GPT-4o brings real-time multimodal interaction

OpenAI's GPT-4o reasons across audio, vision and text in real time, at GPT-4 level, free to all users.

What happened and why it matters

Native audio-in/audio-out with ~300ms latency made conversational AI feel qualitatively different and brought GPT-4-class capability to hundreds of millions of free users.

Sources

• Hello GPT-4o ↗ OpenAI · 13 May 2024