Skip to main content
Prototype voice agents in the Playground. Test prompts, configure voices, and deploy in seconds.

​
Create your agent

Go to play.cartesia.ai/agents and select Start in Playground.
Create your first voice agent options
Describe your agent in the prompt builder.
Describe your agent interface
Configure your agent’s behavior:
  • Use Case — Professional or Personal
  • Attitude — Personality traits (Concise, Empathetic, Informative)
  • Main Goals — What your agent should accomplish
Start from example agents (Customer Support, Sales Assistant, Pizza Delivery) or skip the wizard to write your prompt directly. Submit to deploy. Your agent builds in under 30 seconds.

​
Configure your agent

Customize your agent’s behavior, voice, and greeting.
Dynamic agent configuration interface
System Prompt — Define your agent’s role and guidelines. The editor provides structured sections: Your Role, Conversation Guidelines, Core Capabilities, and Additional Information. Voice — Choose from Cartesia’s voice library. Preview voices before selecting. Initial Message — Set the greeting your agent speaks when calls start. Check Skip agent introduction to have the agent wait for the user to speak first. Background Sound — Add ambient audio for call center atmospheres or office environments. Preview changes before publishing.

​
Continue building in code

Connect your Playground agent to GitHub to customize with code.
1

Connect to GitHub

On your agent page, click Connect to GitHub. Authorize Cartesia to create a repository.
2

Clone locally

git clone https://github.com/your-org/your-agent.git
cd your-agent
3

Install dependencies

uv pip install .
4

Edit your agent

Open main.py to add tools, custom logic, or modify the prompt.
5

Deploy

Push to deploy your changes.
git push

​
Next steps

Quickstart

Build agents with the SDK

Agents

Prompts, voices, and pre-call configuration