How can we decrease latency keeping intelligence?
# supportb
Blacky
07/19/2025, 10:46 AMHow can I lower the latency? Do you have strategies for calling in my language, Italian? I can use Flash 25, but it's not consistent with the Italian accent. Therefore, I need an AI to help maintain consistency in the voice because there are also some XML tasks.
https://cdn.discordapp.com/attachments/1396080825673711656/1396080825895747625/Screenshot_2025-07-18_at_12.18.10.png?ex=687cc916&is=687b7796&hm=8d0f2d13c64cd901c5d266029ed3d12c53e5dbf9e64a326cbc93ff7f70ef2a14&
c
Chiranjeet Mishra
07/19/2025, 6:13 PMHey Blacky,
I sincerely apologize for the delay in our responses this week. We experimented with some process adjustments that didn’t work as intended, and unfortunately, this caused some disruptions. That’s entirely my responsibility.
Just a quick note—our team is unavailable on weekends. However, if something urgent or critical comes up, feel free to reach out to me directly, and I’ll assist you.
The support issues will be resolved in the coming weeks, and starting Monday, you can expect more consistent and improved support. Thank you so much for your patience and for continuing to stick with us!
Chiranjeet Mishra
07/22/2025, 11:07 AMUse OpenAI GPT 4o-mini cluster or Groq llama3.1-8b-instant as the LLM and Azure for the voice. There is a workaround for the azure issue currently and I can guide you through it. By using the API tool in the documentation, you will be able to update your assistant to the azure voice of your choice. What you will need:
- Your VAPI API Key (Bearer token)
- The assistant ID you want to update
Once you gather that information, head to this page and enter those into the fields -->
Use the drop-downs to select Voice > AzureVoice > then select String for voiceId
Below is the string value for Isabella
Copy code
it-IT-IsabellaNeural2 Views