Live Transcribing Phone Calls using Twilio Media Streams and DeepgramAI

With Twilio Media Streams, you can extend the capabilities of Twilio-powered voice application with real time access to the raw audio stream of phone calls. For example, we can build tools that transcribe the speech using DeepgramAI from a phone call live into a browser window, run sentiment analysis of the speech on a phone call or even use voice biometrics to identify individuals.

Prerequisites

Before we can get started, you’ll need to make sure to have:

• A Free Twilio Account
• A Deepgram Account
• Installed ngrok

---

Setup

1. Modify the .env.sample file to include the Deepgram API keys and save it as a .env file

2. Run the following commands:

   Start ngrok:

   $ ngrok http 8080

   While this is running in a new window copy the forwarding HTTPS URL (https://xxxxx.ngrok.io) and configure the Voice url of the number in your Twilio console. not this is for Inbound calls

   Install dependencies and start your server:

   $ npm install

   $ npm start

---