Skip to main content
Speech-to-Speech

qwen-audio-3.1-realtime-plus

A real-time duplex speech model with text and audio input and output, function calling, web search, and voice cloning.

The inference service provider is Alibaba Cloud Model Studio. The default voice is longanqian_v3.1. For integration, supported voices, and parameters, see the real-time speech guide. Enable web search with enable_search. Web search and Function Calling cannot be enabled together.

Context limits

ParameterLimit (tokens)
Context window262,144
Max input length245,760
Max output length16,384

Pricing and rate limits

  • Singapore
  • China (Beijing)
Prices are per million tokens.
Model IDText inputAudio inputText outputAudio output
qwen-audio-3.1-realtime-plus$0.8$6.4$6.4$24
Rate limits: 60 RPM and 100,000 TPM.
Token Plan
Model Playground
  • Audio generation
  • Music generation
Statistics and Monitoring
Asset Center
Support