<express-as>

Adjusts the speaking style, style degree, and role at the sentence level.

<?xml version="1.0"?>
<speak version="1.0"
    xmlns:mstts="https://www.w3.org/2001/mstts"
    xml:lang="en-US">
    <voice name="en-US-JennyNeural">
        <mstts:express-as style="cheerful" styledegree="2">
            That'd be just amazing!
        </mstts:express-as>
        <mstts:express-as style="assistant" styledegree="0.01">
            What's next?
        </mstts:express-as>
    </voice>
</speak>

Attributes

style

The voice-specific speaking style that may be one of the following:

• advertisement_upbeat - Expresses an excited and high-energy tone for promoting a product or service.
• affectionate - Expresses a warm and affectionate tone, with higher pitch and vocal energy. The speaker is in a state of attracting the attention of the listener. The personality of the speaker is often endearing in nature.
• angry - Expresses an angry and annoyed tone.
• assistant - Expresses a warm and relaxed tone for digital assistants.
• calm - Expresses a cool, collected, and composed attitude when speaking. Tone, pitch, and prosody are more uniform compared to other types of speech.
• chat - Expresses a casual and relaxed tone.
• cheerful - Expresses a positive and happy tone.
• customerservice - Expresses a friendly and helpful tone for customer support.
• depressed - Expresses a melancholic and despondent tone with lower pitch and energy.
• disgruntled - Expresses a disdainful and complaining tone. Speech of this emotion displays displeasure and contempt.
• documentary-narration - Narrates documentaries in a relaxed, interested, and informative style suitable for dubbing documentaries, expert commentary, and similar content.
• embarrassed - Expresses an uncertain and hesitant tone when the speaker is feeling uncomfortable.
• empathetic - Expresses a sense of caring and understanding.
• envious - Expresses a tone of admiration when you desire something that someone else has.
• excited - Expresses an upbeat and hopeful tone. It sounds like something great is happening and the speaker is happy about it.
• fearful - Expresses a scared and nervous tone, with higher pitch, higher vocal energy, and faster rate. The speaker is in a state of tension and unease.
• friendly - Expresses a pleasant, inviting, and warm tone. It sounds sincere and caring.
• gentle - Expresses a mild, polite, and pleasant tone, with lower pitch and vocal energy.
• hopeful - Expresses a warm and yearning tone. It sounds like something good will happen to the speaker.
• lyrical - Expresses emotions in a melodic and sentimental way.
• narration-professional - Expresses a professional, objective tone for content reading.
• narration-relaxed - Expresses a soothing and melodious tone for content reading.
• newscast - Expresses a formal and professional tone for narrating news.
• newscast-casual - Expresses a versatile and casual tone for general news delivery.
• newscast-formal - Expresses a formal, confident, and authoritative tone for news delivery.
• poetry-reading - Expresses an emotional and rhythmic tone while reading a poem.
• sad - Expresses a sorrowful tone.
• serious - Expresses a strict and commanding tone. Speaker often sounds stiffer and much less relaxed with firm cadence.
• shouting - Expresses a tone that sounds as if the voice is distant or in another location and making an effort to be clearly heard.
• sports_commentary - Expresses a relaxed and interested tone for broadcasting a sports event.
• sports_commentary_excited - Expresses an intensive and energetic tone for broadcasting exciting moments in a sports event.
• whispering - Expresses a soft tone that's trying to make a quiet and gentle sound.
• terrified - Expresses a scared tone, with a faster pace and a shakier voice. It sounds like the speaker is in an unsteady and frantic status.
• unfriendly - Expresses a cold and indifferent tone.

styledegree

Optional. The intensity of the speaking style. Specify a stronger or softer style to make the speech more expressive or subdued. The range of accepted values are: 0.01 to 2 inclusive. The default value is 1 that indicates the predefined style intensity.

role

Optional. The speaking role to play that may be one of the following:

• Girl - The voice imitates a girl.
• Boy - The voice imitates a boy.
• YoungAdultFemale - The voice imitates a young adult female.
• YoungAdultMale - The voice imitates a young adult male.
• OlderAdultFemale - The voice imitates an older adult female.
• OlderAdultMale - The voice imitates an older adult male.
• SeniorFemale - The voice imitates a senior female.
• SeniorMale - The voice imitates a senior male.

Children

none

Parents

<emphasis>, <s>, and <voice>.

Source: Microsoft Azure Speech Synthesis Markup Language (SSML)