Set up an audio sequence

AI-generated summary

Genesys Cloud provides comprehensive audio sequence management through Architect's Sequence Builder and Custom Expression Builder interfaces, enabling users to create ordered sequences combining Text-to-Speech (TTS), pre-recorded prompts, data playback from variables, and customizable blank audio segments. Users can construct sequences using either a visual card-based interface with drag-and-drop functionality or a text-based expression builder for complex implementations. The Edit Audio Sequence dialog box allows configuration of ordered audio elements to play to callers, with Sequence Builder as the default interface and the option to switch to Custom Expression Builder via the Sequence Options menu. Key operational capabilities include rearranging sequence cards through click-and-hold or keyboard navigation using the Tab key with Alt/Option and arrow keys, deleting cards using the trash icon or Delete key, and adding multiple audio element types. TTS functionality converts typed words or phrases into speech output, while the Add Prompt feature enables selection of pre-recorded prompts from a dropdown list or creation of new prompts through the Create Prompt dialog. The platform supports flexible audio element arrangement through keyboard shortcuts for efficient navigation, language-specific accommodations for grammatical gender systems, and expression-based operations for specific audio playback requirements. Custom and preset variables—including caller zip code, ANI, DNIS, and time zone—can be analyzed and played back to callers using the Add Data function, with playback format options varying by variable type. For example, Call.ANI can be formatted as a phone number using ToAudioPhoneNumber, and recorded prompts can be converted to audio using expressions like ToAudio(Prompt.Greeting). Blank audio segments can be inserted to create pauses in sequences, with duration specified in milliseconds or seconds through the ToAudioBlank function. The expression editor provides Function and Operator help tools to assist users in configuring complex audio sequences and integrating multiple audio elements within a single sequence. Both Sequence Builder and Expression Builder interfaces provide equivalent functionality for audio sequence operations, supporting language-specific grammatical gender systems that allow configuration of gender-specific content parameters for text-to-speech playback at runtime.

In the Edit Audio Sequence dialog box, you can set up an ordered sequence of audio elements to play to the caller. You can build simple audio sequences in Architect’s Sequence Builder, or you can create more complex sequences using expressions in the Custom Expression Builder.

By default, Architect opens the Edit Audio Sequence dialog box in Sequence Builder. To switch to Custom Expression Builder, click the Sequence Options menu in the upper right corner and select the Switch to custom expression link.

Note: These steps assume you are building the audio sequence in Sequence Builder, but provide examples of how the same string looks like if you add the audio in Expression Builder.

The following video describes how to build an audio sequence.

Note: Ongoing innovation may cause your interface to appear differently.

How to use the builder

The following common operations are available in Architect builders that support multiple data types:

To build an expression value using a sequence of items of specific data types, click and configure the desired data types. Architect displays the added items as card elements within the sequence.
To rearrange the sequence of cards, click and hold the card that you want to move up or down in the list. Alternatively, use the Tab key to move through the list of cards and select the card that you want to move. To move the card to the desired position within the list, select Alt or Option and use the up and down arrow keys.
To delete a card, click the trash icon for the card that you want to delete. Alternatively, use the Tab key to move through the list of cards and select the card that you want to delete. Then, use the Delete key to delete the card.

Add text to speech to the audio sequenceClick to expand

Use TTS, or text to speech, to type words or phrases that Architect will convert to speech and read back to the caller.

Click Add TTS. Architect displays a Text To Speech field.
Enter the word or phrase you want Architect to covert to audio for the caller.
Optionally add another TTS, prompt, or data element to the sequence.

Example:

In Sequence Builder, type: Thank you for calling.
In Expression Builder, type: ToAudioTTS(“Thank you for calling.”)

Add a prompt to the audio sequenceClick to expand

Select a pre-recorded prompt, or add one from the dialog box. Adding one on the fly opens the Edit Prompt dialog.

Click Add Prompt. Architect displays a Prompt field.
Select the desired prompt from the drop-down list.

Note: To record or upload a new prompt, click the + button. The Create Prompt dialog box opens. For more information on recording prompts, see the Suggested content.

Example:

In Sequence Builder, select: Prompt.Greeting from the drop-down list.
In Expression Builder, type: ToAudio(Prompt.Greeting)

Add data to the audio sequenceClick to expand

You can choose to direct Architect to analyze custom variables that you create, for example the caller’s zip code or what time the call entered the flow; or preset variables such as the caller’s ANI, DNIS, and time zone.

Click Add Data. Architect displays a Data field.
Click the arrow at the end of the Select variable drop-down list and select the appropriate attribute.
Click the arrow at the end of the Select Options drop-down list and choose how to play the attribute details back to the caller.

Note: The options available here change, depending on the variable you select.

Example:

In Sequence Builder, from the Select variable drop-down list select Call.ANI. From the Options drop-down list select As phone number.
In Expression Builder, type: ToAudioPhoneNumber(Call.ANI)

Add blank audio to the sequenceClick to expand

You can add blank audio to create a pause in the audio sequence.

Click the arrow at the end of the Other drop-down list and choose Add Blank Audio.
Click the arrow at the end of the Blank drop-down list and select the appropriate length of the blank audio, in milliseconds or seconds.

Example:

In Sequence Builder, from the Blank drop-down list select 3 seconds.
In Expression Builder, type: ToAudioBlank(3000)

Add an expression to the audio sequenceClick to expand

You can add an expression to an audio sequence to perform certain operations, such as read information back to a caller.

Click the arrow at the end of the Other drop-down list and choose Add Expression.
In the Expression field, do one of the following:

Type the expression.
Click the Open large expression editor and in the Audio Expression dialog box use the Function and Operator help or other element tools to configure the full expression.

Example:

In Sequence Builder, in the Expression box type: ToAudioPhoneNumber(“812-555-1234”).
In Expression Builder, type: ToAudioPhoneNumber(“812-555-1234”).

Note: Some languages use a grammatical gender system that classifies nouns as being feminine, masculine, neuter, or common. In addition, other part of speech, such as articles, must also agree with the language gender. For information about configuring parameters that specify how TTS plays a supported language’s gender-specific content back to the caller at runtime, see the Suggested content.

[NEXT] Was this article helpful?

Get user feedback about articles.

Loading...

Set up an audio sequence

How to use the builder

[NEXT] Was this article helpful?