Delay en Speech to text and Text to speech

I’m developing a voice-based virtual assistant. I’m using Microsoft Azure Speech Service as a Text to Speech Engine, but it has a delay of several seconds in responding to a user’s response.
In an audio call, is this delay normal?

Thanks.

Hello Eugenia,

Thank you for reaching out to Kore.ai Community.

Please some delay can be expected when using third-party Text to Speech (TTS) services, like Microsoft Azure Speech Service, due to factors such as network latency, processing time, and the complexity of the audio being generated.

However, a delay of several seconds is on the higher side and may not be ideal for a smooth user experience in a voice-based virtual assistant.

May i request you to please verify and confirm the duration of the delay observed in your use case ?

Thank you,
Srujan Madderla
Kore.ai Community Team

Hello,
thanks for your reply.
I am sending an example image of the delay we have.