Qwen-TTS is the first speech synthesis model in the Qwen series, supporting Chinese, English, and mixed inputs. It adaptively adjusts output tone based on text, offers natural voice quality, and supports streaming output.
Inference Service Provider
The inference service provider for qwen-tts is Alibaba Cloud Model Studio.
Model Capabilities
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text | Output Modality | 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 | 512 | Max Output Length | 7680 |
Context Window | 8192 |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
- China (Beijing)
| Billing Item | Price (USD) | Unit |
|---|---|---|
Input: Text | 0.23 | Per 1M tokens |
Output: Audio | 1.434 | Per 1M tokens |
Rate Limits
- China (Beijing)
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 10 |
TPM (Tokens Per Minute) | 100,000 |
Dynamic Updates
qwen-tts-latest
Qwen-TTS is the first speech synthesis model in the Qwen series, supporting Chinese, English, and mixed inputs. It adaptively adjusts output tone based on text, offers natural voice quality, and supports streaming output.
Inference Service Provider
The inference service provider for qwen-tts-latest is Alibaba Cloud Model Studio.
Model Capabilities
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text | Output Modality | 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 | 512 | Max Output Length | 7680 |
Context Window | 8192 |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
- China (Beijing)
| Billing Item | Price (USD) | Unit |
|---|---|---|
Input: Text | 0.23 | Per 1M tokens |
Output: Audio | 1.434 | Per 1M tokens |
Rate Limits
- China (Beijing)
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 10 |
TPM (Tokens Per Minute) | 100,000 |
Snapshot Versions
qwen-tts-2025-05-22
Qwen-TTS is the first speech synthesis model in the Qwen series, supporting Chinese, English, and mixed inputs. It adaptively adjusts output tone based on text, offers natural voice quality, and supports streaming output.
Inference Service Provider
The inference service provider for qwen-tts-2025-05-22 is Alibaba Cloud Model Studio.
Model Capabilities
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text | Output Modality | 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 | 512 | Max Output Length | 7680 |
Context Window | 8192 |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
- China (Beijing)
| Billing Item | Price (USD) | Unit |
|---|---|---|
Input: Text | 0.23 | Per 1M tokens |
Output: Audio | 1.434 | Per 1M tokens |
Rate Limits
- China (Beijing)
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 10 |
TPM (Tokens Per Minute) | 100,000 |
qwen-tts-2025-04-10
Qwen-TTS is the first speech synthesis model in the Qwen series, supporting Chinese, English, and mixed inputs. It adaptively adjusts output tone based on text, offers natural voice quality, and supports streaming output.
Inference Service Provider
The inference service provider for qwen-tts-2025-04-10 is Alibaba Cloud Model Studio.
Model Capabilities
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text | Output Modality | 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 | 512 | Max Output Length | 7680 |
Context Window | 8192 |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
- China (Beijing)
| Billing Item | Price (USD) | Unit |
|---|---|---|
Input: Text | 0.23 | Per 1M tokens |
Output: Audio | 1.434 | Per 1M tokens |
Rate Limits
- China (Beijing)
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 10 |
TPM (Tokens Per Minute) | 100,000 |