Menu
Use the menu node to prompt the caller to select from a list of options. The menu node supports touch tone (DTMF) and spoken input (ASR).
Node
Give the node a name.
Language
Specify the ASR language.
For multilingual support, use a different menu node for each required language.
Grammar Conditions
Specify the menu options for DTMF, spoken input, and the goto node. The call is routed according to the selected menu item.
The caller selects 1 or says the word sales to route the call to the node called salesNode. The caller selects 2 or says the word support to route the call to the node called supportNode. The caller selects 3 or says the word address to route the call to the node called addressNode.
|
DTMF |
Grammar |
Goto Node |
|---|---|---|
|
1 |
Sales |
salesNode |
|
2 |
Support |
supportNode |
|
3 |
Address |
addressNode |
The spoken input can be expanded to include words that you are expecting the caller to say. For example, to accept yes, yep, and yeah as valid responses to the same DTMF option, enter as grammar values yes || yep || yeah. A double pipe character || separates the voice inputs.
If voice input is disabled, the grammar input fields can be left blank.
Ensure the grammar matches the specified language. The grammar input field supports UTF-8.
The number of menu items should not exceed 7 as a best practice although the menu node does not impose physical limits on the number of menu items.
Text to Speech
Specify each of the prompts to play to the caller.
The Add Pause, Volume, Pitch, Emphasis, Say As, and Rate menus above the TTS prompt apply SSML parameters. See Speech Synthesis Markup Language (SSML).
|
Prompt |
Description |
|---|---|
|
Prompt |
The caller hears this prompt first. The prompt tells the caller what to do. Example:
Press 1 or say sales for sales inquiries. Press 2 or say support for support. Press 3 or say address for our address and contact details. |
|
Fallback Prompt |
The caller hears the fallback prompt when the system fails to hear the caller's response, or the caller's response is not understood. Typically, the fallback prompt repeats the menu options or provides greater context on the menu. |
|
No Input Prompt |
The caller hears the no input prompt, followed by the fallback prompt, when the caller does not respond to the prompt. |
|
No Match Prompt |
The caller hears the no match prompt, followed by the fallback prompt, when the caller's response to the prompt is not understood. Studio uses natural language so no match indicates a high transcription confidence level. |
Speech Recognizer
|
Field |
Description |
|---|---|
| Speech Controls |
Select whether the caller is allowed to Barge In. Barge In enables the caller to interrupt the system and progress to the next prompt. It enables experienced callers to move rapidly through the system to get to the information that they want. You may want to disable barge in at key times, such as when your prompts or menu systems change. Select Disable Voice Input to turn off grammar detection and allow only DTMF inputs. |
| Confidence Level |
Represents the system's confidence when interpreting caller input. A higher confidence level requires a higher accuracy in caller input. |
|
Inter-Digit Timeout (Seconds) |
Select the time in seconds to wait between each DTMF key press. The longer the timeout, the greater the allowable time between each key press. When the timeout is reached, Studio finalizes the collected DTMF input so far and moves on to the next node in the call flow. |
|
No Input Timeout |
Shortens or lengthens the time in milliseconds the system waits for the caller to speak before directing the call to the No Input Event Handler. |
Event Handler
The event handler routes the call to a task canvas. If the canvas has not been created yet, type the name of the canvas. Each event handler has a count value specifying the number of attempts to run before triggering the event handler.
|
Event Handler |
Description |
|---|---|
| No Input Event Handler | Select a task canvas. The call is routed to the canvas if no input is detected from the caller after multiple attempts. |
| No Match Event Handler | Select a task canvas. The call is routed to the canvas if no match is detected from the caller after multiple attempts. |
Confirmation
Use the confirmation tab to prompt the caller to confirm their response.
|
Condition |
Description |
|---|---|
|
Not Required |
The caller does not confirm their response. This is the default behavior. |
|
Required |
The caller is required to confirm their response. |
|
Speech Recognizer Confidence |
The caller is required to confirm their response if it falls bellow the speech recognizer confidence threshold. The confidence level is representative of the system's confidence when interpreting the caller's response. Raise the Confidence Level to require a higher level of accuracy from the caller. |
Configure these settings for the case where the caller confirms their response.
|
Settings |
Description |
|---|---|
|
Barge In |
Select the box to enable Barge In. Barge In enables the caller to confirm their response before the confirmation prompt has finished playing. It enables the caller to move rapidly through the call flow. The caller may miss the confirmation prompt repeating their response. |
|
Confirmation Prompt |
The caller hears the confirmation prompt. Include [user_input] to play the response the prompt is confirming. If there are multiple response values, [user_input] captures the first value. Example:
You entered: [user_input]. Say Yes or press 1 if this is correct. Otherwise say No or press 2. |
|
No Input Prompt |
The caller hears the no input prompt when the caller does not confirm. |
|
No Match Prompt |
The caller hears the no match prompt when the caller's confirmation response is not understood. |
|
Maximum Number of Attempts to Confirm |
After the maximum number of attempts to confirm the response the call flows to the No Match Event Handler. |