranslate","name":"Qwen3.8-LiveTranslate (Flash Realtime)","org":"Alibaba (Qwen)","family":"Qwen3.8","released":"2026-09-19","status":"current","type":"audio/speech","modality_in":["audio","image","text"],"modality_out":["audio","text"],"open_weights":false,"model_license":"proprietary","context_window":53248,"max_output":4096,"knowledge_cutoff":null,"pricing":{"audio_input":7.5,"image_input":0.55,"text_output":20,"audio_output":30,"unit":"USD per 1M tokens (QwenCloud list price; press estimates about $1.54 per hour of speech in and out)","source":"https://www.qwencloud.com/models/qwen3.8-livetranslate-flash-realtime"},"price_line":"$7.50 audio in, $20 text out per 1M tokens","access":[{"provider":"QwenCloud (Realtime WebSocket)","model_id":"qwen3.8-livetranslate-flash-realtime","endpoint":"wss://maas.qwencloudapi.com/api-ws/v1/realtime?model=qwen3.8-livetranslate-flash-realtime","docs":"https://www.qwencloud.com/models/qwen3.8-livetranslate-flash-realtime"},{"provider":"Alibaba Cloud Model Studio","model_id":"qwen3.8-livetranslate-flash-realtime","docs":"https://www.alibabacloud.com/help/en/model-studio/models"}],"capabilities":[{"name":"Simultaneous interpretation with lower lag","detail":"Streams translated speech and text while the speaker is still talking; average lagging (LAAL) cut from 2.8 s to 2.3 s across 60 languages with a new 'Interleave' architecture.","first":false,"discovered":"launch","source":"https://x.com/Alibaba_Qwen/status/2101206705111757253"},{"name":"Multi-speaker diarization with per-speaker voice cloning","detail":"Tells speakers apart in multi-party speech and keeps each speaker's own voice in the translated audio; synchronized bilingual on-screen display.","first":false,"discovered":"launch","source":"https://x.com/Alibaba_Qwen/status/2101206705111757253"},{"name":"Long-context disambiguation","detail":"Uses conversation history to keep names and terminology consistent across a session.","first":false,"discovered":"launch","source":"https://x.com/Alibaba_Qwen/status/2101206705111757253"}],"entry":"2026-09-23-qwen-audio-3-1","notes":"Understands 60 languages and speaks 29 (the rest get text-only translation). Thinker-talker hybrid MoE on the Qwen-Omni stack (press). API-only, no open weights and no announced timeline for them. MindStudio's hands-on found short sentences fine but weak end-of-turn detection, so developers need their own turn-taking logic. Announced on X 2026-09-19 (294k views by 2026-09-29), shortly before Apsara 2026.","verified":"2026-09-29","body_md":"Alibaba's hosted real-time interpretation model, a competitor to gpt-realtime-translate and Gemini 3.5 Live Translate.\n\nSources: https://x.com/Alibaba_Qwen/status/2101206705111757253 · https://qwen.ai/blog?id=qwen3.8-livetranslate · https://www.qwencloud.com/models/qwen3.8-livetranslate-flash-realtime · https://www.marktechpost.com/2026/09/19/alibaba-qwen-team-releases-qwen3-8-livetranslate/ · https://www.mindstudio.ai/blog/qwen3-8-livetranslate-hands-on","page_url":"https://postcutoff.com/m/qwen3-8-livetranslate/","standing":{"kind":"speech and audio","newer_count":22,"newer":[{"id":"nemotron-3-5-transcribe","name":"NVIDIA Nemotron 3.5 Transcribe (30B-A4B)","org":"NVIDIA","released":"2026-10-28","page_url":"https://postcutoff.com/m/nemotron-3-5-transcribe/"},{"id":"hy-simulmt-30b-a3b","name":"Hy-SimulMT-30B-A3B","org":"Tencent","released":"2026-10-22","page_url":"https://postcutoff.com/m/hy-simulmt-30b-a3b/"},{"id":"eleven-realtime-v1-max","name":"Eleven Realtime v1 Max / Mini","org":"ElevenLabs","released":"2026-10-20","page_url":"https://postcutoff.com/m/eleven-realtime-v1-max/"},{"id":"voxtral-mini-transcribe-3","name":"Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-mini-transcribe-3/"},{"id":"voxtral-small-transcribe-3","name":"Voxtral Small Transcribe 3","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-small-transcribe-3/"}],"before":{"id":"qwen3-asr","name":"Qwen3-ASR (0.6B / 1.7B) + Qwen3-ForcedAligner","org":"Alibaba (Qwen)","released":"2026-01-29","page_url":"https://postcutoff.com/m/qwen3-asr/"},"after":{"id":"qwen-audio-3-1-tts-next","name":"Qwen-Audio-3.1-TTS-Next","org":"Alibaba (Qwen)","released":"2026-09-22","page_url":"https://postcutoff.com/m/qwen-audio-3-1-tts-next/"},"weights":"closed","licence":"proprietary","licence_permissive":false,"summary":"Closed weights; access is hosted only."}}