Post-Cutoff.com
  1. Home
  2. Models
  3. Qwen3.8-LiveTranslate (Flash Realtime)

Qwen3.8-LiveTranslate (Flash Realtime)

Alibaba (Qwen)currentaudio/speechQwen3.8

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.

Context window
53,248 tokens
Max output
4,096 tokens
Input
audio, image, text
Output
audio, text
License
proprietary
Pricing
audio input: $7.5 · image input: $0.55 · text output: $20 · audio output: $30 (USD per 1M tokens (QwenCloud list price; press estimates about $1.54 per hour of speech in and out)) source
Verified
2026-09-29

How to call it

ProviderModel idEndpoint / URLDocs
QwenCloud (Realtime WebSocket)qwen3.8-livetranslate-flash-realtimewss://maas.qwencloudapi.com/api-ws/v1/realtime?model=qwen3.8-livetranslate-flash-realtimedocs
Alibaba Cloud Model Studioqwen3.8-livetranslate-flash-realtime—docs

Notable capabilities (3)

Timeline entry

  1. Alibaba launches Qwen-Audio-3.1 five-model voice stack and cuts audio API prices up to 95% ★★★

    Around its 2026 Apsara Conference Alibaba's Qwen team released Qwen-Audio-3.1: upgraded ASR, TTS and full-duplex Realtime models plus two new ones (ASR-Next for audio understanding, TTS-Next for one-pass speech+SFX+ambience generation), with price cuts of ~70% (TTS), ~85% (Realtime) and up to 95%…

Other Alibaba (Qwen) models

Qwen-Audio-3.1-ASR (Flash) · Qwen-Audio-3.1-Realtime (Plus) · Qwen-Audio-3.1-TTS-Next · Qwen3.8-Omni-Flash · Qwen3.8-27B · Qwen3.8-Flash · Qwen3.8-Max · Qwen-Image-3.0 (Pro) · Qwen3.7-Plus · Qwen3-ASR (0.6B / 1.7B) + Qwen3-ForcedAligner · Qwen3-TTS (open weights 0.6B / 1.7B; API qwen3-tts-flash)