Odaily News OpenAI released its latest flagship model GPT-4o, which can reason about audio, vision and text in real time. The main concept is a humanized, supernatural, ultra-low latency personal voice interaction assistant. According to the OpenAI official website and the official account of the X platform, the o in GPT4o stands for Omni (comprehensive), which is a step towards more natural human-computer interaction-it accepts any combination of text, audio and images as input, and supports the generation of any combination of text, audio and image output. It can respond to audio input in 232 milliseconds and an average of 320 milliseconds, which is similar to the human reaction time in conversation. In terms of English and code, it performs on par with GPT-4 Turbo, with significant improvements on non-English language texts, while the API is faster and 50% cheaper. Compared with existing models, GPT-4o performs particularly well in visual and audio understanding. Text and image input will be launched in API and ChatGPT today, and voice and video input will be launched in the coming weeks.