Skip to main content
This builds a working voice assistant: it greets the caller, listens, and responds in real time. The example uses Deepgram, Google Gemini, and Cartesia. Select your language in the tabs; the steps are otherwise the same.

Prerequisites

  • A Zero Runtime address and auth token from the dashboard
  • API keys for the providers you use (Deepgram, Google, and Cartesia here)
  • One of: Python 3.11+, Node.js 18+, or Go 1.26+
1

Install the SDK

2

Set your environment

3

Write your agent

4

Run it

When the worker starts, it prints a playground link in your terminal. Open it in your browser to talk to your agent and hear it respond in real time.

What’s next

The Plugins section documents each stage you configured above: Deepgram, Google Gemini, Cartesia, Turn Detector, Silero, and RNNoise. For how they fit together, read Pipeline; to understand what runs where, read Why Zero Runtime.