{"id":16808,"date":"2024-07-31T09:37:43","date_gmt":"2024-07-31T01:37:43","guid":{"rendered":"https:\/\/www.1ai.net\/?p=16808"},"modified":"2024-07-31T09:37:43","modified_gmt":"2024-07-31T01:37:43","slug":"openai-%e5%90%91%e9%83%a8%e5%88%86%e4%bb%98%e8%b4%b9%e8%ae%a2%e9%98%85%e7%94%a8%e6%88%b7%e5%bc%80%e6%94%be-gpt-4o-%e8%af%ad%e9%9f%b3%e6%a8%a1%e5%bc%8f%ef%bc%8c%e5%8f%af%e6%8f%90%e4%be%9b%e6%9b%b4","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/16808.html","title":{"rendered":"OpenAI opens GPT-4o voice model to some paid subscribers, providing more natural real-time conversations"},"content":{"rendered":"<p data-pm-slice=\"0 0 []\">30th local time.<a href=\"https:\/\/www.1ai.net\/en\/tag\/openai\" title=\"[View articles tagged with [OpenAI]]\" target=\"_blank\" >OpenAI<\/a> announced that with immediate effect, it will provide some of the <a href=\"https:\/\/www.1ai.net\/en\/tag\/chatgpt\" title=\"[View articles tagged with [ChatGPT]]\" target=\"_blank\" >ChatGPT<\/a> Plus User Open <a href=\"https:\/\/www.1ai.net\/en\/tag\/gpt-4o\" title=\"[View articles tagged with [GPT-4o]]\" target=\"_blank\" >GPT-4o<\/a> (Alpha version) and will be rolled out to all ChatGPT Plus this fall. <a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%ae%a2%e9%98%85%e7%94%a8%e6%88%b7\" title=\"[See articles with [subscriber] labels]\" target=\"_blank\" >subscriber<\/a>.<\/p>\n<div class=\"pgc-img\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-16809\" title=\"get-948\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/07\/get-948.jpg\" alt=\"get-948\" width=\"828\" height=\"552\" \/><\/div>\n<p data-track=\"21\">In May of this year, OpenAI CTO Mira Murati gave a talk about it:<\/p>\n<blockquote>\n<p data-track=\"22\">In GPT-4o, we train a new unified model end-to-end across text, vision, and audio, meaning that all inputs and outputs are processed by the same neural network.<\/p>\n<p data-track=\"23\">Since GPT-4o is our first model to combine all of these modalities, we are still in the early stages of exploring the model\u2019s capabilities and its limitations.<\/p>\n<\/blockquote>\n<p data-track=\"24\">The OpenAI company had 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 a delay in June, saying that they needed to<strong>More time to polish<\/strong>The model, improving the model<strong>Detecting and rejecting certain content<\/strong>The ability of the<\/p>\n<p data-track=\"25\">According to the previously revealed information, the GPT-3.5 model has an average speech feedback delay of 2.8 seconds, while the GPT-4 model has a delay of 5.4 seconds, making it less than excellent for speech communication, and the upcoming GPT-4o can greatly reduce the delay time.<strong>Nearly seamless dialog<\/strong>.<\/p>\n<p data-track=\"26\">The GPT-4o voice mode has<strong>rapid response<\/strong>,<strong>You sound like a real person.<\/strong>OpenAI further claims that GPT-4o speech patterns can sense emotional tones in speech, including sadness, excitement, or singing.<\/p>\n<p data-track=\"27\">OpenAI spokesperson Lindsay McCallum said, \"ChatGPT <strong>You can't fake another person's voice.<\/strong>, including the voices of individuals and public figures, and would prevent the<strong>Different from the preset sounds<\/strong>of the output.\"<\/p>\n<p data-track=\"27\">","protected":false},"excerpt":{"rendered":"<p>On May 30th, OpenAI announced that it is opening up GPT-4o's speech model (Alpha version) to a select number of ChatGPT Plus subscribers, with a gradual rollout to all ChatGPT Plus subscribers in the fall of this year. In May, OpenAI CTO Mira Murati said in a speech: \"In GPT-4o, we've trained a new end-to-end unified model across text, vision, and audio, meaning that all inputs and outputs are processed by the same neural network. Since GPT-4o is our first model that combines all of these modalities, we are still in the beginning stages of exploring the model's capabilities and its limitations.<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[177,2582,190,3792],"collection":[],"class_list":["post-16808","post","type-post","status-publish","format-standard","hentry","category-news","tag-chatgpt","tag-gpt-4o","tag-openai","tag-3792"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/16808","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=16808"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/16808\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=16808"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=16808"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=16808"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=16808"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}