Use Case - Setting Up a Speech Recognizer in Azure Portal and Nimbus

A step-by-step guide for setting up a Speech Recognizer in Azure Portal and integrating it with Nimbus.

Speech recognition is the process of converting spoken words into written text or commands. Speech Recognizers can be used for various purposes, such as Live Caption & Transcription or voice input. In this use case, we will configure a Speech Recognizer in Azure Portal and add it in Nimbus.


You require tenant administrator rights to add and configure Speech Recognizers in Nimbus Admin.


INC Azure Billing Cognitive Services


The usage of Standard Azure AI Services will cause Azure Cognitive Services costs. These costs are determined by Microsoft. Also see:

  • Please note that Nimbus support does not cover pricing discussions or make recommendations based on the Microsoft Azure infrastructure.

Configuring a Speech Service in Azure Portal

  1. Go to Azure Portal and sign in.
  2. On the Azure home page, search for “Speech services” in the search bar and select it from the results.
  3. On the Speech services page, click “Create” to create a new speech service.
  4. On the Create Speech Services page, select your subscription, the resource group, and the region.
  5. Enter a name for your speech service.
  6. Select the pricing tier that suits your needs.
    💡You can use the F0 (free) tier which allows up to 5 hours of free speech recognition per month.
  7. Click Review + create to review your settings and then Create to create your speech service.
  8. Wait for the deployment to complete.
    ⮑ You will see a notification once your speech service is ready to use.
  9. Go to the overview page of your speech service where the details of your speech service are shown.
  10. For registering your speech service in Nimbus, you will need one of the two keys and the location/region code.
    Copy/save them for later use.

Adding Your Speech Service in Nimbus

  1. In Nimbus Admin, go to Configuration > Virtual Assistants > Speech Recognizers.
  2. Click Create new.
  3. Enter a name and select the Organization Unit for your Speech Recognizer.
  4. Select the region of your speech service and enter the previously saved API key.
  5. In the language section, you can add up to 4 different languages for use with the Speech Recognizer.
  6. Click Create to save and create your Speech Recognizer.
    ⮑ Your Speech Recognizer is ready to use for Live Caption & Transcription and for voice input analysis e.g. in the Input Customer (Advanced) Workflow Activity.

Using Your Speech Recognizer

Once your Speech Recognizer is set up, you can use it for Live Caption & Transcription and in the Workflow Activity Input Customer (Advanced). Refer to the following use cases to learn more:

Table of Contents