Speech Recognizers are a piece of software that transcribes audio to text. You can create and configure Speech Recognizers in Configuration > Virtual Assistants > Speech Recognizers.
🤔What do I need Speech Recognizers for? Speech Recognizers are needed for Live Caption & Transcription features and for voice input analysis in the Workflow Activity Input Customer (Advanced).
🔍 Refer to Use Case - Setting Up a Speech Recognizer in Azure Portal and Nimbus for an instruction on how to set up Speech Recognizer.
INC Azure Billing Cognitive Services
Disclaimer: Support for Azure Billing & Cognitive Services
☝ The usage of Microsoft Azure AI Services for Speech1 and AI2 will cause additional costs outside your Nimbus subscription, which are exclusively determined by Microsoft.
Please note:
- Nimbus Support does not cover pricing discussions or make recommendations on Microsoft Azure Services. → Please inform yourself via the references below on pricing models.
- Nimbus Support can not provide any technical help, insights or solutions on Azure Cognitive Service related technical problems.
1 Azure Speech Services: https://azure.microsoft.com/en-us/pricing/details/cognitive-services/speech-services/
2 Generative AI Services (Copilot Studio):
Configuring Speech Recognizers
A Speech Recognizer consists of the following elements:
| Item | Description |
|---|---|
| Name | Name of your speech recognizer as it appears in lists and selections. |
| Organization Unit | Determines where the speech recognizer will be available. |
| Type |
The type of the speech recognizer. You can either bring your own Azure AI Service or use the native Nimbus AI Service:
💡The “Type” field may be locked to “Azure AI Services" (Bring your own). Nimbus Development aims to provide a native solution on all clusters, opening up this selection field with a later release. |
| Region | The region used for your speech services. For more details, see Speech service supported regions. |
| API Key | The API Key of your speech service. |
| Multilanguage | If toggled on, multiple languages can be selected for the speech recognizer. |
| Language |
Selected language for the speech recognizer to recognize. 💡If no language is selected, the language will be auto-detected. |