Skip to navigation

Prerequisites (NGC authentication, secrets, high-speed network, and the topology-aware scheduler) and Holoscan for Media platform setup are covered in Getting Started. Confirm in particular that the cluster meets the Scheduler and NUMA Topology requirements before running helm install; otherwise the NIM pod stays Pending with a cannot align container event.

Pull Helm Charts

Add the Helm repository and pull the charts. Use chart version 1.2.0 (listed in the NGC catalog for Studio Voice on Holoscan for Media).

export NGC_API_KEY=<PASTE_API_KEY_HERE>
helm repo add nim-repo \
https://helm.ngc.nvidia.com/nim/nvidia/ \
'--username=$oauthtoken' --password=$NGC_API_KEY
helm repo update

Pull the charts:

helm pull nim-repo/nvidia-studio-voice-h4m-sample --version 1.2.0
helm pull nim-repo/nvidia-studio-voice-h4m-service --version 1.2.0
helm pull nim-repo/nvidia-studio-voice-h4m-operator --version 1.2.0

Deployment Options

The following pages describe Helm-based installation for Studio Voice:

  • NIM Service Chart (nvidia-studio-voice-h4m-service) — NIM service deployment only, for integration into a custom pipeline.
  • Kubernetes Operator Chart (nvidia-studio-voice-h4m-operator) — Operator controller and NvidiaStudioVoiceMediaFunction custom resource.
  • End-to-End Demo Chart (nvidia-studio-voice-h4m-sample) — Sender, NIM service, and receiver deployed as a single Helm release for evaluation.

Helm values and operator custom resource fields are summarized in Configuration Reference.