SDKs & Tools

Official SDKs, web components, and developer tools for the Corti API

The fastest way to integrate the Corti API is through our official SDKs. They handle authentication, token refresh, WebSocket connections, pagination, retries, and error handling — so you can focus on building your healthcare application.

Official SDKs

JavaScript SDK

Full-featured SDK for Node.js and browser environments. Supports all REST endpoints, real-time WebSocket streaming, and every authentication flow.

npm install @corti/sdk

C# .NET SDK

Production-ready SDK for .NET 8+, .NET Framework 4.6.2+, and .NET Standard 2.0. Full API coverage with async/await and WebSocket support.

dotnet add package Corti.Sdk

Why use an SDK?

	Raw API calls	With an SDK
Authentication	Manual OAuth token exchange and refresh logic	Automatic: just provide credentials
Token management	Track expiry, handle refresh races, store tokens	Built-in with thread-safe refresh
WebSockets	Raw connection management, reconnection, message parsing	Managed connections with typed events
Type safety	Manual request/response validation	Full JavaScript / C# type definitions
Error handling	Parse HTTP status codes and error bodies	Typed exceptions with structured details
Pagination	Manual cursor/offset tracking	for await / await foreach iteration
Retries	Implement backoff for 429/5xx	Configurable automatic retries

Web Components

Dictation Web Component

Drop-in <corti-dictation> element with built-in UI for real-time speech-to-text. Handles microphone management, audio streaming and live transcripts. Works with any frontend framework or vanilla HTML.

Ambient Web Component

Drop-in <corti-ambient> element with built-in UI for real-time multi-speaker ambient streaming. Handles microphone management, audio streaming, and live transcripts and facts. Works with any frontend framework or vanilla HTML.

Adapters

AI SDK Adapter

Adapter for integrating Corti A2A agents with the Vercel AI SDK. Build chat interfaces powered by Corti agents using familiar patterns like useChat.

Developer Tools

Postman Collection

Pre-built API requests for testing every Corti endpoint. Import into Postman and start exploring immediately.

Examples Repository

Working examples for JavaScript, C# .NET, React, and more — covering authentication flows, WebSocket streaming, dictation, proxy setups, and embedded assistant integration.

Quickstart

Pick your language and follow the guide:

1. Get API credentials

   Sign up at the Corti Console and create an API client. See Getting Access for details.

2. Install the SDK

   JavaScript

   npm install @corti/sdk
   # or
   yarn add @corti/sdk
   # or
   pnpm add @corti/sdk
   

   dotnet add package Corti.Sdk
   
   # Alternatively, in your .csproj:
   # <PackageReference Include="Corti.Sdk" Version="*" />
   
3. Create a client

   JavaScript

   import { CortiClient } from "@corti/sdk";
   
   // Replace these with your values
   const CLIENT_ID = "<your-client-id>";
   const CLIENT_SECRET = "<your-client-secret>";
   const ENVIRONMENT = "<eu-or-us>";
   const TENANT = "<your-tenant-name>";
   
   const client = new CortiClient({
       environment: ENVIRONMENT,
       tenantName: TENANT,
       auth: {
           clientId: CLIENT_ID,
           clientSecret: CLIENT_SECRET,
       },
   });
   

   using Corti;
   
   // Replace these with your values
   const string CLIENT_ID = "<your-client-id>";
   const string CLIENT_SECRET = "<your-client-secret>";
   const string ENVIRONMENT = "<eu-or-us>";
   const string TENANT = "<your-tenant-name>";
   
   var client = new CortiClient(
       tenantName: TENANT,
       environment: ENVIRONMENT,
       auth: CortiClientAuth.ClientCredentials(
           clientId: CLIENT_ID,
           clientSecret: CLIENT_SECRET)
   );
   
4. Make your first API call

   JavaScript

   // Token acquisition and refresh happen automatically
   const interactions = await client.interactions.list();
   

   var pager = await client.Interactions.ListAsync(new InteractionsListRequest());
   

   import requests
   
   # Replace these with your values
   ENVIRONMENT = "<eu-or-us>"
   TENANT = "<your-tenant-name>"
   TOKEN = "<your-access-token>"
   
   response = requests.get(
       f"https://api.{ENVIRONMENT}.corti.app/v2/interactions",
       headers={
           "Authorization": f"Bearer {TOKEN}",
           "Tenant-Name": TENANT,
       },
   )
   response.raise_for_status()
   interactions = response.json()["interactions"]
   

   # Replace these with your values
   ENVIRONMENT="<eu-or-us>"
   TENANT="<your-tenant-name>"
   TOKEN="<your-access-token>"
   
   curl "https://api.${ENVIRONMENT}.corti.app/v2/interactions" \
     -H "Authorization: Bearer ${TOKEN}" \
     -H "Tenant-Name: ${TENANT}"
   

---

For support or questions, contact us