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

# Voice AI Overview For Real Customer Calls

> Understand Voice AI in DialNexa from the caller and operator point of view, including provider choices, call routing, integrations, transcripts, recordings, latency, and call evidence.

Voice AI in DialNexa is a live phone conversation where software listens, understands, decides, speaks, and records evidence. For an end user, the goal is not to admire the stack. The goal is to answer a customer, collect the right information, take the right action, and leave a call record that a teammate can trust later.

<Tip>
  A good voice agent should feel boring in the best way: the caller speaks, the agent understands, and the next step happens without drama.
</Tip>

## Voice AI For Real Customer Calls

Start with the kind of call you want to run. Provider settings make sense only after the user outcome is clear. For a product-path view of the same scenarios (which tabs and features to use, rather than which providers), see [Common Use Cases](/common-use-cases).

| If your user needs to       | The agent must be good at                                                                                  | Read next                                                                                                                                                                   |
| --------------------------- | ---------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Book appointments.          | Hearing dates and times, calling the calendar or booking API, confirming the slot, and ending politely.    | [Functions](/agent-settings/functions), [custom functions](/agent-settings/custom-functions), and [Google Calendar](/integrations/googlecalendar).                          |
| Qualify leads.              | Asking short questions, scoring answers, writing structured fields, and pushing context to the sales team. | [Post-call analysis](/agent-settings/post-call-analysis), [HubSpot](/integrations/hubspot), and [Salesforce](/integrations/salesforce).                                     |
| Send reminders.             | Reading a fixed script, handling objections, retrying later, and sending written follow-up.                | [Batch calls](/batch-calls/overview), [WhatsApp with Wati](/dashboard-integrations/whatsapp-with-wati), and [email with Resend](/dashboard-integrations/email-with-resend). |
| Handle support intake.      | Understanding messy caller speech, summarizing the issue, and routing the case to a team.                  | [Transcripts and recordings](/monitoring/transcripts-recordings-and-summaries), [Zendesk](/integrations/zendesk), and [Intercom](/integrations/intercom).                   |
| Confirm orders or payments. | Speaking amounts clearly, verifying status, and sending the right confirmation.                            | [Text to speech and voices](/voice-ai/text-to-speech-and-voices), [Shopify](/integrations/shopify), and [Stripe](/integrations/stripe).                                     |

## The Call Loop In One Paragraph

Every live call moves through the same five layers: a route carries the call in (Plivo number, SIP trunk, web call, batch, workflow, or test call), a transcriber turns caller speech into text (Deepgram or Soniox), an LLM chooses the next move (OpenAI, Google, or Groq - or a speech-to-speech model that handles hearing and speaking itself), a voice provider speaks the reply (ElevenLabs or Cartesia), and Call History stores the evidence. When a call fails, identify the layer before changing settings - [How Voice AI Works](/voice-ai/how-voice-ai-works) walks the full loop and how to debug each layer.

## When Integrations Enter The Picture

Voice AI becomes useful when the call result moves somewhere your team already works. An integration should answer a simple question: what should happen after the caller gives useful information?

| Caller outcome                       | Good next action                                                  | Relevant integration docs                                                                                                                                                       |
| ------------------------------------ | ----------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Caller asks for an appointment.      | Create or update a calendar event, then send a confirmation.      | [Using integrations in agents](/dashboard-integrations/using-integrations-in-agents), [Google Calendar](/integrations/googlecalendar), [Gmail](/integrations/gmail).            |
| Lead is qualified.                   | Add context to the CRM and alert the owner.                       | [Integration functions](/dashboard-integrations/integration-functions), [HubSpot](/integrations/hubspot), [Salesforce](/integrations/salesforce), [Slack](/integrations/slack). |
| Support case needs follow-up.        | Create or enrich a ticket with transcript and summary context.    | [Zendesk](/integrations/zendesk), [Intercom](/integrations/intercom), [Google Sheets](/integrations/googlesheets).                                                              |
| Campaign needs written confirmation. | Send a WhatsApp or email message after the call branch completes. | [WhatsApp with Wati](/dashboard-integrations/whatsapp-with-wati), [email with Resend](/dashboard-integrations/email-with-resend), [Resend](/integrations/resend).               |

<Note>
  Do not connect an integration just because it exists. Connect it when the caller has given enough information for the action to be safe.
</Note>

## What A Published Agent Carries

DialNexa does not publish only a prompt. A published agent version carries the full call configuration that controls what the caller hears and what your team reviews later.

| Configuration         | Where users see it                                                                   | Runtime effect                                                                                   |
| --------------------- | ------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------ |
| Language              | Voice selector language choices or language selector, depending on dashboard layout. | Controls language fit, voice options, transcriber compatibility, and Hinglish Map visibility.    |
| Transcriber           | Agent builder transcriber selector.                                                  | Chooses Deepgram or Soniox and the model used for live speech recognition.                       |
| LLM model             | Agent builder model selector and model settings popover.                             | Controls reasoning, function calling, fallback behavior, and per-minute model cost preview.      |
| Voice and voice model | Voice selector and voice settings popover.                                           | Controls speaker identity, output model, speed, stability, volume, and Audio Cache key behavior. |
| Call settings         | Agent Settings.                                                                      | Controls silence timeout, duration, voicemail detection, call ending, and transfer behavior.     |
| Post-call fields      | Agent Settings.                                                                      | Defines the structured fields users expect after the call.                                       |

## The First Pages To Read

<CardGroup cols={2}>
  <Card title="How Voice AI Works" icon="workflow" href="/voice-ai/how-voice-ai-works">
    Follow the full runtime loop and debug calls layer by layer.
  </Card>

  <Card title="Choose Voice AI Providers" icon="sliders-horizontal" href="/voice-ai/provider-selection-guide">
    Pick the transcriber (Deepgram, Soniox), LLM (OpenAI, Google, Groq), and voice (ElevenLabs, Cartesia) based on caller language, latency, cost, and voice quality.
  </Card>

  <Card title="Speech To Text" icon="file-text" href="/voice-ai/speech-to-text-and-transcription">
    Understand what Deepgram and Soniox change in live calls.
  </Card>

  <Card title="LLMs And Conversation Behavior" icon="brain" href="/voice-ai/llms-and-conversation-behavior">
    Tune model selection, temperature, fallback, and predictive preprocessing.
  </Card>

  <Card title="Text To Speech And Voices" icon="volume-2" href="/voice-ai/text-to-speech-and-voices">
    Choose and tune ElevenLabs or Cartesia voices.
  </Card>

  <Card title="Speech Settings" icon="sliders-horizontal" href="/agent-settings/speech-settings">
    Tune Response Eagerness, Audio Cache, Denoising Mode, and Hinglish Map.
  </Card>

  <Card title="Call Detail Page" icon="activity" href="/monitoring/call-detail-page">
    Read the evidence after real calls.
  </Card>

  <Card title="Dashboard Integrations" icon="plug" href="/dashboard-integrations/overview">
    Move call outcomes into WhatsApp, email, workflows, and external tools.
  </Card>

  <Card title="Integration Catalog" icon="blocks" href="/integrations/overview">
    Browse business systems and provider pages that can support voice workflows.
  </Card>
</CardGroup>

## A Practical First Test

Run one controlled test before trusting any provider choice.

<Steps>
  <Step title="Create one short test script">
    Include the welcome line, one caller interruption, one name, one city, one amount, and one final outcome.
  </Step>

  <Step title="Use one published draft stack">
    Pick language, transcriber, LLM, voice, and phone path. Publish the version you want to test.
  </Step>

  <Step title="Place three calls">
    Run a clean call, a noisy call, and a caller-interrupts-early call.
  </Step>

  <Step title="Score the evidence">
    Mark transcript accuracy, first response delay, pronunciation, function calls, summary, and post-call fields.
  </Step>

  <Step title="Change one thing">
    Change only the transcriber, only the LLM, or only the voice. If you change everything, the winner gets credit for work it may not have done.
  </Step>
</Steps>

## Recap

Voice AI in DialNexa is a stack: route, transcriber, LLM, voice, and evidence. Most production fixes come from finding the exact layer that failed, then changing one setting and testing the same call pattern again.