LLM

Azure OpenAI LLM for Bolna AI voice agents

Azure OpenAI runs GPT models for your Bolna voice agent inside your own Azure account, for teams that need regional data residency and private networking.

Book a Demo Bolna Docs

llmazureenterpriseopenaigptcompliance

Official Documentation

At a glance

How Azure OpenAI fits in the stack

Best for

Reasoning, policy handling, tool use, and response generation.

Use this layer when

You want to tune quality, cost, latency, or function-calling behavior.

Connects to

Transcribed caller input upstream and voice or actions downstream.

Voice Stack

The LLM is the reasoning layer

This provider decides how the agent interprets intent, selects next actions, calls tools, and formulates responses. It is the decision engine inside the voice stack.

TelephonyPhone Network

→

STTListener

→

LLMReasoning

→

TTSVoice

→

ToolsActions

Last updated 11 October 2026

What is Azure OpenAI used for in a Bolna voice agent?

Azure OpenAI gives a Bolna voice agent the same OpenAI GPT models, served from your own Azure deployment, so you get regional data handling, private networking and Azure's enterprise compliance (SOC 2, HIPAA, ISO 27001). Pick it when your data must stay in a specific region or your organisation already runs on Azure; otherwise the direct OpenAI integration is simpler to set up.

How do I set up Azure OpenAI with Bolna?

In the Azure portal, create a deployment for the model you want, such as gpt-5.4-mini. Keep the model name in the deployment name.
Connect your Azure account at platform.bolna.ai/auth/azure with your API key, endpoint URL, API version and deployment name.
Open your agent in Agent Studio, go to the Intelligence tab and choose Azure as the provider with your deployment as the model.
Keep the token limit around 150 for short spoken replies. GPT-5 models need a temperature of 1.

The Azure OpenAI setup guide in the Bolna docs covers the API config, reasoning effort and custom deployment names.

Which models does Bolna support with Azure OpenAI?

Model	Context	Best for on Bolna	On the flat rate
`gpt-5.4-mini`	400K tokens	Most voice agents. Recommended for latency and cost	Yes
`gpt-5.4-nano`	400K tokens	Very high volume, simple tasks. Cheapest option	Yes
`gpt-5.4`	1M tokens	General-purpose production agents	No
`gpt-5.5`	1M tokens	Maximum quality on complex tasks	No
`gpt-4.1-mini`	1M tokens	Previous generation, if already deployed	Yes

Model availability varies by Azure region, and new models reach Azure a little after OpenAI. Check Microsoft's model availability page for your region.

What can you build with Azure OpenAI and Bolna?

Healthcare call lines. Appointment scheduling and reminder agents where patient data has to stay in a chosen region.

Financial services support. Account queries and customer support for teams with data residency rules.

Enterprise contact centres on Azure. Keep the LLM inside the cloud account your security team already manages, with private endpoints. The Bolna docs pair Azure OpenAI with Azure speech-to-text and Azure text-to-speech for enterprise setups.

Lower-latency agents in a region. Deploy to the Azure region closest to your callers and keep reasoning effort at none to cut response time.

FAQ

Azure OpenAI on Bolna: frequently asked questions

Your Azure OpenAI API key, the endpoint URL, the API version and a deployment name. Enter them at platform.bolna.ai/auth/azure or under Settings → Integrations.

Yes. You create a named deployment for each model in the Azure portal, and that deployment name is what Bolna uses as the model. Keep the model name inside the deployment name, for example prod-gpt-5.4-mini, so Bolna applies the right GPT-5 settings.

Some Azure models are. azure/gpt-5.4-mini, azure/gpt-5.4-nano, azure/gpt-5-mini, azure/gpt-4.1-mini and azure/gpt-4o-mini are on the preferred model list, so they stay on the flat rate. Other models are billed at usage-based rates.

GPT-5 models only accept a temperature of 1. Any other value is rejected, so control tone and length through the prompt instead.

Other providers in this layer

LLM

Anthropic

Anthropic Claude writes your Bolna voice agent's replies. Use claude-sonnet-5 for most agents, or claude-haiku-4-5 for faster, high-volume calls.

LLM

DeepSeek

DeepSeek V4 runs the conversation in a Bolna voice agent at low cost per token. deepseek-v4-flash suits high-volume calls, with a 1M token context window.

LLM

Google Gemini

Google Gemini runs the conversation in a Bolna voice agent with a 1M token context and strong multilingual skills. gemini-2.5-flash is the recommended default.

Browse this layer

Keep exploring the voice stack

Browse

Large Language Models

The LLM is the brain of your voice agent. It understands what callers say and decides how to respond. Bolna lets you switch between models like GPT-5.4 mini, Claude and DeepSeek by changing the provider and model in your agent LLM settings, so you can tune for speed, cost or reasoning depth.

Browse

Telephony

Telephony providers connect your voice agents to the phone network so they can make and receive real calls. Bolna supports managed integrations with major carriers as well as bring-your-own-carrier via SIP trunking, giving you full control over call routing, number provisioning, and cost.

Browse

Speech-to-Text

Speech-to-text converts what callers say into text that your LLM can process. Transcription accuracy and latency directly affect how natural a conversation feels. Bolna supports streaming STT providers optimized for telephony audio, including specialized models for Indian languages.

Browse

Text-to-Speech

Text-to-speech turns your agent responses into spoken audio. Voice quality shapes how callers perceive your brand. Flat, robotic speech kills trust while natural, expressive voices build it. Bolna integrates with the fastest TTS providers so responses sound human and arrive without awkward pauses.

Browse

Tools & Workflows

Tools let your voice agents take action during a call, not just talk. Book a calendar slot, look up an order through your own API, push a lead into your CRM, or trigger a multi-step automation in Zapier. These integrations turn voice agents from answering machines into workflow engines.

See where Azure OpenAI fits in your production workflow

Use the demo to walk through provider selection, stack tradeoffs, and the exact workflow you want Bolna to automate.

Book a Demo Read Bolna Docs