Skip to content
Realtime engine · openai-realtime

The openai-realtime engine on Wixzel Voice: OpenAI Realtime, gpt-realtime-2.1-mini

One OpenAI model for the whole turn. gpt-realtime-2.1-mini, or gpt-realtime-2.1 when you name it, hears the caller, reasons and answers in its own voice, with phone audio going in and out as it is. It calls your tools natively and follows the caller's language with auto, or speaks one you pin.

Last updated

$0.0850per connected minute, including the $0.012 orchestration fee
Create an accountVoice engines in the docs

What does each model in the openai-realtime engine cost on Wixzel Voice?

A realtime engine hands the whole turn to one model, so the price is mostly that model’s units. The pipeline label is OpenAI Realtime, gpt-realtime-2.1-mini.

StageModelUnit pricePer minute
Realtime modelopenai/gpt-realtime-2.1-mini$0.0140 per 1k audio tokens in$0.0210
Realtime modelopenai/gpt-realtime-2.1-mini$0.0280 per 1k audio tokens out$0.0420
Realtime modelopenai/gpt-realtime-2.1-mini$0.0008 per 1k tokens in$0.0020
Realtime modelopenai/gpt-realtime-2.1-mini$0.0034 per 1k tokens out$0.0016
Speech-to-textopenai/gpt-transcribe$0.0001 per second$0.0063
Orchestrationwixzel/orchestration$0.0120 per minute$0.0120

Rounded up, never down. Where two models are listed for one stage the engine picks by language; the engine price above assumes the dearer path. All prices on the model price list.

Frequently asked questions

What is the openai-realtime voice engine?

openai-realtime is a realtime voice engine on Wixzel Voice. One OpenAI model for the whole turn. gpt-realtime-2.1-mini, or gpt-realtime-2.1 when you name it, hears the caller, reasons and answers in its own voice, with phone audio going in and out as it is. It calls your tools natively and follows the caller's language with auto, or speaks one you pin.

How much does the openai-realtime engine cost per minute?

$0.0850 per connected minute at typical speech rates, including the flat $0.012 per minute orchestration fee. The figure is generated from the price book the meter bills against and is rounded up, never down. Telephony runs over your own SIP trunk and is not included or marked up.

Which models does the openai-realtime engine use?

openai-realtime hands the whole turn to one realtime model: openai/gpt-realtime-2.1-mini, openai/gpt-transcribe. There is no separate speech-to-text or text-to-speech stage to configure.

Do I need my own openai account to use openai-realtime?

No. The provider accounts belong to Wixzel Voice. One wv_live_… API key and a prepaid balance cover the openai-realtime engine and every other engine; there are no provider keys to bring.

How do I use the openai-realtime engine in a call?

Set the agent's voice to {"realtime": {"model": "openai/gpt-realtime-2.1-mini"}} when you create it with POST /v1/agents, then place a call with POST /v1/calls. GET /v1/engines lists what is available right now; an engine whose provider is degraded disappears from that list before calls start failing.

Is the openai-realtime price per minute a flat rate?

No. $0.0850 is what a typical minute adds up to. The meter charges per second of speech, per token and per character for the models that actually ran, plus the flat orchestration fee, and every micro-dollar is itemised in GET /v1/usage/events. A quieter or shorter turn costs less; a long monologue costs more.

Which other voice engines does Wixzel Voice run?

classic: $0.0865 per minute

Deepgram + GPT-6 Luna + ElevenLabs

sarvam: $0.0617 per minute

Sarvam, Indian languages end to end

gemini-live: $0.0491 per minute

Gemini Live, native audio

deepgram-agent: $0.1851 per minute

Deepgram Voice Agent

openai-live: $0.0827 per minute

OpenAI GPT-Live + GPT-6 Luna

grok-voice: $0.1240 per minute

xAI Grok Voice

Compose your own

Name a model for each stage and see the minute it adds up to.

Build your first voice agent

Sign upRead the quickstart