Specify speech recognition settings

You can specify default settings for the flow’s speech recognition behavior. You can edit these configuration settings for specific menus, but you may find it helpful to set up primary settings for most configurations. You can also select to enable or disable company directory speech recognition.

The Company Directory speech recognition setting enables the company directory for the entire flow or the starting task or menu only, or disables it for the entire flow. 


By default, company directory speech recognition is enabled for new flows. When enabled, callers are prompted to say the name of the person they want to reach. Architect does not provide automatic prompts for use when this feature is enabled--you must include instructions for the user in your recorded prompts.

To keep both options selected and direct the system to ask callers to say the name of the person or department they wish to transfer to, modify the main greeting prompt to include this option for the caller. You can re-record the prompt in the main menu’s Initial Greeting area. If your prompts are professionally recorded, obtain an updated recording from the recording company and upload it.

Specify speech recognition settings

  1. From the Architect home page, click or hover over the Flows menu and select the desired flow type.
  2. Click the flow you want to open. The flow’s configuration page opens.
  3. Under Settings, click Speech Recognition.
  4. To allow callers to verbally indicate their selection in this flow, under General Speech Settings select the Enable speech recognition for the entire flow check box.
  5. To use the company directory’s speech directory catalog in this call flow, under Company Directory select Enable for entire flow or Enable for starting task or menu only.
  6. Under Default Flow-Level Speech Settings, select the preferred confidence and timeout levels:
    1. To select the scoring percentage the phrase must receive to achieve a successful match, use the up and down arrows in the Minimum confidence level area and choose a percentage between 1 and 100.
    2. To select the maximum time in seconds to wait after caller provides a valid speech input and stops talking before the system presents a positive match, in the Complete match timeout area, select the desired time (in seconds). The minimum time is 0.1 and the maximum is 20.
    3. To select the length of time to wait after caller stops talking and when the verbal selection is invalid before the system indicates no match is found, in the Incomplete match timeout area, use the up and down arrows to select a time (in seconds). The minimum time is 0.1 and the maximum is 40.
    4. To select the length of time allotted to the caller to make his or her verbal selection before the system times out and either prompts the caller to make a selection or disconnects the call, in the Maximum speech length area use the up and down arrows to select an amount of time (in seconds).
  7. Click Save.