voice-enrollment
The large-model voice replication service leverages advanced large-model technology for feature extraction, replicating a voice without any training process. With only a very short audio sample, it quickly generates a highly similar and natural-sounding custom voice. Large-model voice design uses the FunAudioGen-VD model and supports creating voices from text prompts. Free from any audio quality constraints, it generates high-quality speech based on descriptions of the desired timbre, tone, intonation, speech rate, emotion, and other expressive dimensions for the target scenario, closely reproducing the performance of professional voice actors.
Inference Service Provider
The inference service provider for voice-enrollment is Alibaba Cloud Model Studio.
Model Capabilities
China (Beijing)
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Audio | 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 |
Singapore
Scope: International
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Audio | Output Modality | Text |
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 | — |
Pricing
No public pricing information available.
Rate Limits
China (Beijing)
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 600 |
Singapore
Scope: International
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 600 |