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).
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: |
| Region | The region used for your speech services. For more details, see Speech service supported regions. |
| API Key |
💡Not required when type “Nimbus AI Services” was selected. 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. This may lead to |
Notes and FAQ
Azure Cost and Billing
Transcription troubleshooting
Â