Creating a text-to-speech audio asset in Zoom Contact Center

Admins can create or update audio assets in Zoom Contact Center using text-to-speech (TTS), which converts written text into natural-sounding speech. This eliminates the need for manual recordings, making it easier to update IVR menus, system messages, and automated responses. Admins can also select a voice from the TTS voice list to match their preferred tone and style.

In addition to creating TTS audio assets, admins can also configure TTS directly within flows using the Send Media and Collect Input widgets. Zoom Contact Center supports Speech Synthesis Markup Language (SSML) for TTS prompts, allowing for more control over speech patterns, pauses, pronunciation, and emphasis.

Requirements for creating a text-to-speech audio asset in Zoom Contact Center

Pro, Business, or Education account

Account owner or admin privileges; or relevant role/privilege

Zoom Contact Center license

Assets added to the asset library must 2MB or lower.
Note: To increase this maximum to 10MB, submit a request to Zoom Support.

How to create a text-to-speech audio asset

In the navigation menu, click Contact Center Management then Asset Library.

Click Add Asset.

Specify the following:

Name: Enter an internal display name for the asset.
Description (Optional): Enter an internal description for the asset.

Select the Audio asset type.
Note: To edit an existing asset, locate a text-to-speech audio asset, click the ellipses icon

in the last column, then click Edit.

(Optional) Select a category for your audio asset.

Enter a filename.

Select the language of the file.

Click the Text to speech tab.

Specify the following:

Select a voice: Select a language and voice from the text-to-speech engine's voice list.
Message to Play: Enter text to convert to speech. Click the variable icon to insert global variables in assets within the assets library. These variables allow for personalized consumer experiences by dynamically adjusting based on context or information in prompts and messages. Click Play to play the audio.

Click Save.
If you're updating an asset that's already in use, you will see a pop-up notification that lists where the asset is used.

Click Save to confirm the update.

Text-to-speech voice list

Language Code	Language Name	Voices
ca-ES	Catalan (Spain)	Arlet
yue-CN	Chinese Cantonese	Hiujin
cmn-CN	Chinese Mandarin	Zhiyu
da-DK	Danish (Denmark)	Naja Sofie Mads
nl-NL	Dutch (Netherlands)	Laura Ruben Lotte
en-US	English (US)	Joanna Stephen Kimberly Matthew Danielle Gregory Kevin Salli Kendra Justin Joey Ivy Ruth
en-GB	English (UK)	Emma Brian Amy Arthur
en-AU	English (Australia)	Olivia Russell Nicole
en-NZ	English (New Zealand)	Aria
fr-FR	French (France)	Celine Lea Remi Mathieu
fr-CA	French (Canada)	Gabrielle Liam Chantal
de-DE	German (Germany)	Daniel Vicki Marlene Hans
it-IT	Italian (Italy)	Adriano Bianca Giorgio Carla
ja-JP	Japanese (Japan)	Takumi Kazuha Tomoko Mizuki
ko-KR	Korean (Korea)	Seoyeon
pl-PL	Polish (Poland)	Ola Maja Jan Jacek Ewa
pt-PT	Portuguese (Portugal)	Ines Cristiano
pt-BR	Portuguese (Brazil)	Camila Thiago Vitoria Ricardo
ro-RO	Romanian (Romania)	Carmen
ru-RU	Russian (Russia)	Maxim Tatyana
es-US	Spanish (US)	Lupe Pedro Penelope Miguel
es-MX	Spanish (Mexico)	Mia Andres
es-ES	Spanish (European)	Lucia Sergio Enrique Conchita
sv-SE	Swedish (Sweden	Elin Astrid
tr-TR	Turkish (Turkey)	Filiz Burcu

Creating a text-to-speech audio asset in Zoom Contact Center

Requirements for creating a text-to-speech audio asset in Zoom Contact Center

Table of Contents

How to create a text-to-speech audio asset

Text-to-speech voice list