Support Matrix#
Models#
Model Name |
Model ID |
Publisher |
|---|---|---|
Studio Voice |
studio-voice |
NVIDIA |
Optimized Configurations#
GPU |
Precision |
|---|---|
T4 |
FP16 + FP32 |
A2, A10, A16, A40 |
FP16 + FP32 |
A30, A100 |
FP16 + FP32 |
L4, L40 |
FP16 + FP32 |
H100 |
FP16 + FP32 |
B100, B200 |
FP16 + FP32 |
B40, RTX PRO 6000 Blackwell Server Edition |
FP16 + FP32 |
Other Architectures (Consumer RTX GPUs)#
Consumer GPU |
Precision |
|---|---|
RTX 4090 |
FP16 + FP32 |
RTX 5090, 5080 |
FP16 + FP32 |
The Studio Voice NIM is compatible with professional and consumer GPUs that have Tensor cores and are based on the following NVIDIA architectures: Blackwell, Ada, Ampere, and Turing. The RTX-based GPUs are also supported.
Software#
Linux Requirements#
Prerequisites for Studio Voice NIM on Linux:
Prerequisite |
Version |
Download and install steps |
|---|---|---|
NVIDIA Graphic Drivers for linux |
571.21+ |
|
Docker |
latest |
Ubuntu, CentOS, Debian: https://docs.docker.com/engine/install/ |
NVIDIA Container Toolkit |
latest |
Installation and configuration instructions: https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html |