> ## Documentation Index
> Fetch the complete documentation index at: https://docs.zeptar.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Welcome to Zeptar

> Build and ship real-time voice agents — from the dashboard or the API.

Zeptar is a platform for building **real-time voice agents**. Describe how an
agent should behave, preview it by talking to it, and ship versions you can
trust. Everything you can do in the dashboard is also available over a clean,
versioned REST API.

## Pick your path

<Columns cols={2}>
  <Card title="ZeptarAgents" icon="microphone" href="/agents/overview" horizontal>
    The product: design an agent's behavior, preview the conversation, and
    publish versions safely with branches and drafts.
  </Card>

  <Card title="ZeptarAPI" icon="code" href="/api-reference/introduction" horizontal>
    The API: manage agents, start conversations, and automate your workspace
    from your own backend with an API key.
  </Card>
</Columns>

## Jump straight in

<Columns cols={2}>
  <Card title="Build your first agent" icon="rocket" href="/agents/quickstart">
    Create an agent, write a system prompt, and talk to it in the live preview.
  </Card>

  <Card title="Make your first API request" icon="terminal" href="/api-reference/quickstart">
    Create an API key and call the Zeptar API in a couple of minutes.
  </Card>
</Columns>

## How the pieces fit

* **Agents** run a speech pipeline (speech-to-text → language model →
  text-to-speech → turn-taking). You configure behavior; the runtime
  orchestrates the call. See [the agent overview](/agents/overview).
* **Branches, drafts, and versions** let you change an agent without touching
  what's live. See [Versioning](/agents/operate/versioning).
* **The API** mirrors the product surface under `/v1`, authenticated with a
  session cookie (browser) or an API key (server-side). See
  [Authentication](/api-reference/authentication).