Personas

Overview

A persona is a simulated customer character used to test your voice AI agents. Each persona represents a different type of caller with specific characteristics - from their language and accent to their emotional state and communication style.

Navigate to Simulations → Personas in your Roark dashboard to view and manage your personas.

Creating a Persona

To create a new persona, navigate to Simulations → Personas in your dashboard and click the “Create New Persona” button. The creation modal is organized into collapsible sections where you’ll define who your simulated customer is and how they behave during calls.

Basic Information

Define the fundamental characteristics of your persona - who they are and their calling environment.

Setting	Options	Default
Name	Any descriptive text	Required
Language	English, Spanish, German, Hindi, French, Dutch, Arabic, Greek	English
Accent	US, US Southern, British, Australian, Spanish, German, Indian, French, Dutch, Saudi Arabian, Greek	US
Gender	Male, Female, Neutral	Female
Background Noise	None, Office	None

Speech Settings

Control how your persona speaks - their pace, clarity, and natural speech patterns.

Setting	Options	Default	Impact
Speech Pace	Slow, Normal, Fast	Normal	How quickly the persona speaks
Speech Clarity	Clear, Vague, Rambling	Clear	How directly they express themselves
Disfluencies	Enabled, Disabled	Disabled	Adds “um”, “uh” and natural hesitations

Behavior Settings

Define the persona’s emotional state and communication style during the conversation.

Setting	Options	Default	Impact
Base Emotion	Neutral, Cheerful, Confused, Frustrated, Skeptical, Rushed	Neutral	Underlying emotional tone
Intent Clarity	Clear, Indirect, Vague	Clear	How directly they state their goal
Confirmation Style	Explicit, Vague	Explicit	How clearly they confirm things
Memory Reliability	High, Low	High	Consistency of information provided

Backstory

Optional text field for additional context about the persona’s background and situation. Helps create more nuanced interactions.

Custom Properties

Define specific attributes that make your personas more realistic and contextually relevant to your simulations. These properties are automatically used by the simulation when appropriate, allowing for dynamic, context-aware conversations. How Properties Work:

Properties are key-value pairs specific to each persona
During simulations, these values are automatically referenced when relevant
The persona will naturally incorporate these details into conversations

Common Property Examples:

Property Type	Example Key	Example Value	Usage in Simulation
Location	`zipCode`	`"10001"`	Provides when asked for location/delivery
Account	`accountNumber`	`"ACC-789456"`	References when discussing account details
Status	`membershipLevel`	`"Gold"`	Mentions when relevant to service tier
History	`lastOrderDate`	`"2024-01-15"`	Recalls when discussing recent interactions
Preference	`preferredContact`	`"email"`	States when asked about contact preferences

Properties make your simulations more realistic by ensuring personas provide consistent, relevant information throughout the conversation. This is especially useful for testing data validation, personalization features, and context-aware responses.

Example Personas

Below are sample personas that demonstrate common customer types you might encounter. Each example shows the configuration settings and explains when to use that persona type for testing.

The Frustrated Regular

Name: "Sarah - Billing Issue"
Language: English
Accent: US
Gender: Female
Background: Office
Speech Pace: Fast
Speech Clarity: Clear
Base Emotion: Frustrated
Intent Clarity: Clear
Backstory: "Long-time customer calling about third billing error this year.
  Usually patient but reaching limit."

Use for: Testing de-escalation, problem resolution, empathy responses

The Confused Elder

Name: "Robert - Tech Support"
Language: English
Accent: US
Gender: Male
Background: None
Speech Pace: Slow
Speech Clarity: Vague
Disfluencies: Enabled
Base Emotion: Confused
Intent Clarity: Vague
Memory Reliability: Low
Backstory: "Retired, not tech-savvy, calling about password reset.
  May repeat questions or forget earlier answers."

Use for: Testing patience, clear explanations, handling repetition

The Happy Path Customer

Name: "Alex - Quick Inquiry"
Language: English
Accent: British
Gender: Neutral
Speech Pace: Normal
Speech Clarity: Clear
Base Emotion: Cheerful
Intent Clarity: Clear
Backstory: "Calling to check order status. Has order number ready."

Use for: Baseline testing, happy path scenarios, quick resolutions

The Busy Professional

Name: "Maria - Appointment Change"
Language: Spanish
Accent: Spanish
Gender: Female
Background: Office
Speech Pace: Fast
Speech Clarity: Clear
Base Emotion: Rushed
Confirmation Style: Vague
Backstory: "Calling during work break, needs to reschedule quickly.
  May not fully listen to options."

Use for: Testing efficiency, handling rushed callers, clear communication

Using Personas

Once created, personas can be:

Selected when creating new simulations
Reused across multiple test scenarios
Modified to create variations for different tests
Shared with your team for consistent testing

Start with 3-5 core personas representing your most common customer types, then expand based on edge cases you discover.

API Integration

Create personas dynamically from customer data or integrate persona management into your CI/CD pipeline for automated testing. Combine with custom properties to build realistic personas that test business-specific flows.

Available Endpoints

Create Persona - POST /v1/persona
Update Persona - PUT /v1/persona/{id}
Get Persona - GET /v1/persona/{id}
List Personas - GET /v1/persona

Example: Creating a Persona via API

curl -X POST https://api.roark.ai/v1/persona \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Emma Johnson",
    "language": "EN",
    "accent": "US",
    "gender": "FEMALE",
    "properties": {
      "accountNumber": "ACC-123456",
      "zipCode": "90210",
      "membershipLevel": "Premium"
    }
  }'

For complete API documentation including all available parameters and response formats, see the Persona API Reference.

Reference

Complete Language Options

English (EN) 🇺🇸 - Spanish (ES) 🇪🇸 - German (DE) 🇩🇪 - Hindi (HI) 🇮🇳 - French (FR) 🇫🇷 - Dutch (NL) 🇳🇱 - Arabic (AR) 🇸🇦 - Greek (EL) 🇬🇷

Complete Accent Options

United States (US) 🇺🇸 - United States - Southern (US_X_SOUTH) 🇺🇸 - British English (GB) 🇬🇧 - Australian (AU) 🇦🇺 - Spanish (ES) 🇪🇸 - German (DE) 🇩🇪 - Indian (IN) 🇮🇳 - French (FR) 🇫🇷 - Dutch (NL) 🇳🇱 - Saudi Arabian (SA) 🇸🇦 - Greek (GR) 🇬🇷

Speech Profile Details

Speech Pace: - Slow: “Okay… let me… think about that…” - Normal: “Sure, I’d like to book a time.” - Fast: “Yeahsowhattimecanyoudotoday?” Speech Clarity: - Clear: “I’d like a refund for my last order.” - Vague: “I’m not really sure what happened, but it was… weird.” - Rambling: “So, basically… okay, let me start from the beginning, right…” Disfluencies: - Enabled: “Um, yeah, I think… I think I called earlier.” - Disabled: Clean, scripted-sounding speech

Behavioral Profile Details

Base Emotion: - Neutral: “I just wanted to ask a quick question.” - Cheerful: “Hey! I hope you’re having a great day!” - Confused: “Wait, so… how does this work again?” - Frustrated: “I’ve already explained this twice.” - Skeptical: “Are you sure this is the right number?” - Rushed: “I really don’t have time, can we do this quickly?” Intent Clarity: - Clear: “I need to cancel my appointment.” - Indirect: “So… I was wondering if it’s possible to, like, change something?” - Vague: “I guess I’m calling about… something with my booking?” Confirmation Style: - Explicit: “Yes, that’s exactly right.” - Vague: “Uh, I think so… yeah, maybe?” Memory Reliability: - High: Consistent information throughout call - Low: “Did I say 3pm? I meant 2pm.”

Default Values

When creating a new persona without specifying all options: - Language: English (EN) - Accent: United States (US) - Gender: Female - Background Noise: None - Speech Pace: Normal - Speech Clarity: Clear - Disfluencies: Disabled - Base Emotion: Neutral - Intent Clarity: Clear - Confirmation Style: Explicit - Memory Reliability: High

Best Practices

Start Simple: Begin with basic personas before adding complexity - Mirror Reality: Base personas on actual customer data - Test Extremes: Include edge cases (very angry, very confused) - Document Purpose: Use clear names that indicate the test scenario - Iterate: Refine based on simulation results - Share Knowledge: Document lessons learned with each persona

Getting Started

Observability

Simulations & Testing

Integrations

SDKs & Libraries

Resources

Overview

Creating a Persona

Basic Information

Speech Settings

Behavior Settings

Backstory

Custom Properties

Example Personas

The Frustrated Regular

The Confused Elder

The Happy Path Customer

The Busy Professional

Using Personas

API Integration

Available Endpoints

Example: Creating a Persona via API

Reference

Next Steps

Create Scenarios

Run Simulations

Getting Started

Observability

Simulations & Testing

Integrations

SDKs & Libraries

Resources

​Overview

​Creating a Persona

​Basic Information

​Speech Settings

​Behavior Settings

​Backstory

​Custom Properties

​Example Personas

​The Frustrated Regular

​The Confused Elder

​The Happy Path Customer

​The Busy Professional

​Using Personas

​API Integration

​Available Endpoints

​Example: Creating a Persona via API

​Reference

​Next Steps

Create Scenarios

Run Simulations

Overview

Creating a Persona

Basic Information

Speech Settings

Behavior Settings

Backstory

Custom Properties

Example Personas

The Frustrated Regular

The Confused Elder

The Happy Path Customer

The Busy Professional

Using Personas

API Integration

Available Endpoints

Example: Creating a Persona via API

Reference

Next Steps