Dhvanee DocsDashboard
Build

Voice agents

Create, configure, test and publish the agents that answer your calls.

A voice agent is what talks to your callers. You describe its job, choose its voice and language, test it, and publish it. Only workspace owners and admins can open the Agents area.

Create an agent

  1. 1

    Open Agents

    Go to Agents in the sidebar. The All Agents list shows each agent's name, type, engine, voice, phone number and when it was last edited. The default agent has a Default badge.

  2. 2

    Choose Create an Agent

    Give the agent a Name and pick its type (see below). Start from Build from scratch or choose a template, then choose Create agent.

  3. 3

    Or import one

    Import accepts an agent file exported earlier. To export, open the row menu and choose Export.

Single prompt or conversational flow

Single prompt

Describe the whole task in one prompt and let the model run the conversation. The simplest way to start.

Conversational flow

Build the call as connected steps on a canvas, for calls that must follow a fixed order.

Start with a single prompt and test it. Move to a conversational flow only when the call must follow fixed steps.

Set up a single-prompt agent

  • Pick the Model, Voice and Language. A model without an API key shows (needs API key).
  • Write the prompt. Type a backtick to insert a function and {{ to insert a dynamic variable.
  • Choose the Welcome Message: AI speaks first or User speaks first.
  • Use Global Settings on the right for everything else.

Build a conversational flow

The canvas starts at a Begin node. Connect nodes with transitions, each with its own condition. Auto layout tidies the canvas. The node types are:

NodeWhat it is for
ConversationA step where the agent talks with the caller
SubagentHands a part of the call to a smaller agent
FunctionRuns a function you have set up
Call TransferTransfers the call to a person or number
Press DigitWaits for the caller to press a key
Logic SplitChooses a path from a condition
Agent TransferMoves the call to another agent
In-Call SMSSends a text message during the call
Extract VariablePulls a value out of the conversation
CodeRuns a small piece of code
MCPCalls a connected MCP tool
EndingEnds the call
NoteA comment for your team; it does nothing in the call

Global settings

Open Global Settings in the studio to configure how the agent behaves on every call. Its sections are:

  • Agent Settings and Functions
  • Knowledge Base & Memory: attach documents from your knowledge base
  • Speech settings and Realtime transcription settings
  • Call settings, Post call extraction and Post call memory settings
  • Security & fallback settings, Webhook settings and MCPs

Call settings

SettingAllowed range
User Keypad Input Detection: Timeout0.5 to 15
User Keypad Input Detection: Digit Limit1 to 50
End Call on Silence10 to 1800
Max Call Duration60 to 7200
Ring Duration5 to 300

The same panel has switches for DNC Detection, Voicemail Detection, IOS/Android Call Screen Handling and IVR Hangup.

Call lifecycle

The Workflow tab on the left shows the steps around a call: dial in or out, pre-call functions, call started, call ended, post-call functions and post-call data extraction. Post-call extraction has a model picker that defaults to Workspace default.

Test your agent

  1. 1

    Test in the studio

    Choose Test to open the test panel. Use Test Audio to talk to the agent, or Test LLM to chat by typing. Fill in your dynamic variables first if the prompt uses any.

  2. 2

    Test with a real phone call

    Choose Phone Call, enter the number in Call to, and the agent calls that phone. Test calls are rate limited per hour.

Save versions and publish

  • Your edits stay a Draft until you choose Publish. Once live, the button reads Update.
  • Save draft keeps your work without changing live calls.
  • The Versions panel lets you Save version, make a version live (new calls use it straight away), Restore to draft, or Delete version (not available for the live one).
  • Configure Tags labels versions. The tag prod marks the live version, and you can add your own such as staging or qa.
Deleting an agent moves its phone numbers to the default agent. The default agent cannot be deleted.

Frequently asked questions

Who can create and publish agents?
Workspace owners and admins. Other members are taken back to the dashboard if they open Agents.
Can I move an agent to another workspace?
Yes. Use Export on the agent, then Import in the other workspace.
How big can a cloned voice upload be?
Up to 10 MB.
Where do I connect Cal.com or other tools my agent uses?
In Integrations. Functions that need a connection link you there.
Was this page helpful?