Overview

Webex Contact Center offers in-built Text-to-Speech (TTS) capability for customers. TTS automatically converts any written text into speech or synthesized audio to provide Interactive Voice Response (IVR) service to customers. TTS service includes a predefined set of neural voices and language options that you can configure in the IVR application to build call flows.

Note: Existing customers on the Webex Contact Center Next Generation Voice Media Platform (RTMS) can view both Cisco TTS and Google TTS connectors in the Prompt settings of IVR activities, such as Play Message, Menu, and Collect Digits in the Flow Designer. Refer to the Webex Contact Center Seup and Administration Guide for configuration details.

Supported languages and voices

Webex Contact Center supports 22 languages and 2 voices per language for Cisco TTS. The following table lists the languages and voices supported for Cisco TTS:

Locale

Language

Male Voice Name

Female Voice Name

de-CHGerman (Switzerland)de-CH-Luca

de-CH-Eva

*default

de-DEGerman (Germany)

de-DE-Jonas

*default

de-DE-Emma
en-GBEnglish (United Kingdom) en-GB-Colton

en-GB-Agnes

*default

en-IEEnglish (Ireland)en-IE-Liam

en-IE-Fiona

*default

en-INEnglish (India) en-IN-Veer

en-IN-Ananya

*default

en-USEnglish (United States) en-US-Daniel

en-US-Maria

*default

en-AUEnglish (Australia)en-AU-Chris

en-AU-Amelia

*default

es-ESSpanish (Spain)

es-ES-Pablo

*default

es-ES-Cristina
es-MXSpanish (Mexico)

es-MX-Arturo

*default

es-MX-Luna
es-USSpanish (United States)

es-US-Alonso

*default

es-US-Paloma
fil-PHFilipino (Philippines)fil-PH-Luis

fil-PH-Sofia

*default

fr-CAFrench (Canada)

fr-CA-Andre

*default

fr-CA-Lea
fr-FRFrench (France) fr-FR-Adrien

fr-FR-Ariane

*default

it-ITItalian (Italy)

it-IT-Nico

*default

it-IT-Alice
ja-JPJapanese (Japan)ja-JP-Haru

ja-JP-Aiko

*default

nl-NLDutch (Netherlands) nl-NL-Edwin

nl-NL-Adriana

*default

pl-PLPolish (Poland) pl-PL-Filip

pl-PL-Natalia

*default

pt-BRPortuguese (Brazil) pt-BR-Davi

pt-BR-Camila

*default

sv-SESwedish (Sweden)

sv-SE-Hugo

*default

sv-SE-Kristina
th-THThai (Thailand)

th-TH-Chaisai

*default

th-TH-Anong
vi-VNVietnamese (Vietnam) vi-VN-Tai

vi-VN-Linh

*default

zh-CNChinese (Mandarin, Simplified) zh-CN-Hong

zh-CN-Liu

*default


 

  • To use the default language and voice for Cisco Text-to-Speech, you must configure the global variables Global_VoiceName and Global_Language in the flow. For more information about how to add these global variables to the flow, see Global Variables.
  • To override the default language and voice for Cisco Text-to-Speech, configure the Set Variable activity with the appropriate voice name code.

Supported Speech Synthesis Markup Language (SSML) tags

The following table lists the standard SSML tags that are supported for TTS voice.


 
The <speak> tag is the root element of all SSML text and is mandatory.

SSML Tag

Attributes

Description
<speak>

Identifies the SSML-enhanced text.

<break>
  • strength
  • time

Adds a pause in your message.

<say-as>
  • interpret-as
  • format
  • detail

Controls how special types of words are spoken.

<audio>src

Embeds short, pre-recorded audio within your message.

<p>

Adds a pause between paragraphs.

<s>

Adds a pause between sentences.

<prosody>
  • volume
  • rate
  • pitch

Controls the volume, speaking rate, and pitch of the voice.

  • volume: The volume level of the speaking voice. The volume tag must begin with a lowercase 'v'. The default value is medium (100 or 0 decibels).

  • rate: The speaking rate of the text. The default value is medium.

  • pitch: The baseline pitch for the text. The default value is 100.


 
The values for rate, pitch, and volume must adhere to the W3C recommendation for Speech Synthesis Markup Language (SSML) 1.0. For detailed information about the parameters and values, see https://www.w3.org/TR/2004/REC-speech-synthesis-20040907/.
<sub>alias

Pronounces acronyms and abbreviations