GPT-4o Audio

OpenAI

Realtime audio model for low-latency voice and text interactions over WebRTC or WebSocket

Pricing

per minute

Input / min$0.60
Output / min$2.40

Specifications

API Model IDgpt-4o-audio-preview
TypeRealtime

Modalities

textaudio

Capabilities

streamingtool-usevision

Other OpenAI Audio Models

ModelInput / minOutput / min
Whisper$0.0060—
TTS—$0.01
TTS HD—$0.03