Assistants quickstart
Overview
Create a voice assistant, connect it to a phone number, and make your first calls. You can complete this quickstart in the Dashboard or with the Vapi API.
In this quickstart, you’ll:
- Create and test an assistant
- Connect the assistant to a phone number
- Make inbound and outbound calls
Prerequisites
- A Vapi account
- For cURL or SDK requests, a Vapi API key
1. Create an assistant
By default, when you create an assistant, the transcriber, model, and voice are set to the Balanced preset.
Dashboard
cURL
TypeScript (Server SDK)
Create an assistant
Select Create Assistant to create a blank assistant.
To start from a predefined template instead, select the down arrow next to Create Assistant, then choose a template.
Configure the conversation
Replace the content in First Message and System Prompt with the following examples.
First message
System prompt

Publish the assistant
Select Publish, review the changes, then select Quick Publish. Publishing creates a new assistant version.
2. Connect a phone number
Dashboard
cURL
TypeScript (Server SDK)
Choose a phone number option
Select Create Phone Number, then choose Free Vapi Number. To use a number from another provider, choose the corresponding import option instead.

Create the phone number
Enter a three-digit US area code in Area Code, then select Create.
Your first free Vapi number does not require a payment method. To create additional free Vapi numbers, add a payment method. You can create up to five free Vapi numbers in total.
Free Vapi phone numbers support US area codes only. For international use, import a number from another provider.
3. Make your first calls
Test an inbound call
Call the phone number you created. Your assistant answers with its configured first message.
Place an outbound call
Dashboard
cURL
TypeScript (Server SDK)
Open the phone number
Open the Dashboard, select Phone Numbers, then select the phone number that will place the call.

Next steps
- Add tools: Custom tools
- Tune speech: Speech configuration
- Use a preset: Model Intelligence presets bundle a transcriber, model, and voice for common use cases.
- Structure data: Structured outputs
- Move to multi-assistant: Squads