Skip to main content
This quickstart walks through setting up a simple LLM-to-TTS conversational pipeline with the Inworld Node.js Agent Runtime SDK in just a few minutes. The pipeline is powered by an LLM for generating the response and Inworld’s TTS model for generating the audio output. You’ll use the Inworld Runtime CLI to scaffold a project from a template, so you can fast-track development whether you’re building a new project or migrating an existing feature. After completing this guide, you will have a conversational pipeline running locally, ready to extend and integrate with your own application.

​
Inworld Runtime CLI Overview

The Inworld Runtime CLI enables local development, testing, and deployment of AI graphs. Get started with installation, authentication, and your first graph project.

​
Key Capabilities

  • Local Development: Create and test graphs in your development environment
  • Project Templates: Bootstrap projects with production-ready templates (including LLM+TTS samples)
  • Authentication: Secure access to Inworld services
  • Local Servers: HTTP and gRPC servers for integration testing
  • Graph Management: Visualization, deployment, and variant management

​
Prerequisites

Before you get started, please make sure you have the following installed:

​
Setup

1

Install CLI

Create a new test folder and install the Inworld Runtime CLI globally.
sudo npm install -g @inworld/runtime
Verify the installation by checking available commands:
inworld-runtime help
2

Authenticate with Inworld Platform

Log into your Inworld account to access platform services.
inworld-runtime login
Verify your authentication status:
inworld-runtime status
3

Create Your First Project

The inworld-runtime init command downloads the llm-to-tts-node template—a production-ready LLM to TTS pipeline with GPT-4o-mini (by default) and TTS.
Currently, only the llm-to-tts-node template is available via CLI. To view all available templates, visit the templates repository.
inworld-runtime init --template llm-to-tts-node --name my-project
4

Install Dependencies

Navigate to your project directory and install the required Node.js dependencies.
cd my-project  # Or your project name
npm install
Your CLI setup is now complete! You can start testing your graph locally.

​
Local Development & Testing

# Basic input
inworld-runtime run ./graph.ts '{"input":"test"}' 

# Complex structured input format
inworld-runtime run ./graph.ts '{
"input": {
    "message": "Hello world",
    "context": "greeting",
    "urgency": "low"
}
}'

# Advanced input with execution context
inworld-runtime run ./graph.ts '{
    "input": {"message": "Hello world"},
    "executionId": "123e4567-e89b-12d3-a456-426614174000",
    "userContext": {"targetingKey": "user123", "attributes": {"tier": "premium"}},
    "dataStoreContent": {"sessionData": "value"}
}'

​
Local Servers

Available transports:
  • http (default) - REST API with optional Swagger UI
  • grpc - gRPC server for high-performance applications
# Serve on HTTP Server with Swagger
inworld-runtime serve ./graph.ts --swagger  

# Serve on custom port
inworld-runtime serve ./graph.ts --port 8080

# Serve on custom host
inworld-runtime serve ./graph.ts --host 0.0.0.0 --port 3000

# Combine options
inworld-runtime serve ./graph.ts --host 0.0.0.0 --port 8080 --swagger

# gRPC server for high-performance applications
inworld-runtime serve ./graph.ts --transport grpc

​
Test HTTP Requests

curl -X POST http://localhost:3000/v1/graph:start -H "Content-Type: application/json" -d '{"input": "Hello"}'

​
Next Steps

Once you have your CLI set up and tested locally, you can:
  1. Deploy to Cloud - Deploy your graphs to Inworld Cloud
  2. Experiments - Build, register, target, and monitor variants end to end
  3. Experiments UI - Manage Portal targeting rules and rollouts

​
Need Help?

  • Setup & development issues? See CLI Troubleshooting Guide
  • Advanced workflows & production issues? See Experiments for the full CLI + Portal loop
  • General CLI help: Run inworld-runtime help or inworld-runtime [command] --help