Types Of DialNexa Agents - DialNexa Documentation

The types of DialNexa agents are Single Prompt Agents, Conversational Flow Agents, Speech to Speech Agents, and IVR Agents. Choose Manual Build to compare the agent cards, or use Agent Builder to get a recommendation from your brief.

Who This Is For

Use this page before you create or rebuild an agent. It helps product owners, operations teams, and developers decide which agent structure fits the call goal, compliance requirements, latency target, and debugging workflow.

Types Of DialNexa Agents At A Glance

Agent type	Best for	How it works	Main tradeoff
Single Prompt Agent	Focused calls with one primary goal.	One instruction set guides the whole call. The agent uses the prompt, model, tools, variables, and post-call fields to complete the objective.	Complex branching can become hard to maintain inside one prompt.
Conversational Flow Agent	Calls with defined stages, compliance steps, or audited paths.	A visual node canvas controls each state, branch, function, transfer, and ending.	More setup work, and every important path must be designed.
Speech to Speech Agent	Latency-sensitive voice calls and web calls.	A realtime speech model listens and speaks directly. DialNexa hides separate transcriber, voice model, and Audio Cache controls.	Less separate control over STT and TTS layers than a cascaded stack.
IVR Agent	Keypad menus, digit collection, and routing to another published agent.	Static prompt audio and DTMF input move the caller through a visual menu.	Beta feature, no open-ended conversation inside the IVR, and phone-call testing only.

Choose An Agent Type In The Dashboard

Open Agents and select Create agent. The guided Agent Builder appears first. Choose it when you want DialNexa to build a structured draft from your answers, or select Manual Build to choose a type manually. In manual creation:

The type screen shows Single Prompt, Conversational Flow, and Speech to Speech cards.
Select Show the IVR agent under Need a classic keypad menu? to reveal the IVR Agent card, marked Beta.

DialNexa Manual Build agent type screen with the Single Prompt, Conversational Flow, and Speech to Speech cards.

DialNexa Manual Build agent type screen after revealing the IVR Agent card, marked Beta.

Selecting IVR creates a blank IVR draft directly because IVR does not use conversational templates.

Choose IVR Agents For Keypad Routing

An IVR Agent gives callers a predictable keypad menu before a conversational agent takes over. It can speak static prompts, route 0 to 9, *, and #, collect a digit sequence, connect the current call to another published agent, or hang up. IVR Agents are available through Manual Build > Show the IVR agent in every workspace and are currently marked Beta. They do not use an LLM, transcriber, tools, or knowledge base while the caller is in the menu. See Build IVR Agents for graph rules, publishing, testing, and billing behavior.

Choose Single Prompt Agents For Focused Calls

A Single Prompt Agent is the fastest way to build a production voice agent when the call has one main outcome. The prompt explains the role, goal, boundaries, call flow, tool usage, and closing behavior. Good use cases include:

Appointment reminders
Payment nudges
Lead qualification with one simple script
Feedback collection
Support intake where the agent collects details and creates a follow-up

Use this type when the call can be tested from one prompt and the expected result can be captured in post-call fields. If the prompt keeps growing into separate stages, move the logic into a Conversational Flow Agent.

Choose Conversational Flow Agents For Explicit Paths

A Conversational Flow Agent is the right structure when the conversation needs a visual map. Each node can have its own prompt, branch rules, function calls, transfer behavior, and ending. Use a flow when:

Compliance requires a specific disclosure at a specific point
The caller’s answer must move to a defined next step
Different paths need different transfer destinations or handoff context
Your team needs to review the call path visually
Debugging requires node-level history instead of prompt-level reasoning

Flow agents are easier to audit than a long prompt, but they require careful path design. Every branch should lead to a useful next node, transfer, or end state.

Choose Speech To Speech Agents For Realtime Voice

A Speech to Speech Agent uses a realtime speech model instead of a cascaded speech to text, text LLM, and text to speech pipeline. This can reduce turn latency because the model processes audio and returns audio directly. DialNexa supports Speech to Speech model paths such as OpenAI realtime models and Gemini models where they are enabled for your workspace. Use the dashboard model selector and pricing preview as the source of truth for the models available to your account. Speech to Speech is a good fit when:

Callers interrupt often and fast turn taking matters
You are testing web calls where first audio timing is very visible
You want to compare OpenAI realtime behavior against Gemini realtime behavior
The call can accept the realtime model’s voice and model constraints

Do not choose Speech to Speech only because it sounds newer. Choose it when the call outcome improves after real tests against the same prompt, route, and caller script.

How To Decide

Write the call outcome first

Define what the call should accomplish, what result should be stored, and what should happen next.

Estimate the branching complexity

If the path is mostly linear, start with Single Prompt. If the caller can move through many defined states, start with Conversational Flow.

Decide how much stack control you need

If you need separate transcriber, TTS, Audio Cache, and fallback STT controls, use a cascaded Single Prompt or Conversational Flow setup. If realtime turn taking is more important, test Speech to Speech.

Test the hardest caller behavior

Use interruptions, silence, wrong-person responses, objections, and missing variables before publishing.

Publish and route intentionally

A draft agent does not receive live traffic until you publish a version and assign it to a phone number, workflow, batch call, or web call.

Common Selection Mistakes

Using one huge prompt for a multi-stage script

If the prompt contains many numbered branches, transfer paths, and exception rules, the user experience will usually be easier to control in a Conversational Flow Agent.

Choosing a flow for a simple reminder

A simple reminder or survey often works better as a Single Prompt Agent. Avoid node complexity when one clear prompt and post-call fields can do the job.

Comparing Speech to Speech against a cascaded stack unfairly

Keep the prompt, route, caller script, and test conditions the same. Otherwise you are comparing the setup, not the model path.

Publishing before assigning the route

Publishing creates a version. It does not automatically move every phone number, batch, workflow, or web call to that version.

Recap

Choose Single Prompt when one instruction set can complete the call. Choose Conversational Flow when the path must be explicit and reviewable. Choose Speech to Speech when realtime turn taking is the main reason to change the stack. Choose IVR Agent when the caller should use a keypad menu before any conversational handoff.

Single Prompt Agents

Build one prompt around one clear call objective.

Conversational Flow Agents

Build explicit call paths with nodes and branches.

Speech To Speech Agents

Configure OpenAI realtime and Gemini Speech to Speech model paths.

IVR Agents

Build keypad menus and hand callers to a published agent.

Languages Voices Models And Transcribers

Choose the conversation stack for the selected agent type.

​Who This Is For

​Types Of DialNexa Agents At A Glance

​Choose An Agent Type In The Dashboard

​Choose IVR Agents For Keypad Routing

​Choose Single Prompt Agents For Focused Calls

​Choose Conversational Flow Agents For Explicit Paths

​Choose Speech To Speech Agents For Realtime Voice

​How To Decide

​Common Selection Mistakes

​Recap

​Related Pages