SSML text to speech
Direct the delivery of synthesized speech with standard SSML markup.
- Standard SSML tags for prosody, breaks, emphasis
- Control rate, pitch, and volume
- Insert precise pauses
- Works across the voice catalog
definition
SSML (Speech Synthesis Markup Language) is a standard XML markup that tells a text-to-speech engine how to speak. Rather than accepting a flat default read, you wrap text in tags that control pacing, pitch, pauses, and emphasis, directing the delivery word by word.
what-you-control
Prosody tags set speaking rate, pitch, and volume. Break tags insert pauses of a chosen length, which matter between paragraphs, list items, and scenes. Emphasis tags stress the words that carry meaning. Together they replace a monotone with speech that has rhythm.
where-it-matters
SSML is the difference between usable and cheap-sounding audio in long-form work. Audiobooks need paragraph pauses, e-learning needs measured pacing, and ads need punch on the key line. All of it comes from the same markup.
compatibility
SSML applies across the voice catalog, so the same markup shapes delivery no matter which voice you pick. See the SSML guide for the supported tag set.
Frequently asked questions
What is SSML in text-to-speech?
What can I control with SSML?
Does SSML work with any voice?
Start building
Direct the delivery of synthesized speech with standard SSML markup.