> For the complete documentation index, see [llms.txt](https://docs.dapta.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.dapta.ai/ai-voice-agents/ai-voice-agents.md).

# Start here

Voice Agents make and answer phone calls for you. What they do, what you need to run one, and where to go for each part of the setup.

A **Voice Agent** is an AI that talks on the phone — it calls your leads, answers your inbound line, books appointments, qualifies, transfers to a person when it should, and writes down what happened.

It runs on a real phone number, speaks in the language and tone you give it, works from your own company information, and can reach into your systems mid-call.

## What you need to run one

|                         |                                                                                  |
| ----------------------- | -------------------------------------------------------------------------------- |
| **An agent**            | Its purpose, instructions, voice and behaviour                                   |
| **A phone number**      | Bought in Dapta, verified from your own line, or your own SIP trunk              |
| **Something to say**    | Your company context, and a Brain if it needs to know your catalogue or policies |
| **A way to measure it** | Metrics, transcripts, and the variables the agent captures on every call         |

***

## Start here

{% content-ref url="/pages/aYi9pJObiV6RNXLnR059" %}
[Create your first Voice Agent](/ai-voice-agents/creating-a-voice-agent.md)
{% endcontent-ref %}

{% content-ref url="/pages/LTTYVGIha5QU4p862AQe" %}
[Configure your agent](/ai-voice-agents/how-to-set-up-your-ai-voice-agent.md)
{% endcontent-ref %}

## Give it a phone line

{% content-ref url="/pages/we5zspVTGdlh8PjAmZVe" %}
[Buying Phone Numbers through Dapta](/ai-voice-agents/phone-numbers/buying-phone-numbers-through-dapta.md)
{% endcontent-ref %}

{% content-ref url="/pages/JdvL0SojlEy8DZBqVXOx" %}
[Connecting your telephony (SIP trunk) to Dapta](/ai-voice-agents/phone-numbers/connecting-your-sip-trunk.md)
{% endcontent-ref %}

## Let it do things

{% content-ref url="/pages/ep52rgmRRdUR5nGya2Zh" %}
[Agent actions](/ai-voice-agents/agent-actions.md)
{% endcontent-ref %}

## Call a list

{% content-ref url="/pages/rsR0nQ5Dv7MR3pHNQre0" %}
[Sequences](/ai-voice-agents/how-to-create-your-first-campaign-in-dapta.md)
{% endcontent-ref %}

## See how it went

{% content-ref url="/pages/uI8l4qDh6RmvBK0qHvWa" %}
[Voice Agent Metrics](/ai-voice-agents/analyze-your-calls/voice-agent-metrics.md)
{% endcontent-ref %}

{% content-ref url="/pages/4BbTdf7Ys54cKii0LwlT" %}
[Extracting Information from your Calls](/ai-voice-agents/analyze-your-calls/extracting-information-from-your-calls.md)
{% endcontent-ref %}

***

## What people build with them

* **Outbound qualification** — call a list, ask the questions your sales team would, pass on only the ones worth a human's time.
* **Inbound reception** — answer every call, at any hour, and book or route it.
* **Appointment booking and reminders** — fill the calendar and cut no-shows.
* **Follow-up at scale** — reach hundreds of contacts without hiring for it.

{% content-ref url="/pages/Itx6Rcuw87OFJueeoRNl" %}
[Voice Agent Use Case: Calling & Logging HubSpot Leads](/ai-voice-agents/ai-voice-agents/voice-agent-use-case-calling-and-logging-hubspot-leads.md)
{% endcontent-ref %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.dapta.ai/ai-voice-agents/ai-voice-agents.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.