GPT-4o Realtime Preview

A versatile model capable of handling real-time text and audio inputs and outputs, with a wide range of capabilities including text, image, video, audio, transcription, and text-to-speech.

Supports a 128,000 token context window. Handles Text, Image, Video, Audio, Transcription, Text-to-Speech inputs and outputs. Supports fine-tuning for custom applications. Supports tool use for advanced automation. Capable of generating structured output formats.