dashboard.mdx

title	Dashboard
subtitle	Learn to build a voice agent in under 5 minutes.
slug	quickstart/dashboard

Overview

Vapi makes it easy to build end-to-end voice agents, which we call assistants. Assistants support live, two-way conversations. You can call an assistant or have it call you.

Each assistant has three components: Speech-to-text (STT), Language model (LLM) and Text-to-speech (TTS). Vapi gives you full control over each, with dozens of providers and models to choose from.

In this quickstart, you'll learn to:

• Create an assistant in the Vapi dashboard
• Pick your STT, LLM, and TTS providers
• Attach a phone number
• Make your first call over the web or by phone

Prerequisites

• A Vapi account

Get started by creating an assistant

Go to [dashboard.vapi.ai](https://dashboard.vapi.ai) and log in to your account. In the Vapi dashboard, create a new assistant using the customer support specialist template.

<Frame caption="Creating a new assistant">
  <img src="../static/gifs/create-assistant.gif" />
</Frame>

Set the first message that the assistant will speak when a conversation is started with it.

    ```plaintext First message
    Hi there, this is Alex from TechSolutions customer support. How can I help you today?
    ```
  </Step>

  <Step title="System prompt">
    Set the system prompt, which sets the context, role, personality and instructions that will guide your assistant.

    ```plaintext System Prompt
    You are Alex, a customer service voice assistant for TechSolutions. Your primary purpose is to help customers resolve issues with their products, answer questions about services, and ensure a satisfying support experience.
    - Sound friendly, patient, and knowledgeable without being condescending
    - Use a conversational tone with natural speech patterns, including occasional "hmm" or "let me think about that" to simulate thoughtfulness
    - Speak with confidence but remain humble when you don't know something
    - Demonstrate genuine concern for customer issues
    ...
    ```
  </Step>
</Steps>

Select your preferred provider and the large language model (LLM) that will power your assistant (default gpt-4o).

    <Frame>
      <img src="../static/images/quickstart/dashboard/set-llm.png" />
    </Frame>
  </Step>

  <Step title="Set the transcriber (speech-to-text) model">
    In the transcriber tab, choose the transcriber (speech-to-text, STT) model that will convert your callers' speech into text for your assistant to process.

    <Frame>
      <img src="../static/images/quickstart/dashboard/set-transcriber.png" />
    </Frame>

    <Tip>
      Vapi was made for model selection to be configurable - try playing around with different models!
    </Tip>
  </Step>

  <Step title="Choose the voice (text-to-speech) model">
    In the voice tab, select the voice (TTS) model that will determine how your assistant sounds to callers.
    
    <Frame>
      <img src="../static/images/quickstart/dashboard/set-voice.png" />
    </Frame>

    Just like with the transcriber, you can plug in any provider!
  </Step>
</Steps>

Make an inbound call (call your assistant)

Try calling your assistant by clicking the call button in the dashboard.

In the Phone Numbers tab, you can create a free new number or import an existing number from another telephony provider (Twilio, Vonage, Telnyx, etc.).

Select your assistant in the inbound settings for your phone number. Whenever this number is called, your assistant will pick up and have a conversation with them!

Make an outbound call (assistant calls you)

1. Fill out your own phone number as the number to dial. 2. Set the assistant that will be making the call

<Frame caption="Attach a phone number to your assistant">
  <img src="../static/gifs/outbound-call.gif" />
</Frame>

When you click on the outbound call button, your assistant will make an outbound call to the phone number. Your assistant won't yet be able to hang-up the phone at the end of the call. You will learn more about configuring call end behavior in later guides.