Amazon Connect and Deepgram
Integrate Deepgramβs Speech-to-Text (STT) and Text-to-Speech (TTS) models directly into Amazon Connect and Amazon Lex to power intelligent IVR systems and virtual voice agents.
This guide explains how to integrate your Deepgram models into Amazon Connect flow.
Overview
Amazon Connect is AWSβs cloud-based contact center platform, and Amazon Lex provides tools for quickly building conversational chatbots. With Deepgram integrated into Connect, organizations can seamlessly replace AWS Transcribe and Polly with Deepgramβs STT and TTS modelsβwithout modifying their existing Connect flows or operational logic.
This integration supports Deepgram-hosted customers only. Support for self-hosted deployments will be added in a future phase.
Architecture
-
Connect/Lex β Deepgram (STT): Live caller audio is streamed to Deepgram for real-time transcription.
-
Deepgram β Connect/Lex: The transcript is returned instantly for intent recognition or routing logic.
-
Connect/Lex β Deepgram (TTS): Lex sends text to Deepgram TTS model to generate natural spoken responses.
Prerequisites
Before starting:
- An active Deepgram account
- An active AWS account
- A Deepgram API key
- An Amazon Connect instance, and Amazon Lex bot if using Lex
Before you can use Deepgram, youβll need to create a Deepgram account. Signup is free and includes $200 in free credit and access to all of Deepgramβs features!
Get Your Deepgram API Key and Add as AWS Secret
-
Sign in to the Deepgram Console.
-
Go to API Keys β Create API Key.
-
Copy the generated key β youβll need it in AWS Connect.
-
Follow these steps to store the Deepgram API key in your AWS Secrets Manager
Configure Deepgram in Amazon Lex
If youβre using Amazon Lex bots in your Connect flow, follow the AWS guide to set up Deepgram in Amazon Lex.
Configure Deepgram STT in Amazon Connect
Follow the AWS guide to configure Deepgram as the STT provider in your Amazon Connect bots.
- Under Model Type, select Speech-to-Text
- Under Voice Provider, select Deepgram
- Under Model Id, fill in the Deepgram model you want to use, e.g.
nova-3-general. Please see the full list of supported languages and models. - Under Secrets Manager ARN, use the ARN for you Deepgram API key from Step 1
Configure Deepgram TTS in Amazon Connect
Similarly, follow the AWS guide to configure Deepgram as the TTS provider in your Amazon Connect bots.
- In the Set voice block in your Connect flow, select Deepgram in the Voice provider dropdown
- Under Model, choose Set manually and enter the Deepgram TTS model you want to use, e.g.
aura-2. - Under Voice, choose Set manually and enter the voice, e.g.
thalia. Under Language, choose Set manually and use a language that is supported by the voice, e.g. English. Please see the full list of supported languages and voices. The model and language/voice combination in Connect setting will map to Deepgramβs model name such as aura-2-thalia-en. - Under Secrets Manager ARN, use the ARN for you Deepgram API key