Azure TTS voices

Azure voices by language

What is Azure Text to Speech?

Microsoft's Azure Text to Speech is a service that converts text into natural-sounding speech. It's a powerful tool for creating voice-enabled applications, such as virtual assistants, chatbots, and more.

Azure Text to Speech is part of the Azure Cognitive Services, which includes a range of services for speech recognition, natural language processing, and more.

Azure Text to Speech is available in multiple languages and voices, each with its own unique characteristics and accents.

What languages are supported?

Azure Text to Speech supports 82 languages, including English, Spanish, French, German, Italian, Portuguese, Dutch, Russian, Chinese, Japanese, Korean, and more.

Check all supported voices by language for a complete list of languages supported by Azure Text to Speech.

Check all supported languages

How to use Azure Text to Speech?

JSON2Video API integrates with Azure Text to Speech to generate voiceovers and provide a wide range of voices and languages.

Basically, you can use the Voice element to generate voiceovers, set the model to azure and the voice to the ID of the voice you want to use.

For example, to use the Sara voice, you can use the following code:

{
    "type": "voice",
    "model": "azure",
    "voice": "en-US-SaraNeural",
    "text": "Hello, how are you?"
}

$scene->addElement([
'voice',
'azure',
'en-US-SaraNeural',
'Hello, how are you?'
]);

scene.addElement([
"voice",
"azure",
"en-US-SaraNeural",
"Hello, how are you?"
]);

Deep dive into how to use Azure Text to Speech with JSON2Video by reading the Voice elements tutorial.

How much does Azure Text to Speech cost?

Azure Text to Speech is a paid service by Microsoft Azure.

In JSON2Video, voiceovers with Microsoft voices are included in every plan. You create them inside JSON2Video, with the voice you want, without an Azure account or any extra cost.

Check the pricing page to learn more about the different JSON2Video plans and pricing for programmatic video generation.

How Microsoft voices compare to ElevenLabs voices?

Microsoft Text-to-Speech voices and ElevenLabs voices are both great tools for generating voiceovers. However, they have some differences that you should consider when choosing the right voice for your project.

Pros

• Microsoft Text-to-Speech voices support a wide range of languages and accents, much wider than ElevenLabs that in this aspect is quite limited. If you need a voice in a language that is not supported by ElevenLabs, you can use Microsoft voices.
• Microsoft voices support SSML, which allows you to customize the voice output with the tone, pitch, speed, pauses, emphasis, etc. ElevenLabs voices do not support SSML.

Cons

• Microsoft Text-to-Speech voices don't sound as natural as ElevenLabs voices. Best Microsoft voices sound like radio hosts, and those not that good may sound a bit robotic.

Conclusion

Microsoft Text-to-Speech voices is a great choice for generating voiceovers when language support or SSML customization is a priority.

JSON2Video API integrates natively with Microsoft Text-to-Speech voices, so you can use them in your videos without any additional cost.