Session Speech Parameters Config¶
Description¶
The Session Speech Parameters - Config Node enables the change of speech parameters during the flow.
When executed, the settings will apply for the remainder of the session.
Synthesizer - Text-To-Speech - Settings
The TTS settings can be chosen from a pre-filled dropdown for Microsoft Azure, AWS Polly and Google.
| Parameter | Type | Description |
|---|---|---|
| TTS Vendor | Dropdown | Select the desired TTS Vendor |
| TTS Language | Dropdown | Defines the language of the Voice Bot output |
| TTS Voice | Dropdown | Defines the voice that should be used for the Voice Bot output |
| Custom | Text | The custom fields can be used to choose a TTS voice, which is not in the dropdown list. This can be the case for region specific voices. The format to use is depending on the TTS Vendor e.g. de-DE-ConradNeural |
Recognizer - Speech-To-Text - Settings
The STT settings can be chosen from a pre-filled dropdown for Microsoft Azure, AWS and Google.
| Parameter | Type | Description |
|---|---|---|
| STT Vendor | Dropdown | Select the desired STT Vendor |
| STT Language | Dropdown | Defines the language that should be recognized |
| STT Hints | Text | Array of words or phrases to assist speech detection. Note: This requires support from the STT engine |
| Disable STT Punctuation | Toggle | Prevents the STT response from the bot to include punctuation marks |