Speech-to-text

Use this block to convert customer speech into text and save it to a variable. The default variable is {{asr_input}}.

To configure the speech-to-text service, do the following:

1. Connect the block via the Fail and Success ports.
2. Double-click the Speech-to-text block.
3. Select a variable from the Create a variable drop-down list, or enter a new one and press Enter.
4. Configure the maximum duration of a message for speech recognition in the Max message duration field.

5. In the Remain silent to finish field, specify how long a customer can remain silent after answering before the scenario moves on to the next block.

6. Select the language from the Recognition language field.
7. Enable the Background noise switch to play background sounds to fill in the gaps between the robot’s phrases. Select an audio recording from the drop-down list or upload a media file from your PC.

8. Click Save.