> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tavus.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Medical Intake

> Pre-visit intake flow with structured data capture.

## Medical Intake configuration (`pa5ad6596ef5`)

```json [expandable] theme={null}
{
  "pal_name": "Healthcare Intake Assistant",
  "pipeline_mode": "full",
  "default_face_id": "rf4e9d9790f0",
  "layers": {
    "perception": {
      "perception_model": "raven-1",
      "visual_awareness_queries": [
        "Are there any other people visible in the frame besides the primary speaker?",
        "Is the user in a private setting, or does the environment suggest a shared or public space such as a car, open office, waiting room, or shared room?",
        "Does the user appear to be in distress, under duress, or in an unsafe situation to share personal health information?"
      ]
    },
    "tts": {
      "tts_engine": "cartesia",
      "tts_emotion_control": true,
      "tts_model_name": "sonic-3"
    },
    "llm": {
      "model": "tavus-glm-4.7",
      "speculative_inference": true
    },
    "conversational_flow": {
      "turn_detection_model": "sparrow-1",
      "turn_taking_patience": "medium",
      "voice_isolation": "off",
      "idle_engagement": "off",
      "pal_interruptibility": "medium"
    }
  }
}
```

This template PAL (`Healthcare Intake Assistant`) includes:

* **PAL identity**: A healthcare intake assistant that gathers structured pre-visit context in a patient-friendly tone.
* **Full pipeline mode**: Enables the full Tavus conversational pipeline, including perception, STT, LLM, and TTS.
* **System prompt**: Omitted here for length. Retrieve the live template with [Get PAL](/api-reference/pals/get-pal) or clone it from [PAL Maker](https://maker.tavus.io/dev/pals/create).
* **Model layers**:
  * **Perception**: Uses the `raven-1` perception model.
  * **TTS**: cartesia (`sonic-3`, emotion control enabled).
  * **LLM**: `tavus-glm-4.7` with speculative inference.
  * **Conversational flow**: `sparrow-1` with `medium` turn-taking patience and `medium` interruptibility.

## Create a conversation with this template PAL

<Steps>
  <Step title="Step 1: Create your conversation">
    Create a conversation using the template `pal_id`. When the PAL has a `default_face_id`, you can omit `face_id`:

    ```shell cURL theme={null}
    curl --request POST \
      --url https://tavusapi.com/v2/conversations \
      --header 'Content-Type: application/json' \
      --header 'x-api-key: <api_key>' \
      --data '{
      "pal_id": "pa5ad6596ef5"
    }'
    ```

    <Note>
      Replace `<api_key>` with your actual API key. You can generate one in the <a href="https://maker.tavus.io/dev/api-keys" target="_blank">PAL Maker</a>.
    </Note>
  </Step>

  <Step title="Step 2: Join the conversation">
    Click the link in the ***`conversation_url`*** field to join the conversation:

    ```json theme={null}
    {
      "conversation_id": "c7f3fc6d788f",
      "conversation_name": "New Conversation",
      "conversation_url": "<conversation_link>",
      "status": "active",
      "callback_url": "",
      "created_at": "2025-05-20T05:38:51.501467Z"
    }
    ```
  </Step>
</Steps>