APIFleet Sign in

OpenAI.
In your voice stack.

Run a speech-to-speech assistant, or use an OpenAI model in a cascading pipeline.

Where it fits

Realtime voice · Language model

Realtime audio usage is different from text-token usage. Model access and rate limits depend on your OpenAI account.

Configure the connection

Select Realtime → OpenAI on the assistant and choose a model and voice available to your provider account.

Assistant configuration fragment. Merge this into your assistant; select current model and voice IDs from your account before saving.

{
  "pipeline_mode": "realtime",
  "realtime_provider": "openai"
}

Keep provider secrets in workspace credentials. The public MCP provider matrix describes capabilities; it does not connect your provider account.

Test this boundary first

Interrupt a spoken reply, invoke a tool and inspect the resulting transcript. Repeat on a phone connection before changing production routing.

Save a known working configuration and move one test route first. Inspect the call log before increasing traffic. Follow the staged migration guide.

Understand the bill

APIFleet adds $0.03 per connected AI minute, billed per second. Provider and carrier usage are additional. With your own keys, provider charges go directly to the provider. No monthly subscription or free call credits; prepaid top-ups start at $10.

Calculate your scenario · OpenAI documentation

Bring your next conversation.

Explore the API, or sign in to your existing workspace. New workspace access is currently limited; contact us to discuss your project.