You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
<sup>1</sup> The neural voice is available in public preview. Voices and styles in public preview are only available in three service [regions](../../regions.md): East US, West Europe, and Southeast Asia.
@@ -54,4 +54,3 @@ ms.author: eur
54
54
55
55
<sup>4</sup> The `sports-commentary-excited` style for this voice is in preview and only available in three service regions: East US, West Europe, and Southeast Asia.
56
56
57
-
<sup>5</sup> The voice supports style degree for you to specify the intensity of the speaking style.
Copy file name to clipboardExpand all lines: articles/cognitive-services/Speech-Service/language-support.md
+3-3Lines changed: 3 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -56,9 +56,9 @@ Additional remarks for Text to speech locales are included in the [Voice styles
56
56
57
57
### Voice styles and roles
58
58
59
-
In some cases, you can adjust the speaking style to express different emotions like cheerfulness, empathy, and calm. You can optimize the voice for different scenarios like customer service, newscast, and voice assistant. With roles, the same voice can act as a different age and gender.
59
+
In some cases, you can adjust the speaking style to express different emotions like cheerfulness, empathy, and calm. All prebuilt voices with speaking styles and multi-style custom voices support style degree adjustment. You can optimize the voice for different scenarios like customer service, newscast, and voice assistant. With roles, the same voice can act as a different age and gender.
60
60
61
-
To learn how you can configure and adjust neural voice styles and roles, see [Speech Synthesis Markup Language](speech-synthesis-markup-voice.md#speaking-styles-and-roles).
61
+
To learn how you can configure and adjust neural voice styles and roles, see [Speech Synthesis Markup Language](speech-synthesis-markup-voice.md#speaking-styles-and-roles).
62
62
63
63
Use the following table to determine supported styles and roles for each neural voice.
64
64
@@ -80,7 +80,7 @@ Please note that the following neural voices are retired.
80
80
81
81
### Custom Neural Voice
82
82
83
-
Custom Neural Voice lets you create synthetic voices that are rich in speaking styles. You can create a unique brand voice in multiple languages and styles by using a small set of recording data. There are two Custom Neural Voice (CNV) project types: CNV Pro and CNV Lite (preview).
83
+
Custom Neural Voice lets you create synthetic voices that are rich in speaking styles. You can create a unique brand voice in multiple languages and styles by using a small set of recording data. Multi-style custom neural voices support style degree adjustment. There are two Custom Neural Voice (CNV) project types: CNV Pro and CNV Lite (preview).
84
84
85
85
Select the right locale that matches your training data to train a custom neural voice model. For example, if the recording data is spoken in English with a British accent, select `en-GB`.
Copy file name to clipboardExpand all lines: articles/cognitive-services/Speech-Service/speech-synthesis-markup-voice.md
+3-3Lines changed: 3 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -206,16 +206,16 @@ This SSML snippet illustrates how the `role` attribute is used to change the rol
206
206
207
207
Your custom neural voice can be trained to speak with some preset styles such as cheerful, sad, and whispering. You can also [train a custom neural voice](how-to-custom-voice-create-voice.md?tabs=multistyle#train-your-custom-neural-voice-model) to speak in a custom style as determined by your training data. To use your custom neural voice style in SSML, specify the style name that you previously entered in Speech Studio.
208
208
209
-
This example uses a custom voice named "my-custom-voice". The custom voice speaks with the "cheerful" preset style, and then with a custom style named "my-custom-style".
209
+
This example uses a custom voice named "my-custom-voice". The custom voice speaks with the "cheerful" preset style and style degree of "2", and then with a custom style named "my-custom-style" and style degree of "0.01".
0 commit comments