cosyvoice-V2 is a generative speech synthesis model from Tongyi Lab, built on a large-scale pretrained language model. It combines text understanding with speech generation and supports real-time streaming text-to-speech synthesis.
Inference Service Provider
The inference service provider for cosyvoice-v2 is QwenCloud.
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 | — | Max Output Length | — |
Context Window | — |
Rate Limits
- China North 2 (Beijing)
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 180 |