OpenAI ↗ · 2024-05-13 18:00 · UTC+8
OpenAI releases GPT-4o with unified multimodal interaction
Model release OpenAI Source language: English
OpenAI introduced GPT-4o, handling text, vision and audio within one model and cutting response latency for voice conversations. Multimodality became the primary interaction mode rather than an add-on feature.
Excerpt
OpenAI introduced GPT-4o, handling text, vision and audio within one model and cutting response latency for voice conversations. Multimodality became the primary interaction mode rather than an add-on feature.
Short excerpt from the source — open the original for the full text.