> This page is for NVIDIA LipSync on Holoscan for Media, version 1.0.0 (Latest) (default).
> For other versions, use one of these documentation indexes:
> - 1.0.0 (Latest) (default): https://docs.nvidia.com/nim/maxine/lipsync-h4m/1.0.0/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nim/maxine/llms.txt.

# Pipeline Configuration

This page covers NIM service chart Helm values and environment variables specific to the LipSync pipeline, including model options, media format, and SMPTE ST 2110 session wiring.

---

## LipSync Model and Ancillary Options

| Configuration | Helm Key | Comment |
|---------------|----------|---------|
| Head movement speed | `model.headMovementSpeed` | Model tuning; default (chart): `0`. |
| Ancillary data input | `input.ancillaryData.enabled`, `input.ancillaryData.sessionName` | Optional ST 2110-40 / SMPTE 291–style metadata input for multi-subject targeting. |
| Bounding box on output video | `output.boundingBoxEnabled` | When ancillary data input is enabled, draws a bounding box on the active speaker in the output program video. |

---

## Video Raster

The video raster defines the fixed picture format of the incoming SMPTE ST 2110-20 stream. These Helm keys specify the raster of the incoming video so that decoding, audio sync, and inference stay consistent.

| Configuration | Helm Key | Comment |
|---------------|----------|---------|
| Width and height | `video.width`, `video.height` | Resolutions: 720p, 1080p, 4K UHD; refer to [Support Matrix](/nim/maxine/lipsync-h4m/support-matrix) and [Helm Configuration Parameters](/nim/maxine/lipsync-h4m/installation/lipsync-h4m-sample#helm-configuration-parameters). |
| Frame rate | `video.framerateNum`, `video.framerateDen` | Must match the upstream sender and downstream receiver. |

---

## Audio Format

| Configuration | Helm Key | Comment |
|---------------|----------|---------|
| PCM format | `audio.pcmFormat` | Example: `S24BE`. |
| Sample rate | `audio.samplingRate` | Example: `48000` Hz. |
| Channels | `audio.numChannels` | Example: `1`; supports a single stream. |

---

## SMPTE ST 2110 (Static Mode) Input Sessions

| Configuration | Helm Key | Comment |
|---------------|----------|---------|
| Video session | `input.video.sessionName`, `input.video.localInterfaceName`, `input.video.hostIp`, `input.video.hostPort` | Site-specific multicast IP address and port. |
| Audio session | `input.audio.sessionName`, `input.audio.localInterfaceName`, `input.audio.hostIp`, `input.audio.hostPort` | Multicast interface wiring for the incoming audio ST 2110 session. |
| Ancillary session | `input.ancillaryData.enabled`, `input.ancillaryData.sessionName`, `input.ancillaryData.localInterfaceName`, `input.ancillaryData.hostIp`, `input.ancillaryData.hostPort` | Optional; default (chart): `enabled: false`: multicast interface wiring for ancillary ST 2110 when enabled. |

---

## SMPTE ST 2110 (Static Mode) Output Sessions

| Configuration | Helm Key | Comment |
|---------------|----------|---------|
| Video out | `output.video.sessionName`, `output.video.localInterfaceName`, `output.video.hostIp`, `output.video.hostPort` | LipSync output video: site-specific multicast session, interface, IP address, and port. |
| Bounding box overlay | `output.boundingBoxEnabled` | With ancillary data input enabled, draws the active speaker bounding box on program video; refer to [LipSync Model and Ancillary Options](#lipsync-model-and-ancillary-options). |

---

## NIM Pod Resources

| Resource | Requests | Limits |
|----------|----------|--------|
| `cpu` | `8` | `8` |
| `hugepages-2Mi` | `4Gi` | `4Gi` |
| `memory` | `8Gi` | `8Gi` |
| `nvidia.com/gpu` | `1` | `1` |

The `cpu` value is set to `8` cores by default, tuned for real-time ST 2110 performance. You can reduce it, but the value must be consistent with `env.CPU_AFFINITY`.

`env.CPU_AFFINITY` (default `"2-7"`) pins the NIM process to a contiguous range of CPU cores. The chart validates at deploy time that the values of `resources.requests.cpu` and `resources.limits.cpu` are each equal to or greater than the number of cores in the affinity range.

| Setting | Helm Key | Default |
|---------|----------|---------|
| CPU affinity range | `env.CPU_AFFINITY` | `"2-7"` (6 cores) |

The default value of `cpu` (`8`) is intentionally greater than `CPU_AFFINITY` (`"2-7"`, 6 cores): The pinned range covers the NIM workload minimum, and the remaining cores are available to Kubernetes. To configure cores, keep `resources.requests.cpu`, `resources.limits.cpu`, and `env.CPU_AFFINITY` aligned. If `cpu` falls below the affinity range, the chart fails during installation with a descriptive error.

---

## Logging

| Configuration | Helm Key | Comment |
|---------------|----------|---------|
| Log level | `logging.level` | Range: `0`–`4`. `0` FATAL, `1` ERROR, `2` WARNING, `3` INFO (default), `4` DEBUG. |

---

## See Also

- [Configuration Reference](/nim/maxine/lipsync-h4m/configuration)
- [Common Helm Configuration](/nim/maxine/lipsync-h4m/configuration/common): Cluster, NGC secret, PVCs, NMOS.
- [Operator Configuration](/nim/maxine/lipsync-h4m/configuration/operator): Operator CR pipeline tuning equivalent.
- [Limitations and Known Behaviors](/nim/maxine/lipsync-h4m/limitations-and-known-behaviors): NMOS ordering and known issues.