IT Home reported on July 26 that OpenAI CEO Sam Altman replied to questions from netizens today, saying that the Alpha version of GPT-4o's voice mode (Voice Mode) will be opened to ChatGPT Plus users next week to achieve seamless chat.
As reported by IT House in May this year, OpenAI's chief technology officer, Muri Murati, said in his speech:
In GPT-4o, we trained a new end-to-end unified model across text, visuals, and audio, which means that all inputs and outputs are processed by the same neural network.
Since GPT-4o is our first model to combine all of these patterns, we are still in the early stages of exploring the model's capabilities and its limitations.
OpenAI originally planned to invite a small group of ChatGPT Plus users to test the GPT-4o voice mode at the end of June this year, but officials announced the postponement in June, saying it needed more time to polish the model and improve its ability to detect and reject certain content.
According to previously exposed information, the GPT-3.5 model has an average speech feedback delay of 2.8 seconds, while the GPT-4 model has a latency of 5.4 seconds, so it is not very good in terms of voice communication, while the upcoming GPT-4o can greatly reduce the delay time and make the conversation almost seamless.