Qwen3.8-LiveTranslate-Flash-Realtime is a multilingual real-time audio and video translation model. It accepts audio and images and produces text and audio. It understands 60 languages and supports speech output in 29 languages.
Inference Service Provider
The inference service provider for qwen3.8-livetranslate-flash-realtime is Alibaba Cloud Model Studio.
Model Capabilities
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Audio, Image | Output Modality | Text, Audio |
Model Experience | Unsupported | Function Calling | Unsupported |
Structured Outputs | Unsupported | Web Search | Unsupported |
Prefix Completion | Unsupported | Context Caching | Unsupported |
Batch Inference | Unsupported | Fine-tuning | Unsupported |
Context Limits
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | 49152 | Max Output Length | 4096 |
Context Window | 53248 |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
- Singapore
- China (Beijing)
Scope: International
| Billing Item | Price (USD) | Unit |
|---|---|---|
Audio input | 7.5 | Per million tokens |
Image input | 0.55 | Per million tokens |
Text output | 20 | Per million tokens |
Audio output | 30 | Per million tokens |
Rate Limits
- Singapore
- China (Beijing)
Scope: International
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 10 |
TPM (Tokens Per Minute) | 100,000 |
API Usage
Call the model through the WebSocket Realtime API with model ID qwen3.8-livetranslate-flash-realtime. For the endpoint and examples, see the real-time translation guide.
Use session.output_modalities to configure output modalities. Translated text is streamed through response.text.delta or response.audio_transcript.delta. Parameters and events differ from qwen3.5-livetranslate-flash-realtime; see Client events and Server events.