Voice Mode is an optional capability of the AI Chat. It depends on external speech services for output (Text-to-Speech) and input (Speech-to-Text) and becomes available in the AI Chat interface only after the Voice Control connection has been configured and activated.
For general information on setting up and editing connections, see Connection Details and Set up a connection.
Settings
Go to Configuration > Connections > AI+Chat and click Set up... on the Voice Control card, or Edit... if it is already configured. The settings currently support Azure Cognitive Services speech services. Both services are configured independently:
Service |
Setting |
Description |
|---|---|---|
Text-to-Speech (TTS) |
URL |
The speech service endpoint used for TTS requests. |
API key |
The credential used to authenticate requests. |
|
Model / Voice |
The neural voice used for speech synthesis, for example en-US-JennyNeural. |
|
Speech-to-Text (STT) |
URL |
The speech service endpoint used for STT requests. |
API key |
The credential used to authenticate requests. |
|
Model |
The speech recognition model version used for transcription. |
Availability of voice features
•Voice Mode (reading assistant responses aloud) requires a configured TTS service.
•Dictate Mode (converting spoken input into text) requires a configured STT service.
If only one service is configured, only the corresponding voice feature is available.
|
Note: The provided docker-compose.yml defines no Voice Mode specific environment variables. Voice Control is configured on the Voice Control card of the AI+Chat tab in the user interface. |
