nvidia/studiovoice

Pull and run nvidia/studiovoice using Docker (this will download the full model and run it in your local environment)

Get API KeyCopy Code
$ docker login nvcr.io
Username: $oauthtoken
Password: <PASTE_API_KEY_HERE>

NVIDIA Maxine Studio Voice NIM uses gRPC APIs for inferencing requests.

A NGC API KEY is required to download the appropriate models and resources when starting the NIM.

If you are not familiar with how to create the NGC_API_KEY environment variable, the simplest way is to export it in your terminal:

Copy Code
export NGC_API_KEY=<PASTE_API_KEY_HERE>

Run one of the following commands to make the key available at startup:

Copy Code
# If using bash
echo "export NGC_API_KEY=<value>" >> ~/.bashrc

# If using zsh
echo "export NGC_API_KEY=<value>" >> ~/.zshrc

Other, more secure options include saving the value in a file, so that you can retrieve with cat $NGC_API_KEY_FILE, or using a password manager.

The following command launches the Maxine Studio Voice NIM container with the gRPC service. Find reference to runtime parameters for the container here.

Copy Code
docker run -it --rm --name=maxine-studio-voice \
  --net host \
  --runtime=nvidia \
  --gpus all \
  --shm-size=8GB \
  -e NGC_API_KEY=$NGC_API_KEY \
  -e NIM_MODEL_PROFILE=<nim_model_profile> \
  -e FILE_SIZE_LIMIT=36700160 \
  nvcr.io/nim/nvidia/maxine-studio-voice:latest

Ensure you use the appropriate NIM_MODEL_PROFILE for your GPU. For more information about NIM_MODEL_PROFILE, refer to the the NIM Model Profile Table.

Please note, the flag --gpus all is used to assign all available GPUs to the docker container. This fails on multiple GPU unless all GPUs are same. To assign specific GPU to the docker container (in case of different multiple GPUs available in your machine) use --gpus '"device=0,1,2..."' "'`

If the command runs successfully, you get a response similar to the following.

Copy Code
+-------------------------------+---------+--------+
| Model                         | Version | Status |
+-------------------------------+---------+--------+
| maxine_nvcf_studiovoice       | 1       | READY  |
| studio_voice_high_quality-48k | 1       | READY  |
+-------------------------------+---------+--------+

I1126 09:22:21.040917 31 metrics.cc:877] "Collecting metrics for GPU 0: NVIDIA GeForce RTX 4090"
I1126 09:22:21.046137 31 metrics.cc:770] "Collecting CPU metrics"
I1126 09:22:21.046253 31 tritonserver.cc:2598] 
+----------------------------------+------------------------------------------------------------------------------------------------+
| Option                           | Value                                                                                          |
+----------------------------------+------------------------------------------------------------------------------------------------+
| server_id                        | triton                                                                                         |
| server_version                   | 2.50.0                                                                                         |
| server_extensions                | classification sequence model_repository model_repository(unload_dependents) schedule_policy m |
|                                  | odel_configuration system_shared_memory cuda_shared_memory binary_tensor_data parameters stati |
|                                  | stics trace logging                                                                            |
| model_repository_path[0]         | /opt/maxine/models                                                                             |
| model_control_mode               | MODE_EXPLICIT                                                                                  |
| startup_models_0                 | maxine_nvcf_studiovoice                                                                        |
| startup_models_1                 | studio_voice_high_quality-48k                                                                  |
| strict_model_config              | 0                                                                                              |
| model_config_name                |                                                                                                |
| rate_limit                       | OFF                                                                                            |
| pinned_memory_pool_byte_size     | 268435456                                                                                      |
| cuda_memory_pool_byte_size{0}    | 67108864                                                                                       |
| min_supported_compute_capability | 6.0                                                                                            |
| strict_readiness                 | 1                                                                                              |
| exit_timeout                     | 30                                                                                             |
| cache_enabled                    | 0                                                                                              |
+----------------------------------+------------------------------------------------------------------------------------------------+

I1126 09:22:21.048202 31 grpc_server.cc:2558] "Started GRPCInferenceService at 127.0.0.1:9001"
I1126 09:22:21.048377 31 http_server.cc:4704] "Started HTTPService at 127.0.0.1:9000"
I1126 09:22:21.089295 31 http_server.cc:362] "Started Metrics Service at 127.0.0.1:9002"
Maxine GRPC Service: Listening to 0.0.0.0:8001

By default Maxine Studio Voice gRPC service is hosted on port 8001. You will have to use this port for inferencing requests.

We have provided a sample client script file in our GitHub repo. The script could be used to invoke the Docker container using the following instructions.

Download the Maxine Studio Voice Python client code by cloning the NVIDIA Maxine NIM Clients Repository:

Copy Code
git clone https://github.com/NVIDIA-Maxine/nim-clients.git
cd nim-clients/studio-voice

Install the dependencies for the NVIDIA Maxine Studio Voice Python client:

Copy Code
sudo apt-get install python3-pip
pip install -r requirements.txt

Go to scripts directory

Copy Code
cd scripts

Run the command to send gRPC request

Copy Code
python studio_voice.py --target <target_ip:port> --input <input_file_path> --output <output_file_path>

To view details of command line arguments run this command

Copy Code
python studio_voice.py -h

You will get a response similar to the following.

Copy Code
usage: studio_voice.py [-h] [--target TARGET] [--input INPUT] [--output OUTPUT]

Process wav audio files using gRPC and apply Studio Voice.

options:
  -h, --help       show this help message and exit
  --target TARGET  The target gRPC server address.
  --input INPUT    The path to the input audio file.
  --output OUTPUT  The path for the output audio file.

For more details on getting started with this NIM including configuring using parameters, visit the NVIDIA Maxine Studio Voice NIM Docs.