LiveKit docs › Models › Realtime › NVIDIA PersonaPlex

---

# NVIDIA PersonaPlex plugin guide

> How to use the NVIDIA PersonaPlex realtime model with LiveKit Agents.

Available in:
- [ ] Node.js
- [x] Python

> 🔥 **Experimental feature**
> 
> The PersonaPlex realtime model integration is experimental and the API might change in a future release.

## Overview

[PersonaPlex](https://research.nvidia.com/labs/adlr/personaplex/) is a full-duplex speech-to-speech model from NVIDIA. It listens and speaks simultaneously, enabling natural conversational flow with interruptions and backchannels.

### Installation

Install the NVIDIA plugin:

```shell
uv add "livekit-plugins-nvidia[personaplex]"

```

### Authentication

PersonaPlex connects to a self-hosted server. Set the server URL as an environment variable in your `.env` file:

```shell
PERSONAPLEX_URL=ws://localhost:8998

```

If `PERSONAPLEX_URL` isn't set, the plugin defaults to `localhost:8998`.

### Usage

Use PersonaPlex in an `AgentSession`. For example, you can use it in the [Voice AI quickstart](https://docs.livekit.io/agents/start/voice-ai.md).

```python
from livekit.plugins import nvidia

session = AgentSession(
    llm=nvidia.realtime.RealtimeModel(
        text_prompt="You are a helpful voice AI assistant.",
    ),
)

```

PersonaPlex uses `text_prompt` on the model for system instructions. Agent-level `instructions` aren't forwarded to PersonaPlex, so set your instructions here instead.

### Parameters

This section describes some of the available parameters. For a complete reference of all available parameters, see the [plugin reference](https://docs.livekit.io/reference/python/livekit/plugins/nvidia/experimental/realtime/realtime_model.html.md#livekit.plugins.nvidia.experimental.realtime.realtime_model.RealtimeModel).

- **`base_url`** _(str)_ (optional) - Default: `"localhost:8998"`: WebSocket URL of the PersonaPlex server. If not set, reads from the `PERSONAPLEX_URL` environment variable.

- **`voice`** _(str)_ (optional) - Default: `"NATF2"`: Voice to use for speech output. For a full list, see [Voices](https://github.com/NVIDIA/personaplex?tab=readme-ov-file#voices).

- **`text_prompt`** _(str)_ (optional) - Default: `"You are a helpful assistant."`: System instruction for the model.

- **`seed`** _(int)_ (optional): Seed for reproducible generation. See NVIDIA's [prompting guide](https://github.com/NVIDIA/personaplex?tab=readme-ov-file#prompting-guide).

- **`silence_threshold_ms`** _(int)_ (optional) - Default: `500`: Duration of silence in milliseconds before the model finalizes a generation.

## Considerations

PersonaPlex has some differences from other realtime model plugins:

- **Self-hosted only.** Deploy a PersonaPlex server separately. See the [NVIDIA PersonaPlex GitHub repo](https://github.com/NVIDIA/personaplex) for setup instructions.
- **No tool calling.** PersonaPlex doesn't support function calling or tools.
- **No user transcription.** PersonaPlex doesn't provide transcriptions of user speech. If you need to log or display what the user said, add a separate [STT plugin](https://docs.livekit.io/agents/models/stt.md).
- **No conversation history.** Loading prior conversation context isn't supported. Each session starts fresh.
- **Client-side silence detection only.** Turn detection relies on the `silence_threshold_ms` parameter (default 500ms). There's no server-side turn detection or VAD integration.
- **Audio only.** Video input isn't supported.

## Additional resources

The following resources provide more information about using PersonaPlex with LiveKit Agents.

- **[Python package](https://pypi.org/project/livekit-plugins-nvidia/)**: The `livekit-plugins-nvidia` package on PyPI.

- **[Plugin reference](https://docs.livekit.io/reference/python/livekit/plugins/nvidia/experimental/realtime/realtime_model.html.md#livekit.plugins.nvidia.experimental.realtime.realtime_model.RealtimeModel)**: Reference for the PersonaPlex integration.

- **[GitHub repo](https://github.com/livekit/agents/tree/main/livekit-plugins/livekit-plugins-nvidia)**: View the source or contribute to the LiveKit NVIDIA plugin.

- **[PersonaPlex research](https://research.nvidia.com/labs/adlr/personaplex/)**: NVIDIA's PersonaPlex research page and paper.

- **[PersonaPlex model](https://github.com/NVIDIA/personaplex)**: PersonaPlex server source code and deployment instructions.

- **[Voice AI quickstart](https://docs.livekit.io/agents/start/voice-ai.md)**: Get started with LiveKit Agents and PersonaPlex.

---

This document was rendered at 2026-06-07T11:35:51.856Z.
For the latest version of this document, see [https://docs.livekit.io/agents/models/realtime/plugins/personaplex.md](https://docs.livekit.io/agents/models/realtime/plugins/personaplex.md).

To explore all LiveKit documentation, see [llms.txt](https://docs.livekit.io/llms.txt).