> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://developers.deepgram.com/docs/voice-agent/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://developers.deepgram.com/_mcp/server.

# Getting Started

* [Deepgram API Playground: try the Voice Agent API interactively](https://playground.deepgram.com/?endpoint=agent)

Deepgram's Voice Agent API handles the full speech pipeline (listening, thinking, and speaking) so you can focus on what your agent does, not how it hears or talks.

* [Build a Voice Agent](/docs/build-a-voice-agent): step-by-step guide to creating your first voice agent with Python, JavaScript, C#, or Go.
* [Configure Your Agent](/docs/configure-voice-agent): speech-to-text models, LLM providers, TTS voices, endpointing, and audio formats.
* [Function Calling](/docs/voice-agents-function-calling): let your agent call external APIs and tools mid-conversation.
* [Multi-Agent Architecture](/docs/multi-agent-architecture): orchestrate multiple specialized agents that hand off based on context, intent, or domain.

## Explore Further

* [Reusable Configurations](/docs/reusable-agent-configurations): save and reuse agent settings across projects.
* [Telephony](/docs/inbound-telephony-agent): connect voice agents to phone networks for inbound and outbound calls.
* [Browser Agent SDK](/docs/browser-agent-overview): add voice AI to any web application via four composable packages.
* [Prompting](/docs/prompting-voice-agents): write system prompts that shape live-call behavior.
* [Template Apps](/docs/voice-agent-template-apps): clone a working voice agent project and start building.
* [API Reference](/reference/voice-agent/voice-agent): complete WebSocket protocol reference for the Agent API.
* [Feature Overview](/docs/voice-agent-feature-overview): the full list of Voice Agent API capabilities.

> Build real-time, interactive voice agents powered by Deepgram's speech-to-text, LLM integration, and text-to-speech, all over a single WebSocket connection.