> ## 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

> Learn how DialNexa voice AI combines agents, providers, call routes, actions, and evidence for real customer conversations.

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.

## 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](https://dialnexa.com/docs/common-use-cases.md).

| 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](https://dialnexa.com/docs/agent-settings/functions.md), [custom functions](https://dialnexa.com/docs/agent-settings/custom-functions.md), and [Google Calendar](https://dialnexa.com/docs/integrations/googlecalendar.md). |
| Qualify leads. | Asking short questions, scoring answers, writing structured fields, and pushing context to the sales team. | [Post-call analysis](https://dialnexa.com/docs/agent-settings/post-call-analysis.md), [HubSpot](https://dialnexa.com/docs/integrations/hubspot.md), and [Salesforce](https://dialnexa.com/docs/integrations/salesforce.md). |
| Send reminders. | Reading a fixed script, handling objections, retrying later, and sending written follow-up. | [Batch calls](https://dialnexa.com/docs/batch-calls/overview.md), [WhatsApp with Wati](https://dialnexa.com/docs/dashboard-integrations/whatsapp-with-wati.md), and [email with Resend](https://dialnexa.com/docs/dashboard-integrations/email-with-resend.md). |
| Handle support intake. | Understanding messy caller speech, summarizing the issue, and routing the case to a team. | [Transcripts and recordings](https://dialnexa.com/docs/monitoring/transcripts-recordings-and-summaries.md), [Zendesk](https://dialnexa.com/docs/integrations/zendesk.md), and [Intercom](https://dialnexa.com/docs/integrations/intercom.md). |
| Confirm orders or payments. | Speaking amounts clearly, verifying status, and sending the right confirmation. | [Text to speech and voices](https://dialnexa.com/docs/voice-ai/text-to-speech-and-voices.md), [Shopify](https://dialnexa.com/docs/integrations/shopify.md), and [Stripe](https://dialnexa.com/docs/integrations/stripe.md). |

## 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, Soniox, or Sarvam), 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, Cartesia, or Sarvam), and Call History stores the evidence. When a call fails, identify the layer before changing settings - [How Voice AI Works](https://dialnexa.com/docs/voice-ai/how-voice-ai-works.md) 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](https://dialnexa.com/docs/dashboard-integrations/using-integrations-in-agents.md), [Google Calendar](https://dialnexa.com/docs/integrations/googlecalendar.md), [Gmail](https://dialnexa.com/docs/integrations/gmail.md). |
| Lead is qualified. | Add context to the CRM and alert the owner. | [Integration functions](https://dialnexa.com/docs/dashboard-integrations/integration-functions.md), [HubSpot](https://dialnexa.com/docs/integrations/hubspot.md), [Salesforce](https://dialnexa.com/docs/integrations/salesforce.md), [Slack](https://dialnexa.com/docs/integrations/slack.md). |
| Support case needs follow-up. | Create or enrich a ticket with transcript and summary context. | [Zendesk](https://dialnexa.com/docs/integrations/zendesk.md), [Intercom](https://dialnexa.com/docs/integrations/intercom.md), [Google Sheets](https://dialnexa.com/docs/integrations/googlesheets.md). |
| Campaign needs written confirmation. | Send a WhatsApp or email message after the call branch completes. | [WhatsApp with Wati](https://dialnexa.com/docs/dashboard-integrations/whatsapp-with-wati.md), [email with Resend](https://dialnexa.com/docs/dashboard-integrations/email-with-resend.md), [Resend](https://dialnexa.com/docs/integrations/resend.md). |

> [!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.

## 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, Soniox, or Sarvam 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, 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

> [card] [How Voice AI Works](https://dialnexa.com/docs/voice-ai/how-voice-ai-works.md)
>
> Follow the full runtime loop and debug calls layer by layer.

> [card] [Choose Voice AI Providers](https://dialnexa.com/docs/voice-ai/provider-selection-guide.md)
>
> Pick the transcriber (Deepgram, Soniox), LLM (OpenAI, Google, Groq), and voice (ElevenLabs, Cartesia) based on caller language, latency, cost, and voice quality.

> [card] [Speech To Text](https://dialnexa.com/docs/voice-ai/speech-to-text-and-transcription.md)
>
> Understand what Deepgram and Soniox change in live calls.

> [card] [LLMs And Conversation Behavior](https://dialnexa.com/docs/voice-ai/llms-and-conversation-behavior.md)
>
> Tune model selection, temperature, fallback, and predictive preprocessing.

> [card] [Text To Speech And Voices](https://dialnexa.com/docs/voice-ai/text-to-speech-and-voices.md)
>
> Choose and tune ElevenLabs, Cartesia, Sarvam or Soniox voices.

> [card] [Speech Settings](https://dialnexa.com/docs/agent-settings/speech-settings.md)
>
> Tune Response Eagerness, Audio Cache, Denoising Mode, and Hinglish Map.

> [card] [Call Detail Page](https://dialnexa.com/docs/monitoring/call-detail-page.md)
>
> Read the evidence after real calls.

> [card] [Dashboard Integrations](https://dialnexa.com/docs/dashboard-integrations/overview.md)
>
> Move call outcomes into WhatsApp, email, workflows, and external tools.

> [card] [Integration Catalog](https://dialnexa.com/docs/integrations/overview.md)
>
> Browse business systems and provider pages that can support voice workflows.

## A Practical First Test

Run one controlled test before trusting any provider choice.

**1. Create one short test script**

Include the welcome line, one caller interruption, one name, one city, one amount, and one final outcome.

**2. Use one published draft stack**

Pick language, transcriber, LLM, voice, and phone path. Publish the version you want to test.

**3. Place three calls**

Run a clean call, a noisy call, and a caller-interrupts-early call.

**4. Score the evidence**

Mark transcript accuracy, first response delay, pronunciation, function calls, summary, and post-call fields.

**5. 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.

## 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.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.