Azure's TTS service stands out due to its support for SSML, enabling precise customization of voice outputs. Key features include:
Voice Selection
enables you to find the ideal voice that best represents your bot's identity and connects with your target audience.
The expressiveness of the voices can vary based on their age. Check out the documentation to identify which voices are the newest to find the best voice in your language. Do not shy away from trying a multilingual voice from a different language, and through the lang tag in the SSML template.
Language Adaptability
Whether your project requires different voices for various languages or a single voice capable of handling multiple languages, Azure provides the versatility needed. Additionally, various dialects per language allow for even more precise customization to match your audience's linguistic and cultural nuances.
Prosodic Controls
Enhance the delivery of your voice outputs by adjusting parameters such as speech , , and . This allows for the expression of emotions or the emphasis of certain message parts.
Latency
Very low, typically between 200â300 ms, providing quick response times during conversations.
Parloa offers an advanced voice latency reduction strategy for these voices by utilizing multiple processing regions per geography (not applicable to preview voices).
Availability & Pricing
Available to all users and included in standard pricing.
Processing Regions
Regional processing is available in both the US and the EU. The service does not retain any traces of inputs or outputs.
Integrating Azure TTS
Azure is set as the default TTS provider within Parloa, making it ready for immediate use in your projects when creating or editing a release.
Custom Voice
You can create your own voice with Azure as a Custom Neural Voice and integrate it into the Parloa project. Contact your Parloa representative for more details.
For comprehensive guidance on leveraging Azure's SSML for your project, please refer to our .
