Using Qwen3.8-LiveTranslate on Alibaba Cloud PAI-EAS
Implementation guide · Qwen3.8 · Alibaba
Alibaba Cloud PAI-EAS exposes Qwen3.8-LiveTranslate through model ID qwen3.8-livetranslate-flash-realtime. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-09-21. Next refresh: weekly.
Quick Start
- 1
- 2Use the Alibaba Cloud PAI-EAS SDK or REST API to call
qwen3.8-livetranslate-flash-realtime— see the documentation for request format. - 3
Code Examples
Pricing on Alibaba Cloud PAI-EAS
| Type | Price (per 1M) |
|---|---|
| Input tokens | $7.50 |
| Output tokens | $20.00 |
Capabilities
About Qwen3.8-LiveTranslate
Qwen3.8-LiveTranslate is Alibaba Qwen's next-generation real-time simultaneous interpretation model, announced via @Alibaba_Qwen on 2026-09-19 (tip links blog id qwen3.8-livetranslate and QwenCloud). Tip: Interleave architecture; improves faithfulness/fluency/conciseness; reduces average lagging (LAAL) from 2.8s to 2.3s across 60 languages; real-time speaker diarization with more stable voice cloning; synchronized bilingual display; long-context disambiguation via conversation history. First-party QwenCloud card Qwen3.8-LiveTranslate-Flash-Realtime (API id qwen3.8-livetranslate-flash-realtime): real-time version of Qwen3.8-LiveTranslate-Flash; multilingual simultaneous audio and video interpretation; understand 60 languages / speak 29; WebSocket realtime endpoint wss://maas.qwencloudapi.com/api-ws/v1/realtime?model=qwen3.8-livetranslate-flash-realtime. QwenCloud limits: Max Input 49K / Max Output 4K / Context 53K; TPM 100K; RPM 10.