Skip to main content

Working With Voice Messages

Basic Tips for Writing Text-to-Speech

  • When translating numbers, '12345' is spoken as "twelve thousand three hundred forty five," whereas '1 2 3 4 5' is spoken as "one two three four five."
  • The speech engine interprets commas and periods as natural pauses.
  • To create longer pauses, combine punctuation (e.g., periods.)

Advanced Speech Synthesis Markup Language (SSML)

Action SSML Tag Attributes: Values
Adding a Pause <break> strength: none, weak, strong, x-strong

time: { {number} }s
Emphasizing words <emphasis> level: strong, moderate, reduced
Controlling Volume, Speaking Rate and Pitch <prosody> volume: default, silent, x-soft, soft, medium, loud, x-loud, +{ {number} }dB, -{ {number} }dB

rate: x-slow, slow, medium, fast, x-fast, { {number} }%

pitch: default, x-low, low, medium, high, x-high, +{ {number} }%, -{ {number} }%

SSML Usage

<{ {SSML Tag} } { {attribute} }="{ {value} }">Your text</{ {SSML Tag} }>

SSML Example

Hello { {First Name} },

<prosody rate="x-fast">This is just a</prosody> reminder that our
<emphasis level="moderate">Open House</emphasis> is this
<emphasis level="strong">Saturday</emphasis>

<break time="0.5s"></break>


  • Was this article helpful?