Skip to main content
Digital Humans are highly configurable. You can change their accents, languages, background noise, speaking speed, audio quality, and more. This page covers every configuration lever available to you.

​
Voice & Speech Settings

These settings control how the Digital Human sounds during a conversation with your agent. Click each setting to see example values.
The language the Digital Human speaks. Examples: English, Spanish, Mandarin, Hindi, French. Auto-detect is also available.
Regional accent applied to speech. Examples: American, Southern, British, Australian, Indian, Mexican.
How fast or slow the Digital Human talks: Slowest, Slow, Normal, Fast, Fastest.
How fluently the Digital Human speaks the language: Beginner, Intermediate, Native.
How much the Digital Human says per turn: Low, Medium, High.
Simulated line quality of the call: High, Medium, Low, Horrible. Use lower settings to test how your agent handles a bad connection.
Ambient sounds during the conversation: Office, Talking, Traffic, Cafe, Park, TV, Noisy Restaurant, Hospital, None, or a custom sound. A separate volume slider controls how loud the noise is.
To run every digital human under several of these settings at once — a quiet line and traffic noise, a normal pace and a fast talker — add personalities to the simulation run. A personality is a saved configuration of these settings. It overrides only the fields it sets; the rest stay the caller’s own.
There is no separate “emotion” setting: a Digital Human’s attitude comes from its persona and intent. Write it into the scenario, e.g. “You are a frustrated customer who has already called twice about this.” Combined with the voice settings above, this creates realistic personas: a frustrated beginner-fluency caller in a noisy restaurant behaves very differently from a calm native speaker in a quiet office.

​
Intent & Success Criteria

Every Digital Human needs a clear intent and success criteria to produce meaningful test results. Some generation paths (for example workflow-based scenarios) may store empty description or success criteria; see the Create Digital Human and Generate Digital Humans API references for how your payload is validated.

​
Defining Intent

The intent is what the Digital Human wants to accomplish in the conversation. Write it as a clear scenario description:

​
Defining Success Criteria

Success criteria are the conditions that determine whether the test passed. They should be specific and measurable:
The more specific your success criteria, the more actionable your simulation results will be. Avoid vague criteria like “the agent was helpful.” Define exactly what “helpful” means for that scenario.

​
Advanced Behaviors

Digital Humans can do far more than just talk. These advanced behaviors let you test scenarios that standard conversational testing can’t reach.

​
Scripted Responses

Configure a Digital Human to provide specific responses depending on what your agent says. This is useful when you need deterministic behavior for regression testing.
1

Define trigger phrases

Specify what the agent might say that should trigger a scripted response. For example, “Can I have your account number?”
2

Map scripted replies

Define the exact response the Digital Human should give when the trigger is matched. For example, “Sure, it’s 4829-3371.”
3

Set fallback behavior

Decide what happens when no trigger matches. The Digital Human can continue with natural conversation or stay on script.

​
DTMF Codes

Digital Humans can send DTMF (touch-tone) codes during a call. This is critical for testing agents that require keypad input, such as entering an account number, selecting a menu option, or confirming a PIN.

​
Phone Extension

Give a Digital Human an extension (the extension field) to reach a specific extension after the call connects, the same way you save one on a phone contact. This applies only when the Digital Human calls an inbound agent: it dials the agent’s number, then plays the extension as DTMF once connected, before the conversation starts. It is ignored for outbound agents, where the agent calls the Digital Human. Use digits 0-9, *, and #. A comma is a short pause, useful when a menu needs a beat before it accepts input.

​
Silence Simulation

Configure a Digital Human to stay silent for a specified duration. This tests how your agent handles dead air. Does it re-prompt the customer? Does it escalate? Does it hang up too early? Separately, the API stores allow_silence_tool (boolean) and silence_tool_instructions (string) on each Digital Human. When allow_silence_tool is true, the voice runtime may use a silence tool according to its own rules. Use the literal string "default" for instructions to mean “built-in product behavior”; any other non-empty string is custom guidance for that runtime. Ending a call is analogous but not identical: allow_end_call_tool plus optional hangup_instructions (often null when you do not want custom hangup copy). Whether the silence tool actually runs is enforced in the simulation execution layer, not in the API middleware alone.

​
IVR System Simulation

Digital Humans can simulate an IVR (Interactive Voice Response) system so your agent can navigate through it. This flips the typical setup: instead of a human calling your agent, your agent is calling into a phone tree, and the Digital Human plays the role of that phone tree.
1

Define the IVR menu tree

Map out the menu structure: “Press 1 for Sales, Press 2 for Support, Press 3 for Billing.”
2

Configure agent navigation

Set the expected path your agent should take through the IVR to reach the correct department.
3

Validate the outcome

Define success criteria for the agent successfully navigating the IVR and reaching the intended endpoint.

​
Configuration Combinations

The power of Digital Humans comes from combining these settings. Here are a few example configurations:

Frustrated bilingual caller

Language: Spanish → English mid-call
Persona: Frustrated, has called twice before
Speed: Fast
Intent: Billing dispute, wants to speak to a manager
Success: Agent de-escalates and resolves without transfer

Silent customer on hold

Silence: 15 seconds after greeting
Persona: Neutral, distracted
Intent: Waiting for agent to re-engage
Success: Agent re-prompts within 10 seconds, doesn’t disconnect

DTMF account verification

DTMF: Sends account number when prompted
Persona: Calm
Background: Office
Intent: Check account balance
Success: Agent correctly reads back the balance

IVR navigation test

Mode: IVR simulation
Menu: 3-level phone tree
Intent: Agent must reach “Billing → Refunds → Existing Case”
Success: Agent arrives at correct endpoint within 60 seconds

​
Resources

Best Practices

The three principles for Digital Humans that pair cleanly with these settings.

Use Cases

Real-world patterns for combining these configuration levers.

Bulk Upload via CSV

Set every field on this page per row and create a whole population from one CSV.

Generate via API

Create Digital Humans programmatically.