Skip to main content
Audio modelActive

Qwen3.8-LiveTranslate

Alibaba

Released
September 18, 2026
Data date
September 22, 2026
Model class
Real-time simultaneous interpretation model
Languages
60 languages
Access
API

Qwen3.8-LiveTranslate targets real-time interpretation rather than general text chat. It translates audio and images while producing text and audio, supports 60 languages, and can speak 29 of them. Speaker separation, synchronized bilingual output, and long-context disambiguation matter when a conversation has multiple voices and the attribution matters as much as the words.

The WebSocket Realtime API exposes the endpoint as qwen3.8-livetranslate-flash-realtime and caps input at 49,152 tokens and output at 4,096 tokens within a 53,248-token context. Alibaba exposes the model through Model Studio as an API; its model documentation names no license or weight release. Function calling and structured outputs are outside its contract.

Specifications and access

SpecificationValue and source
Weights
ProprietarySource
Model class
Real-time simultaneous interpretation modelSource
Access
APISource
API model ID
qwen3.8-livetranslate-flash-realtimeSource
Input
Audio, imageSource
Output
Text, audioSource
Languages
60 languagesSource
Context window
53,248 tokensSource
Maximum input
49,152 tokensSource
Maximum output
4,096 tokensSource
Capabilities
Speaker separation, synchronized bilingual output, and long-context disambiguationSource
Audio input price
US$7.50 / 1M tokens, SingaporeSource
Image input price
US$0.55 / 1M tokens, SingaporeSource
Text output price
US$20 / 1M tokens, SingaporeSource
Audio output price
US$30 / 1M tokens, SingaporeSource