> 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/flow-studio/nodes/dapta-phone-call.md). # Dapta Phone Call Connect a Flow Studio automation to a Voice Agent: set the From and To numbers, choose the agent, and pass dynamic variables that personalize the call. Our Dapta Phone Call nodes work as a direct connection to our AI Voice agents. They allow you to connect remotely to the agent via a flow in the Flow Studio and send variables to your voice agent. ## What does the Dapta Phone Call node do? It connects a Flow Studio automation directly to your Voice Agents so the flow can place a call. You set a From number, your registered Dapta or verified number, and a To number, pick which agent handles the call, and pass dynamic variables the agent's prompt uses to personalize what it says. To access the node, we are going to open the Flow Studio and add the node to the canvas Open a flow, click the **+** button and search the **Actions** panel for **Make a Call**. The node appears on the canvas as **Dapta Phone Call**.

Empty Flow Studio canvas with the Actions panel open on the right — The Actions panel opens next to the canvas

Actions panel filtered by — Search for Make a Call

The Dapta Phone Call node placed under the Start node on the canvas — The node connected under Start

Once you open the node you can set a “From” phone number as well as a “To” from number. It’s important to take into account these following points: * The from number NEEDS to be a registered phone number. That one is by default Dapta’s phone number but if you want to send calls from a number of your choosing, you have to register your phone number on the Voice Agents>Phone number section

Voice Agents, Phone Numbers page with the Verified, Purchased, Compliance and End Users tabs and the New Phone Number button — Voice Agents → Phone Numbers

* Numbers ALWAYS need to start with a + * Numbers should ALWAYS have the country code You can then select the agent you want your calls to use

Dapta Phone Call node configuration with the Agent dropdown open listing the workspace voice agents — Pick the voice agent that will place the call

And finally you can set your dynamic variables. These are the parameters that the agent will replace in the prompt so that conversations can be personalized.

Variables section of the node with an empty Name and Value row and the Add Variables link — Add a variable row per prompt placeholder

You can select any variable that you have defined in your agent’s prompt inside brackets {{}}

Name dropdown listing the prompt variables contact_name, contact_email and current_time — The Name list is read from the agent prompt

Now you’re all set! Every time the flow will be executed, the agent will call that number and replace the variables for the values you set. You can also set those variables to be dynamic by clicking on the top right button of the input field

Variables row showing the small green dot at the top right of the Value field — The dynamic toggle on the Value field

Value field expanded showing trigger and daptaVault as upstream sources to pick from — Pick an output from an upstream node

There you can set it to any other node located in the flow studio and connected to the Dapta Phone call node. \ \
\ \ \ \
--- # 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/flow-studio/nodes/dapta-phone-call.md?ask=&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.