Swara voice
The voice Swara is available in the Azure Text-to-Speech service for the Hindi language.
How to use Swara voice in your videos
To use Swara voice in your videos, you can use the following JSON2Video code:
{
"type": "voice",
"model": "azure",
"voice": "hi-IN-SwaraNeural",
"text": "рдмрд╕рдВрдд рдХреЗ рдореМрд╕рдо рдореЗрдВ, рдмрдЧреАрдЪрд╛ рд░рдВрдЧреАрди рдлреВрд▓реЛрдВ рдФрд░ рдЧрд╛рддреЗ рд╣реБрдП рдкрдХреНрд╖рд┐рдпреЛрдВ рд╕реЗ рдЬрд╛рдЧреГрдд рд╣реЛ рдЬрд╛рддрд╛ рд╣реИред рдкреБрд░рд╛рдиреЗ рдмрд░рдЧрдж рдХрд╛ рдкреЗрдбрд╝ рдЖрдиреЗ рд╡рд╛рд▓реЛрдВ рдХреЗ рд▓рд┐рдП рдЫрд╛рдпрд╛ рдкреНрд░рджрд╛рди рдХрд░рддрд╛ рд╣реИ, рдЬрдмрдХрд┐ рддрд┐рддрд▓рд┐рдпрд╛рдВ рдЧреБрд▓рд╛рдмреЛрдВ рдХреЗ рдмреАрдЪ рдиреГрддреНрдп рдХрд░рддреА рд╣реИрдВред рдПрдХ рдЫреЛрдЯрд╛ рдлрд╡реНрд╡рд╛рд░рд╛ рд╢рд╛рдВрдд рдзреНрд╡рдирд┐рдпрд╛рдВ рдЙрддреНрдкрдиреНрди рдХрд░рддрд╛ рд╣реИ, рдЗрд╕реЗ рдЖрд░рд╛рдо рдХрд░рдиреЗ рдФрд░ рдкреНрд░рд╛рдХреГрддрд┐рдХ рд╕реМрдВрджрд░реНрдп рдХрд╛ рдЖрдирдВрдж рд▓реЗрдиреЗ рдХреЗ рд▓рд┐рдП рд╕рд╣реА рдЬрдЧрд╣ рдмрдирд╛рддрд╛ рд╣реИред"
}
Swara 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": "hi-IN-SwaraNeural",
"text": "<speak>Hello, <break time="500ms"/> how are you today? <emphasis level="strong">This is important!</emphasis></speak>"
}
Swara supports different voice styles
As part of SSML, you can use the style tags to change the voice style.
Swara supports these styles:
cheerful
empathetic
newscast
{
"type": "voice",
"voice": "hi-IN-SwaraNeural",
"text": "<whispering>I have a secret for you</whispering>"
}
Swara 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