Azure TTS voices with Calm style

Compare Azure TTS voices with a calm style. Play each voice's own calm sample, check which locales offer it, and copy SSML for meditation and guided audio.

💡 Choosing a Calm Delivery

Listen for an even pace, gentle emphasis, and low listening fatigue without a flat or sleepy result. Test instructions, long sentences, and pauses to confirm the voice remains clear for explainers, wellness, or guided content.

Calm voices at a glance

Voices
9
Locales
2
HD models
0
Multilingual
0

Locales with this style

  • Chinese (Mandarin, Simplified) 8
  • Portuguese (Brazil) 1

Hear each voice's Calm sample

Every card plays that voice's own Calm recording from Azure, so you can compare the same style across voices before you write any SSML.

Portuguese (Brazil) · Female

pt-BR-FranciscaNeural

Chinese (Mandarin, Simplified) · Female

Also supports 19 other styles

zh-CN-XiaoxiaoNeural

Chinese (Mandarin, Simplified) · Male

Also supports 15 other styles

zh-CN-YunxiNeural

Chinese (Mandarin, Simplified) · Female

Also supports 9 other styles

zh-CN-XiaohanNeural

Chinese (Mandarin, Simplified) · Female

Also supports 19 other styles

zh-CN-XiaomoNeural

Chinese (Mandarin, Simplified) · Female

Also supports 3 other styles

zh-CN-XiaoruiNeural

Chinese (Mandarin, Simplified) · Male

Also supports 4 other styles

zh-CN-YunxiaNeural

Chinese (Mandarin, Simplified) · Male

Also supports 15 other styles

zh-CN-YunyeNeural

Chinese (Mandarin, Simplified) · Male

Also supports 10 other styles

zh-CN-YunzeNeural

SSML for the Calm style

Pick a voice to get SSML that applies Calm with mstts:express-as. The text is that voice's own preview sentence.

<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="https://www.w3.org/2001/mstts" xml:lang="pt-BR">
  <voice name="pt-BR-FranciscaNeural">
    <mstts:express-as style="calm">
      Desenvolver aplicativos e serviços que conversem naturalmente com os usuários, melhorando a acessibilidade e usabilidade.
    </mstts:express-as>
  </voice>
</speak>