voice-enrollment

Updated at:

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)

CapabilitySupportCapabilitySupport

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

CapabilitySupportCapabilitySupport

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

ParameterValueParameterValue

Max Input Length

—

Max Output Length

—

Context Window

—

Pricing

No public pricing information available.

Rate Limits

China (Beijing)

ParameterValue

RPM (Requests Per Minute)

600

Singapore

Scope: International

ParameterValue

RPM (Requests Per Minute)

600

API usage