Create Amazon Speech Engine

Creates a speech engine using Amazon Poly and Transcribe speech recognition and synthesis service from a specific language and voice.

Starting from IBM RPA 23.0.3, this command is removed from the product. For more information, see Removed.

Important:As a result from the command's removal on IBM RPA 23.0.3, it no longer works on newer IBM RPA client versions.

Command availability: IBM RPA SaaS and IBM RPA on premises

Script syntax

IBM RPA's proprietary script language has a syntax similar to other programming languages. The script syntax defines the command's syntax in the script file. You can work with this syntax in IBM RPA Studio's Script mode.

amazonEngine --culture(Culture) --voice(String) (SpeechEngine)=value

Input parameter

The following table displays the list of input parameters available in this command. In the table, you can see the parameter name when working in IBM RPA Studio's Script mode and its Designer mode equivalent label.

Designer mode label Script mode name Required Accepted variable types Description
Culture culture Required Culture Language that the text is written in.
Voice voice Required Text The voice to synthesize the speech in the chosen language.

Use the voice compatible with the language selected in Culture parameter.

Output parameter

Designer mode label Script mode name Accepted variable types Description
Speech Engine value Speech Engine Returns a speech engine configured with the language and the voice to synthesize the text.


The following code example demonstrates the digital assistant asking a question to the user using the Amazon speech engine. The Create Amazon Speech Engine (amazonEngine) command uses the English (United States) language and Joanna's voice to synthesize the speech.

defVar --name speechEngine --type SpeechEngine
defVar --name language --type Language
defVar --name userAnswer --type String
// Create the Amazon speech engine with the English (United States) language and the Joanna's voice.
amazonEngine --culture "en-US" --voice Joanna speechEngine=value
// Create the digital assistant language. This language contains the writing system, the calendar used, the order of classification of the strings, and the formatting of dates and numbers for a culture-specific.
createLanguage --culture "en-US" --speech ${speechEngine} language=value
// Start the digital assistant engine.
botConnect --type "Ivr" --language ${language} --autoanswer  --timeout "00:01:00"
	// Ask a question to the user.
	botAsk --recognitionTimeout 00:00:05 --speechCompleteTimeout 00:00:10 --noInputTimeout 00:00:15 --speechIncompleteTimeout 00:00:05 --beep  --language ${language} --text "Welcome to IBM. How can I help you?" --timeout "00:02:00" userAnswer=value
// Ends the digital assistant engine.
Note:When you run this command using IVR type, you get prompted by a window to call the IVR. This window might show a phone number or the Zoiper QR code to calls via the Zoiper application. You see this window in debug mode in the IBM RPA Studio.

Starting from IBM RPA 23.0.3, this window isn't available due to the IVR removal. For more information, see Removed.


Although the Amazon speech engine supports different languages, IBM Robotic Process Automation only supports English (United States), Portuguese (Portugal), and Portuguese (Brazil) for commands that extract intentions from the sentences. This includes every command in the Ask section, as well as the Bot Says command.