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

# Personas

> Create reusable caller personas for voice simulations in Netra. Define voice, speech traits, accent, and knowledge so every simulated call is realistic.

Personas define who calls your agent during a [voice simulation](/Simulations/voice-simulations/Simulations). A persona bundles a synthetic voice with speech behavior—pace, clarity, timing, disfluencies—and the knowledge the caller can reference. Build your persona library once, then reuse personas across scenarios and evaluations.

## Why Personas Matter

Real callers vary. Personas let you test against that variation systematically:

| Capability             | Benefit                                                                       |
| ---------------------- | ----------------------------------------------------------------------------- |
| **Consistent Callers** | Reuse the exact same caller across runs to isolate what changed in your agent |
| **Speech Variation**   | Test fast, vague, rambly, or rapid-fire callers without re-recording anything |
| **Voice Control**      | Assign specific TTS voices, accents, and languages per persona                |
| **Grounded Knowledge** | Give each persona only the facts that persona would realistically know        |

## Personas Dashboard

Navigate to **Library → Personas** from the left navigation panel.

The dashboard shows your personas as cards in a searchable grid:

<img src="https://mintcdn.com/netra/I4AMRwYHDuF5FbHN/images/personas-dashboard.png?fit=max&auto=format&n=I4AMRwYHDuF5FbHN&q=85&s=0299186294e6bcb34652c1605466a70f" alt="Personas dashboard grid" width="1854" height="919" data-path="images/personas-dashboard.png" />

* **Search**: Find personas by name, description, or tag
* **Create**: Open the persona builder
* **Edit / Delete**: Manage existing personas from each card

## Creating a Persona

<Steps>
  <Step title="Pick an Avatar">
    <img src="https://mintcdn.com/netra/I4AMRwYHDuF5FbHN/images/voice-simulation/persona_creation.png?fit=max&auto=format&n=I4AMRwYHDuF5FbHN&q=85&s=1d2453c7172ea204931b56460c633eee" alt="Persona Avatar Picker" width="634" height="738" data-path="images/voice-simulation/persona_creation.png" />

    Choose an avatar to make the persona easy to recognize across the dashboard.
  </Step>

  <Step title="Set Identity">
    | Field           | Description                                            |
    | --------------- | ------------------------------------------------------ |
    | **Name**        | A descriptive label (e.g., "Frustrated Refund Caller") |
    | **Gender**      | Female, male, or neutral—influences available voices   |
    | **Description** | Who this person is and why they might call             |

    Choose a behaviour preset—neutral, friendly, frustrated, confused, or custom—to shape how the persona reacts when the conversation gets difficult.
  </Step>

  <Step title="Configure Speech Traits">
    Tune how the persona actually talks:

    | Trait                 | Options                                        |
    | --------------------- | ---------------------------------------------- |
    | **Pace**              | From very slow to very fast                    |
    | **Clarity**           | Clear, vague, or rambling                      |
    | **Response Timing**   | Quick, normal, or relaxed                      |
    | **Disfluencies**      | Add natural "um"s, "uh"s, and self-corrections |
    | **Language & Accent** | The language spoken and its accent             |

    <Tip>
      Vague, rambling callers with disfluencies are the best stress test for STT accuracy. Save them for later-stage testing once basic flows pass.
    </Tip>
  </Step>

  <Step title="Assign a Voice">
    <img src="https://mintcdn.com/netra/I4AMRwYHDuF5FbHN/images/voice-simulation/persona_tts_updation.png?fit=max&auto=format&n=I4AMRwYHDuF5FbHN&q=85&s=ca401fd50ea1c73eaf7e16dd04e6fa5e" alt="Persona TTS Selector" width="633" height="786" data-path="images/voice-simulation/persona_tts_updation.png" />

    Choose the TTS provider, model, and voice that will speak this persona's lines. Available options depend on the provider you select—some models support accents and personality settings, others do not.
  </Step>

  <Step title="Add Knowledge">
    Provide the facts this persona knows (such as order numbers, dates, or account details) as key-value pairs. During a simulation, the persona can only reference this information—if your agent asks about something the persona does not know, it will say so.
  </Step>

  <Step title="Save">
    Click **Create**. The persona becomes selectable in the [voice evaluation](/Simulations/voice-simulations/Simulations) creation flow.
  </Step>
</Steps>

## Using Personas

* **In evaluations**: Each voice scenario requires exactly one persona; mix personas across scenarios in the same evaluation to cover different caller types
* **Across runs**: Because a persona is fixed, changes in results between runs reflect your agent—not the caller

## Best Practices

### Building a Balanced Library

Cover the caller types your product actually serves:

| Persona Type           | Tests                                     |
| ---------------------- | ----------------------------------------- |
| Clear, neutral speaker | Baseline conversation quality             |
| Fast talker            | STT accuracy under pressure               |
| Rambling, vague caller | Your agent's ability to guide and clarify |
| Frustrated caller      | De-escalation and empathy                 |
| Non-native accent      | Transcription robustness across accents   |

### Managing Personas

* **Name by behavior**: "Fast rambling complainer" is more useful than "Test persona 3"
* **Keep knowledge minimal**: Only give personas the facts the scenario needs
* **Reuse before you create**: Check the library before adding a near-duplicate persona

## Related

* [Simulation Overview](/Simulations/Simulation-overview) - Understand the full simulation framework
* [Evaluations](/Simulations/voice-simulations/Simulations) - Create voice simulation scenarios
* [Evaluators](/Evaluators/voice-evaluators) - Score audio quality, transcription, and delivery
* [Test Runs](/Simulations/TestRuns) - Review transcripts with synced audio