Vivienne: Text to Speech

Vivienne voice

The voice Vivienne is available in the Azure Text-to-Speech service for the French language.

How to use Vivienne voice in your videos

To use Vivienne voice in your videos, you can use the following JSON2Video code:

{
    "type": "voice",
    "model": "azure",
    "voice": "fr-FR-VivienneMultilingualNeural",
    "text": "Au printemps, le jardin s'anime de fleurs color\u00e9es et d'oiseaux qui chantent. Le vieux ch\u00eane offre de l'ombre aux visiteurs, alors que des papillons dansent parmi les roses. Une petite fontaine cr\u00e9e des sons paisibles, faisant de cet endroit l'endroit parfait pour se relaxer et profiter de la beaut\u00e9 de la nature."
}

$scene->addElement([
	'type' => 'voice',
	'model' => 'azure',
	'voice' => 'fr-FR-VivienneMultilingualNeural',
	'text' => 'Au printemps, le jardin s\'anime de fleurs colorées et d\'oiseaux qui chantent. Le vieux chêne offre de l\'ombre aux visiteurs, alors que des papillons dansent parmi les roses. Une petite fontaine crée des sons paisibles, faisant de cet endroit l\'endroit parfait pour se relaxer et profiter de la beauté de la nature.'
]);

scene.addElement({
	"type": "voice",
	"model": "azure",
	"voice": "fr-FR-VivienneMultilingualNeural",
	"text": "Au printemps, le jardin s'anime de fleurs colorées et d'oiseaux qui chantent. Le vieux chêne offre de l'ombre aux visiteurs, alors que des papillons dansent parmi les roses. Une petite fontaine crée des sons paisibles, faisant de cet endroit l'endroit parfait pour se relaxer et profiter de la beauté de la nature."
});

Vivienne supports SSML

SSML stands for Speech Synthesis Markup Language. It's a way to add instructions to your text so that a Text-To-Speech (TTS) system knows how to read it aloud.

You use SSML like HTML, but for controlling speech. It helps you adjust things like: Pronunciation, Pauses, Pitch and Volume, Emphasis, Speaking Rate.

{
    "type": "voice",
    "voice": "fr-FR-VivienneMultilingualNeural",
    "text": "<speak>Hello, <break time="500ms"/> how are you today? <emphasis level="strong">This is important!</emphasis></speak>"
}

$scene->addElement([
	'type' => 'voice',
	'voice' => 'fr-FR-VivienneMultilingualNeural',
	'text' => '<speak>Hello, <break time="500ms"/> how are you today? <emphasis level="strong">This is important!</emphasis></speak>'
]);

scene.addElement({
	"type": "voice",
	"voice": "fr-FR-VivienneMultilingualNeural",
	"text": "<speak>Hello, <break time="500ms"/> how are you today? <emphasis level="strong">This is important!</emphasis></speak>"
});

Vivienne is a neural voice

In Azure Cognitive Services, a Neural voice refers to a voice generated using neural network technology. This means the Text-To-Speech system uses advanced machine learning models to create more natural, human-like speech compared to traditional methods.

Key characteristics of Neural voices:

• More expressive and realistic
• Better at handling pitch, tone, and rhythm variations
• Sounds closer to how humans naturally speak

Vivienne is a multilingual voice

A Multilingual voice in Azure Cognitive Services refers to a voice that can speak in multiple languages or accents while maintaining a consistent speaking style.

Key points about Multilingual voices:

• The same voice can pronounce text in different languages accurately
• Useful for applications that switch between languages or need to handle multilingual content
• Maintains natural tone and consistency, even when switching languages