Yandex Cloud
Search
Contact UsGet started
  • Blog
  • Pricing
  • Documentation
  • All Services
  • System Status
    • Featured
    • Infrastructure & Network
    • Data Platform
    • Containers
    • Developer tools
    • Serverless
    • Security
    • Monitoring & Resources
    • ML & AI
    • Business tools
  • All Solutions
    • By industry
    • By use case
    • Economics and Pricing
    • Security
    • Technical Support
    • Customer Stories
    • Start testing with double trial credits
    • Cloud credits to scale your IT product
    • Gateway to Russia
    • Cloud for Startups
    • Education and Science
    • Yandex Cloud Partner program
  • Blog
  • Pricing
  • Documentation
© 2025 Direct Cursus Technology L.L.C.
Yandex SpeechKit
  • SpeechKit technology overview
    • About the technology
    • List of voices
      • Overview
      • TTS markup
      • SSML markup
      • List of TTS supported phonemes
      • List of SSML supported phonemes
  • Supported audio formats
  • IVR integration
  • Quotas and limits
  • Access management
  • Pricing policy

In this article:

  • Markup components
  • Mark the stress
  • Set a pause between sentences explicitly
  • Set a pause depending on the context
  • Place emphasis
  • Use phonetic pronunciation
  • Usage examples for Russian phonemes
  1. Speech synthesis
  2. Text markup
  3. TTS markup

TTS markup

Written by
Yandex Cloud
Updated at April 30, 2025
  • Markup components
    • Mark the stress
    • Set a pause between sentences explicitly
    • Set a pause depending on the context
    • Place emphasis
    • Use phonetic pronunciation
    • Usage examples for Russian phonemes

TTS markup grants the ability to control speech synthesis using special characters and SIL tags. This helps make synthesized speech more natural.

TTS markup is supported for Russian in the API v3 and API v1 for data in text format.

Pausing is available for testing in all languages the speech synthesis is supported for.

Note

SpeechKit is designed for natural speech synthesis. Marking up data for speech synthesis helps set up pronunciation of separate words, phrases, and sentences. However, it is not intended for generating separate sounds and silence.

The markup in the text will serve as a cue for synthesis, not as a direct instruction.

Markup componentsMarkup components

Description Special characters and tags
Mark the stress +
Set a pause between sentences explicitly sil<[t]>, where t is the pause duration in milliseconds.
Set a pause depending on the context <[small]>. Acceptable values: tiny, small, medium, large, and huge.
Place emphasis <[accented]> or **emphasized word**
Use phonetic pronunciation [[<word_phonemes_separated_by_spaces>]]

Warning

When using pattern-based synthesis, the markup outside the variable part is ignored.

Mark the stressMark the stress

Currently, this feature works only for Russian.

Use + before a stressed vowel any time you need to define the correct way to pronounce a word. Here is an example:

They signed the c+ontract the following day.

or

If you contr+act malaria, you will have to spend a long time in a hospital.

Set a pause between sentences explicitlySet a pause between sentences explicitly

To set a pause between sentences explicitly, you can add a special tag, sil<[t]>, where t is the pause duration in milliseconds:

Stop! sil<[300]> Think about it!

Note

Text to synthesize may not contain markup characters only. You cannot use SpeechKit to generate a file with silence instead of speech.

Pauses set at the beginning and end of a sentence will be ignored.

Set a pause depending on the contextSet a pause depending on the context

Use cue words to automatically select the duration of pauses.

Frost and sun; <[medium]> a wonderful day!

Place emphasisPlace emphasis

Currently, this feature works only for Russian.

To place emphasis on a word, you can prepend it with <[accented]>. Here is an example:

Convenient interfaces for your <[accented]> needs.

You can also use asterisks to place emphasis on one or more words (**word**). Here is an example:

We are **forever** responsible for what we have tamed.

Use phonetic pronunciationUse phonetic pronunciation

Tag text with [[ ]] to ensure proper pronunciation using phonemes. The following tagged text will be used for playback:

Hi! My name is [[v a sʲ ʌ]]

You can find the list of supported phonemes here.

Usage examples for Russian phonemesUsage examples for Russian phonemes

Example 1

Ishimbay is a city in Russia.

Всем привет! Я взял билеты на автобус в город [[i ʂ ɨ m b a j]] и буду там наслаждаться природой.

Example 2

Keremet is a Kazakh female name. Possible confusion: Keremet/keremyot.

Познакомься, это моя подруга [[kʲ ɪ rʲ ɪ mʲ ɛ t]]. Мы вместе учились в школе.

Example 3

Lena, a female name, used in the genitive plural case. Possible confusion: Len/lyon.

В моей семье очень много [[lʲ ɛ n]]. Это очень популярное имя у нас.

Example 4

Beret is a type of headwear. Possible confusion: beret/beryot.

Голубой [[bʲ ɪ rʲ ɛ t]]. Передай мне, пожалуйста, мой берет.

Was the article helpful?

Previous
Overview
Next
SSML markup
© 2025 Direct Cursus Technology L.L.C.