Qwen-Audio-3.1-TTS-Flash is a speech synthesis model for real-time interactions. It supports streaming speech synthesis and a range of system voices for voice assistants, real-time conversations, and customer service.
Inference Service Provider
The inference service provider for qwen-audio-3.1-tts-flash is Alibaba Cloud Model Studio.
Model Capabilities
| Input Modality | Output Modality |
|---|
| Text | Audio |
Context Limits
| Max Input Length | Max Output Length |
|---|
| — | — |
Pricing
This page only shows standard model API pricing, excluding limited-time promotions. Visit the Model Studio console for promotional offers.
Singapore
| Billing Item | Price (USD) | Unit |
|---|
| Input | 0.23 | Per million tokens |
| Output | 1.87 | Per million tokens |
China (Beijing)
| Billing Item | Price (USD) | Unit |
|---|
| Input | 0.212 | Per million tokens |
| Output | 1.696 | Per million tokens |
Rate Limits
Singapore
| Parameter | Value |
|---|
| RPM (Requests Per Minute) | 180 |
China (Beijing)
| Parameter | Value |
|---|
| RPM (Requests Per Minute) | 180 |
Invocation