Qwen3.8 LiveTranslate Flash Realtime
Qwen3.8 LiveTranslate understands 60 languages and produces speech in 29. Input can contain audio and images; output can contain translated text and audio.
Technical details
The model does not offer tools, web search, fine-tuning or context caching. Its events differ from the Qwen3.5 translation interface.Qwen3.8 LiveTranslate
Practical use
Practical guidance. Check the requested output language against the spoken-output list. A supported source language does not mean the same language is available as synthesized speech. Review names and specialist terms with representative conversations.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Model identifiers | qwen3.8-livetranslate-flash-realtime |
| Context | 53,248 tokens, with 49,152 input tokens and 4,096 output tokens.Qwen3.8 LiveTranslate |
| Access | Beijing and Singapore; WebSocket, WebRTC or AOQ.Qwen3.8 LiveTranslate |
Related models
- Qwen3.8 Omni Flash
Alibaba · Qwen Omni
Multimodal model that returns text from audio, video, image and text inputs, with 113 audio languages and dialects.
Launch date not confirmedAPI - Qwen3.8 Omni Flash Realtime
Alibaba · Qwen Omni
Real-time model with streaming audio and video input, text and speech output, and tool support.
Launch date not confirmedAPI