Skip to main content
This guide takes you from an empty page to a working consultation. By the end you’ll have TORTUS embedded in your app, a consultation running, and structured results flowing back to your code.

Prerequisites

Before you begin, make sure you have:
  • A publishable key (pk_...) and a client ID + client secret from TORTUS. Contact us if you need them.
  • A modern browser target (ES2020+) and access to install from GitHub Packages.
  • A secure backend you control. Launch tokens must never be minted in the browser.

Steps

1

Install the SDK

Configure the @tortus-ai scope to use GitHub Packages, then install the package.
See Installation for the full registry and authentication setup.
2

Mint a launch token on your backend

The SDK authenticates with a short-lived launch token that you fetch from your own server, so your client secret never reaches the browser.Save the user_id TORTUS returns and resend it as userId on later launches.
Read the full flow, including persisting and resuming users, in Authentication.
3

Add a container to your page

TORTUS renders into an element you provide. Give it a width and height.
4

Load TORTUS

Initialise the client. It starts in standby mode, waiting for instructions.
5

Handle the result

Subscribe to consultation:completed and acknowledge receipt with finish().
6

Start a consultation

Kick off a face-to-face consultation. TORTUS takes over the embedded view from here.
That’s the full loop: load → start → receive results → acknowledge. Everything else builds on these steps.

Next steps

Consultations

Explore audio, face-to-face, and live recording modes plus EHR integrations.

Handling events & results

Learn the full event lifecycle and how to read artifacts.

Configuration

Every option loadTortus() accepts.

How it works

The mental model behind the embedded client.