{"id":643965,"date":"2026-10-28T17:08:11","date_gmt":"2026-10-28T17:08:11","guid":{"rendered":"https:\/\/www.newsbeep.com\/nz\/643965\/"},"modified":"2026-10-28T17:08:11","modified_gmt":"2026-10-28T17:08:11","slug":"voice-ai-in-vogue-nvidia-releases-new-open-transcription-model","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/nz\/643965\/","title":{"rendered":"Voice AI in vogue: Nvidia releases new open transcription model"},"content":{"rendered":"<p id=\"speakable-summary\" class=\"wp-block-paragraph\">Nvidia on Wednesday released <a href=\"https:\/\/huggingface.co\/nvidia\/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">Nemotron 3.5 Transcribe<\/a>, a free, open-weight model that transcribes audio in up to 40 languages. It also released version 2 of Granary, its open source speech dataset.<\/p>\n<p class=\"wp-block-paragraph\">Nvidia boasts that Nemotron 3.5 can translate 31 languages to and from English, handle recordings up to an hour long, and tell up to eight speakers apart. It claims to beat rivals on benchmarks, including Hugging Face\u2019s <a href=\"https:\/\/huggingface.co\/spaces\/hf-audio\/open_asr_leaderboard\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">Open ASR Leaderboard<\/a>.<\/p>\n<p class=\"wp-block-paragraph\">These tools target developers building apps for business meetings and medical transcription, two of AI\u2019s most established footholds in the workplace. Nvidia says developers can use the model, the updated Granary dataset, and tools like its NeMo Speech model to customize apps to recognize an industry\u2019s jargon in each language. One drawback: Transcribe works with recorded audio, not livestreams.<\/p>\n<p class=\"wp-block-paragraph\">Still, the company promises Transcribe, at 30 billion parameters, can run on a single chip, from the Jetson AGX Thor robotics controller and DGX Spark chip <a href=\"https:\/\/techcrunch.com\/2026\/10\/07\/microsoft-releases-new-nvidia-chip-ai-pcs-with-revamped-windows-11\/\" rel=\"nofollow noopener\" target=\"_blank\">powering new laptops<\/a>, to Blackwell datacenter chips. It joins Nvidia\u2019s open-weight voice models, including the super small yet <a href=\"https:\/\/build.nvidia.com\/nvidia\/parakeet-1_1b-rnnt-multilingual-asr\/modelcard\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">powerful Parakeet<\/a> (1.1 billion parameters).<\/p>\n<p class=\"wp-block-paragraph\">Nvidia\u2019s latest voice entry comes during a busy period of AI voice releases: Mistral <a href=\"https:\/\/x.com\/MistralAI\/status\/2112574615318876178\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">shipped Voxtral 3 <\/a>earlier this month; ElevenLabs launched Realtime for instant speech in voice agents; and Salesforce released<a href=\"https:\/\/www.salesforce.com\/blog\/launa-omni\/\" target=\"_blank\" rel=\"noreferrer noopener nofollow\"> Launa-Omni,<\/a> its voice model. <\/p>\n","protected":false},"excerpt":{"rendered":"Nvidia on Wednesday released Nemotron 3.5 Transcribe, a free, open-weight model that transcribes audio in up to 40&hellip;\n","protected":false},"author":2,"featured_media":643966,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[365,363,364,5941,111,139,1042,69,145],"class_list":["post-643965","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-artificial-intelligence","tag-artificialintelligence","tag-in-brief","tag-new-zealand","tag-newzealand","tag-nvidia","tag-nz","tag-technology"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/posts\/643965","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/comments?post=643965"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/posts\/643965\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/media\/643966"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/media?parent=643965"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/categories?post=643965"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/tags?post=643965"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}