Loading
Salesforce now sends email only from verified domains. Read More
Agentforce Contact Center
Table of Contents
Select Filters

          No results
          No results
          Here are some search tips

          Check the spelling of your keywords.
          Use more general search terms.
          Select fewer filters to broaden your search.

          Search all of Salesforce Help
          Voice Control Options

          Voice Control Options

          Manipulate how text is spoken using Speech Synthesis Markup Language (SSML) tags and text normalization. This helps you configure prompts that align with brand tone and clarity, while accommodating multilingual and regulated enterprise scenarios.

          Required Editions

          View supported editions.

          This article applies to:

          Salesforce Voice (Native Telephony)

          Supported SSML tags are <break> and <phoneme>. Here is syntax and examples for these tags:

          <break>
          inserts a pause between words or sentences. Specify the length of the pause using the time attribute. For example, <break time="0.5s"/>. The time duration is in seconds and you can enter a maximum duration of 3 seconds. For example, Thank you for calling. <break time="1s"/> Please stay on the line.
          <phoneme>
          customizes pronunciation using a phonetic alphabet like the Carnegie Mellon University (CMU) Pronouncing Dictionary and the International Phonetic Alphabet (IPA). We recommend using the CMU alphabet for consistent and predictable results with more reliable performance.
          Feature / SSML Tag English Non-English Language Notes
          SSML Tag: <break> Yes Yes Accepts fraction.
          SSML Tag: <phoneme> Yes No Supports CMU/IPA
          Text Normalization Yes Yes Dates, numbers currency, acronyms

          Phoneme tags only work for individual words. For example, if you have a first and last name that you want to be pronounced a certain way, you must create a phoneme tag for each word. An example in the CMU Alphabet is <phoneme alphabet="cmu-arpabet" ph="M AE1 D IH0 S AH0 N"> Madison </phoneme>

          The prompt also supports text normalization that converts raw input text into a more natural, spoken form before it's rendered by the TTS engine. Here are some examples of how text to speech is rendered with normalization.

          Input With Text Normalization
          €99 Ninety nine euros
          12/08/2025 Twelfth of august two thousand and twenty five
          www.example.com/link/to/resource Double double double dot example dot com slash link slash to slash resource
          3.14 Three point one four
          5 kg Five Kilo Gram
          15th Jan Fifteenth of January
          12:00 PM Twelve PM
           
          Loading
          Salesforce Help | Article