Azure Realtime model isn't available
# support
a
Hi, I wanted to use the Azure Realtime model instead of OpenAI directly, as we have credits available with Azure. However, I don’t see an option to select the Realtime model after choosing Azure as the provider. Do you have an estimate on when this option will be available? Thanks,
c
Hi there, Thank you for your message. Our team is currently out of the office. We operate Monday through Friday, from 9:00 AM to 8:00 PM Pacific Standard Time (PST). We’ll get back to you as soon as possible during our normal business hours. If your message is urgent, please mark it accordingly or include “URGENT” in the subject line, and we’ll do our best to respond promptly. Warm regards, Vapi Customer Support Team
v
Currently, Azure OpenAI does not support Realtime models—only traditional models like
gpt-4o-2024-11-20
are available for selection.
There is no official estimate or timeline for when Realtime models will be supported via Azure. For updates, keep an eye on the [Azure OpenAI documentation](https://docs.vapi.ai/providers/model/azure-openai) or the Vapi changelog. Source: - [Azure OpenAI Documentation](https://docs.vapi.ai/providers/model/azure-openai)
l
This issue occurs because Vapi has not yet enabled support for Azure’s Realtime model, even if you select Azure as your provider and have available Azure credits. Currently, Vapi only supports standard Azure OpenAI model deployments, so the Realtime model doesn’t appear as an option in the dashboard. The best workaround for now is to continue using the regular Azure OpenAI endpoints or use OpenAI’s own Realtime API if you urgently need realtime functionality. Vapi has confirmed that Azure Realtime support is planned, but they have not provided a public timeline—so the only thing you can do is follow their updates or contact support@vapi.ai for an estimated release window.
@Amir76
c
Hey Amir, Vapi currently does not support Azure-hosted OpenAI Realtime models directly as a voice provider. You can integrate Azure OpenAI models by configuring them as "Custom LLM" within Vapi; however, this will not enable Realtime model capabilities. For Realtime capabilities, consider using OpenAI's native Realtime API until Azure support is expanded. Keep an eye on Vapi's changelogs for updates on feature releases and support expansion.