This documentation site provides information on how Corti foundation models can be integrated via the Corti API, allowing organizations to build bespoke healthcare AI solutions that meet their specific needs.

​
Documentation

Quickstart

Walkthrough and examples on how to authenticate and make your first API request

Get access

Self-service console to create API client credentials and monitor usage

Real-time ambient documentation

Overview for how to build a real-time ambient documentation app using the streaming fact extraction API

Dictation SDK

Download the dictation SDK to build your speech recognition app in minutes

Standard templates

Description of out of the box templates and template sections, along with the templateKey to use in API requests

Languages

Description of available languages, language code to use in API requests, and speech recognition capabilities per language tier

​
API Reference

Real-time audio stream

Detailed spec for real-time conversational transcript and fact extraction

Stateless dictation

Detailed spec for real-time dictation and voice commands

Create interaction

Detailed spec for creating an interaction and setting appropriate context

Upload recording

Attach an audio file to the interaction

Create transcript

Convert audio files to text

Generate document

Create one to many documents for an interaction based on transcripts, facts, or other documents/ text

​
Resources

Support center

View help articles and support documentation, open tickets, and contact the Corti team

Release notes

Learn about updates to the API, language models, foundation models, and more

Authentication methods

Learn about how to use OAuth based on your workflow needs

Error handling

Troubleshoot the most common errors in API responses