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

# Introduction

Voice agents that talk to callers in real time with a speech-to-speech model: what they are, how they work and how the editor is organised.

A **realtime agent** is a voice agent that answers phone calls with a **speech-to-speech model**, such as OpenAI's gpt-realtime or Gemini Live. The model listens to the caller and answers with its own voice directly – there is no conversation flow with nodes. You describe the agent's role and rules in a prompt, connect the systems it may use as MCP tools, and put it on a phone number.

A realtime agent works in one of two modes – **Audio native** for voice calls or **Text native** for chat conversations. See [Audio native vs Text native](https://docs.borndigital.ai/realtime-agent/audio-native-vs-text-native.md).

## Realtime agent or Digital Agent?

|                    | Realtime agent                                                         | Digital Agent                                              |
| ------------------ | ---------------------------------------------------------------------- | ---------------------------------------------------------- |
| How you build it   | A prompt, optional skills and MCP tools                                | A conversation flow of nodes                               |
| Channels           | Phone calls (Audio native); chat bubbles (Text native)                 | Chat bubble and phone calls                                |
| Conversation style | Natural and fast; the caller can interrupt                             | Exactly as designed; every step under your control         |
| Best for           | Open conversations, service lines, information and simple transactions | Strict processes, forms, identification, regulated scripts |
| Handing over       | Can end the call; no transfer to an operator                           | Transfer and redirect to an operator                       |

## How it works

1. A customer calls a phone number the agent is deployed to.
2. The agent greets the caller – the greeting is generated from your prompt.
3. The speech-to-speech model listens and answers. It follows your **prompt**, switches to a **skill** when the conversation needs it, and calls **MCP tools** to look up or change data in your systems.
4. The conversation is transcribed. After the call, the recording or transcript can be sent to an [Insights](https://docs.borndigital.ai/insights/introduction.md) project for analysis.

## Open the Realtime product

After signing in, choose **Realtime** on the product screen (or in the **Select product** menu in the sidebar). You see **All projects** of your organization – see [Projects](https://docs.borndigital.ai/realtime-agent/projects.md).

## The editor

When you open a project, the editor shows:

* **Left (1):** **Agent** and the list of skills, with **Add Skill**.
* **Centre (2):** the agent's **Identity** (its prompt) and **+ MCP server** – or the selected skill.
* **Right (3):** **Audio native** / **Text native**, the agent name, **Settings** (the gear icon), **History**, undo and redo, then **Go live** with the **Phone number** and **Conversation routing**, and the **Model & Voice**, **Listening** and **Transcript** settings.
* **Bottom right (4):** the **Voice chat** bubble for test calls in the browser.
* **Bottom (5):** the navigation bar switches between **Analytics** – the connection to Insights –, **Recordings** – the agent's finished conversations, see [Test and go live](https://docs.borndigital.ai/realtime-agent/test-and-go-live.md#recordings) – and **Agent**. **Prompt library** and **Campaigns** are not available yet.

<figure><img src="https://4261467870-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6iQTvxgRZRwPS1NgIGEb%2Fuploads%2FyryR7xtCFcbUFyZ3yx0q%2Frealtime-editor-overview.png?alt=media" alt="The realtime editor with numbered parts: 1 Agent and the skill invoices with Add Skill, 2 Identity with the prompt and + MCP server, 3 the settings column with Audio native and Text native, History, Go live, Phone number, Conversation routing, Model and Voice, Listening and Transcript, 4 the Voice chat bubble, 5 the navigation bar with Analytics, Recordings and Agent"><figcaption><p>The realtime editor</p></figcaption></figure>

Several people can edit the same agent at the same time; their changes appear almost immediately.

## Build your first realtime agent

1. [Create a project](https://docs.borndigital.ai/realtime-agent/projects.md#create-a-project).
2. Write the [prompt](https://docs.borndigital.ai/realtime-agent/prompt-and-skills.md).
3. Optionally connect [MCP tools](https://docs.borndigital.ai/realtime-agent/mcp-tools.md).
4. Choose the model, voice and listening behaviour in [Voice and listening](https://docs.borndigital.ai/realtime-agent/voice-and-listening.md).
5. [Test it in the browser and go live](https://docs.borndigital.ai/realtime-agent/test-and-go-live.md) on a phone number.
6. Optionally send the calls to [Insights](https://docs.borndigital.ai/realtime-agent/analytics-with-insights.md).
