OpenAI

Power your Bolna voice agents with GPT-4o, GPT-4o-mini, or GPT-3.5 using your own API key. Fast, accurate language understanding for every phone call.

Official Documentation

How 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.

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

This page focuses on where OpenAI fits in a production voice stack. For full setup steps, credentials, and API details, use the documentation link above.

Overview

OpenAI provides state of the art large language models that power intelligent voice agents. With Bolna's OpenAI integration, you can leverage GPT-4o, GPT-4o-mini, and GPT-3.5 Turbo to create conversational AI agents that understand context, generate natural responses, and handle complex queries.

OpenAI models are the brain of your voice agent, they process what the caller says, understand their intent, and generate appropriate responses in realtime during phone conversations.

Features & Use Cases

Top Performance (GPT-4o)

The smartest model available. It easily understands complex requests and speaks very naturally. Perfect for handling tricky customer support issues or detailed technical questions.

Fast & Affordable (GPT-4o-mini)

A cheaper and faster version of the top model that still does a great job. It is ideal for busy call centers where you need quick answers without spending too much.

Quick & Basic (GPT-3.5 Turbo)

Extremely fast and highly affordable. Great for handling simple tasks like booking appointments or answering basic questions instantly.

Can Take Actions (Function Calling)

The AI doesn't just talk - it can actively do things for you during a call, like securely booking an appointment, updating a customer file, or checking on an order status.

Great Memory (Large Context Window)

Can remember very long conversations, making sure the AI agent never forgets what the caller said earlier in the call.