{"id":38446,"date":"2025-06-28T13:09:11","date_gmt":"2025-06-28T05:09:11","guid":{"rendered":"https:\/\/www.1ai.net\/?p=38446"},"modified":"2025-06-28T13:09:11","modified_gmt":"2025-06-28T05:09:11","slug":"8-%e7%a7%92%e8%bd%ac%e5%bd%95-30-%e5%88%86%e9%92%9f%e6%92%ad%e5%ae%a2%ef%bc%9amacwhisper-%e5%ba%94%e7%94%a8%e6%8e%a5%e5%85%a5%e8%8b%b1%e4%bc%9f%e8%be%be-parakeet-%e6%a8%a1%e5%9e%8b","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/38446.html","title":{"rendered":"8-Second Transcription of a 30-Minute Podcast: MacWhisper App Accesses NVIDIA Parakeet Models"},"content":{"rendered":"<p>June 28, 2011 - Tech media outlet 9to5Mac published a blog post yesterday (June 27) reporting that macOS apps <a href=\"https:\/\/www.1ai.net\/en\/tag\/macwhisper\" title=\"[See articles with [MacWhisper] label]\" target=\"_blank\" >MacWhisper<\/a> In the recent version update<strong>By accessing<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%8b%b1%e4%bc%9f%e8%be%be\" title=\"Look at the article with the label\" target=\"_blank\" >Nvidia<\/a>of <a href=\"https:\/\/www.1ai.net\/en\/tag\/parakeet\" title=\"[See articles with [Parakeet] label]\" target=\"_blank\" >Parakeet<\/a> models, transcription rates spike.<\/strong><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-38447\" title=\"f3ffdb96j00syjvlz0061d000rs00dbp\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2025\/06\/f3ffdb96j00syjvlz0061d000rs00dbp.jpg\" alt=\"f3ffdb96j00syjvlz0061d000rs00dbp\" width=\"1000\" height=\"479\" \/><\/p>\n<p>1AI reported in February 2023 that developer Jordi Bruin had launched the MacWhisper app, based mostly on OpenAI's Whisper transcription model, which does the work of transcribing audio files to text locally.<\/p>\n<p>But as OpenAI shifted its focus to the more commercially viable gpt-4o-transcribe model, Whisper began to look a bit outdated, with faster, newer transcription models overtaking Whisper time and time again.<\/p>\n<p>NVIDIA announced the Parakeet model last month, and on hardware with an A100, H100, T4, or V100 GPU, the<strong>Transcribe 60 minutes of audio in just 1 second.<\/strong><\/p>\n<p>Parakeet is available through open source tools, but the problem is that not everyone is familiar with the command line interface or custom model deployment, which users now have easier access to with the new version of MacWhisper.<\/p>\n<p>Thanks to our collaboration with the Argmax team, MacWhisper now supports Parakeet models,\" said app developer Jordi Bruin. To demonstrate the significance of this change, check out the GIF, below.<strong>In less than 8 seconds we transcribed and organized a 30-minute<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e6%92%ad%e5%ae%a2\" title=\"[Sees articles with [crowding] labels]\" target=\"_blank\" >Internet audio subscription service<\/a>!<\/strong>\u201d<\/p>\n<p>The outlet then tested the new MacWhisper app, which transcribed a three-hour 9to5Mac Happy Hour podcast in just 1 minute and 22 seconds.<\/p>","protected":false},"excerpt":{"rendered":"<p>On June 28, according to the news, 9to5Mac published yesterday, June 27, by the tech media, reports that MacWhisper used MacWhisper in a recent update to record a sharp increase in speed by accessing the Parakeet model in Inverda. 1AI reported in February 2023 that the developer Jordi Bruin launched the MacWhisper application, mainly based on OpenAI's Whisper Transfer Model, which allows for local transcription of audio files into text. But as OpenAI shifts its focus to a more commercial gpt-4o-transcribe model, Whisper begins to show<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[7068,7069,6928,239],"collection":[],"class_list":["post-38446","post","type-post","status-publish","format-standard","hentry","category-news","tag-macwhisper","tag-parakeet","tag-6928","tag-239"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/38446","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=38446"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/38446\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=38446"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=38446"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=38446"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=38446"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}