Is this page helpful?

Operator Configuration#

This page covers Helm values for the nvidia-studio-voice-h4m-operator chart (controller pod) and fields for the NvidiaStudioVoiceMediaFunction custom resource (NIM workload).

Pipeline tuning semantics on the custom resource match the Pipeline Configuration Helm keys.

Operator Helm Chart (nvidia-studio-voice-h4m-operator)#

Values for the operator controller pod (not the NIM deployment):

Configuration	Helm Key	Comment
Operator image	`image.repository`, `image.tag`, `image.pullPolicy`	Default: repo `nvcr.io/nim/nvidia/studio-voice-h4m-operator`, tag `1.2.0`, pull `Always`.
Inline registry credentials (operator pod)	`imageCredentials.*`	Defaults: registry `nvcr.io`, username `$oauthtoken`, password `""`, email `""`; empty password skips chart-created pull secret.
Inline registry credentials (NIM operands)	`mediaFunction.imageCredentials.*`	Same shape as `imageCredentials`; empty password skips the media-function registry secret.
Pull secrets	`imagePullSecrets`	Default: `[{name: ngc-api-key}]` (operator pod image pull).
Default NIM image for operands	`mediaFunction.image`, `mediaFunction.imagePullSecrets`	Defaults: image `nvcr.io/nim/nvidia/studio-voice-h4m:1.2.0`, pull secrets `[{name: ngc-api-key}]`.
Default NIM scheduler	`mediaFunction.schedulerName`	Default: `""` (cluster default); applied to operator-managed NIM pods when the CR omits `spec.schedulerName`. The standalone service and sample Helm charts default to `schedulerName: topo-aware-scheduler` for NUMA-aligned placement and expose it as a Helm value (per-component, or via `global.schedulerName` on the umbrella chart).
Operator replicas	`replicas`	Default: `1`.
Leader election	`leaderElection`	Default: `true`.
Operator pod resources	`resources.*`	Defaults: limits `500m` CPU / `128Mi` memory; requests `10m` CPU / `64Mi` memory.
Metrics	`metrics.enabled`, `metrics.port`	Default: `true`, port `8443`.
Service account	`serviceAccount.create`, `serviceAccount.name`	Default: create `true`, name `""`.

Important

The media-function image is configured when the operator is installed, so NvidiaStudioVoiceMediaFunction instances managed by an operator use the same validated operator and media-function image combination. This approach ensures that the operator and workload are always supported together and avoids compatibility issues.

As a result, CRs managed by an operator share the chart-level mediaFunction.image and mediaFunction.imagePullSecrets configured at install time. To run multiple custom resources with different NIM image tags, deploy multiple operators, each configured with its own mediaFunction.image. For more context, refer to Known Limitations.

Custom Resource (NvidiaStudioVoiceMediaFunction)#

Full YAML example: Example Manifest.

Scheduling and Cluster#

Configuration	CR Path	Comment
Node selector	`spec.nodeSelector`	Kubernetes node labels (for example, `kubernetes.io/hostname`).
Scheduler	`spec.schedulerName`	Optional. Kubernetes `schedulerName` for the Studio Voice NIM operand pod (for example, `topo-aware-scheduler` for NUMA-aligned placement of the GPU, SR-IOV virtual function, and CPU pinning, or `default-scheduler` for clusters that lack a topology-aware scheduler). The operator does not currently validate this field. On a NUMA-spacious cluster, `default-scheduler` typically schedules successfully but is not guaranteed to be NUMA-aligned, so per-packet latency can vary slightly from the Support Matrix figures while remaining within the SMPTE ST 2110-21 envelope. On a NUMA-booked cluster, the kubelet might reject the pod with `TopologyAffinityError`. Refer to Scheduler and NUMA Topology.

Parameters: Network, Resources, Secrets, Security#

Configuration	CR Path	Comment
High-speed networks	`spec.parameters.highSpeedNetwork`	Default name: `media-a-tx-net`; list of `{name}` for Multus.
NIM pod resources	`spec.parameters.resources`	CPU, memory, hugepages, GPU.
NGC model download	`spec.parameters.ngcSecret`	`secretName`, `secretKey`; default key: `NGC_API_KEY`.
Model cache / logs	`spec.parameters.nimModelCache`, `nimLogs`	Each has a `path` (default `/opt/nim/.cache` and `/workspace/nim-logs`) and a nested `pvc.{enabled,claimName,size,storageClassName}` block (default `pvc.enabled: false`). When `pvc.enabled: true`, the operator binds an existing claim with that name or creates one (annotated `helm.sh/resource-policy: keep`). Refer to Advanced Usage.
Security context	`spec.parameters.securityContext`	Example: `runAsUser: 1000`, capabilities for Rivermax and RTP; refer to Getting Started.
Pod security context	`spec.parameters.podSecurityContext`	`fsGroup`, `seccompProfileType`.
NMOS metadata	`spec.parameters.label`, `spec.parameters.description`	NMOS IS-04 registration strings.

Parameters: CR#

Configuration	CR Path (`spec.parameters.*`)	Comment
NMOS enabled	`nmosEnabled`	Default: `true`.
NIM enabled	`nimEnabled`	Default: `true`; `false` disables inference at runtime but does not relax the pod’s resource requests (GPU and SR-IOV VF are still reserved).
Log level	`loggingLevel`	`0` FATAL, `1` ERROR, `2` WARN, `3` INFO (default), `4` DEBUG, `5` VERBOSE.

Inputs and Outputs#

Area	CR Path	Comment
Audio in	`spec.inputs.audio_input`	`control`, `transport`, `format.audio`; single mono audio input. See subfields in the next table.
Audio out	`spec.outputs.audio_output`	Enhanced audio output; same format as input.

Subfields for format.audio#

These subfields apply to audio input and audio output.

Field	Example Value	Comment
`sample_rate`	`48000`	Audio sample rate in Hz. Fixed at 48000; the CRD rejects other values (`enum: [48000]`).
`channel_count`	`1`	Mono per stream. (Studio Voice expects a single mono speech stream.)
`sample_depth`	`24`	Bits; corresponds to PCM L24.
`media_type`	`audio/L24`	Fixed for ST 2110-30 mono L24.