--- title: Voice AI in vogue: Nvidia releases new open... description: Nvidia released Nemotron 3.5 Transcribe, a free, open-weight speech-to-text model supporting up to 40 languages. Nvidia claims it can translate 31 languages to... canonical: https://daily.dev/posts/voice-ai-in-vogue-nvidia-releases-new-open-transcription-model-dotdulayg twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Voice AI in vogue: Nvidia releases new open transcription model | daily.dev og:description: Nvidia released Nemotron 3.5 Transcribe, a free, open-weight speech-to-text model supporting up to 40 languages. Nvidia claims it can translate 31 languages to... og:url: https://daily.dev/posts/voice-ai-in-vogue-nvidia-releases-new-open-transcription-model-dotdulayg og:image: https://api.daily.dev/og/posts/dOtdULayG.png og:image:alt: Voice AI in vogue: Nvidia releases new open transcription model og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Voice AI in vogue: Nvidia releases new open transcription model **[TechCrunch](https://daily.dev/sources/tc)** · 2 min read · 0 upvotes · 0 comments ## Summary Nvidia released Nemotron 3.5 Transcribe, a free, open-weight speech-to-text model supporting up to 40 languages. Nvidia claims it can translate 31 languages to and from English, handle recordings up to an hour long, and distinguish up to eight speakers. Nvidia claims it beats rivals on benchmarks, including Hugging Face's Open ASR Leaderboard. The 30-billion-parameter model can run on a single chip, from Jetson AGX Thor to Blackwell datacenter chips, but it only works on recorded audio, not live streams. Nvidia also released Granary v2, its open-source speech dataset, during a busy period of voice model releases from Mistral, ElevenLabs, and Salesforce. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is Nvidia's Nemotron 3.5 Transcribe model and what can it do? Nemotron 3.5 Transcribe is a free, open-weight speech-to-text model from Nvidia that transcribes audio in up to 40 languages, translates 31 languages to and from English, handles recordings up to an hour long, and distinguishes up to eight speakers. At 30 billion parameters, it runs on a single chip, from the Jetson AGX Thor to Blackwell datacenter chips, but it only works on recorded audio, not live streams. _Developers comparing transcription models for meeting or medical apps can track releases like this on daily.dev._ ### Does Nvidia's Nemotron 3.5 Transcribe support real-time audio transcription? No, Nemotron 3.5 Transcribe works only with recorded audio, not live streams, which is a stated drawback of the model. This limits it to use cases like meeting and medical transcription rather than real-time voice agents, an area where rivals such as ElevenLabs's Realtime product are positioned instead. _Anyone picking between batch and real-time transcription tools can weigh trade-offs like this via daily.dev._ ### What open-source speech dataset did Nvidia release alongside Nemotron 3.5 Transcribe? Nvidia released Granary version 2, its open-source speech dataset, alongside the Nemotron 3.5 Transcribe model. Nvidia says developers can use the model, the updated Granary dataset, and tools like its NeMo Speech model to customize apps to recognize industry-specific jargon across languages. _Teams building multilingual transcription pipelines can follow dataset updates like this on daily.dev._ ## Similar posts on daily.dev - [Building Voice Agents with NVIDIA Open Models](https://daily.dev/posts/building-voice-agents-with-nvidia-open-models-bhrohy86v) · Hacker News · 1 upvotes · 1 comments - [Scaling Real-Time Voice Agents with Cache-Aware Streaming ASR](https://daily.dev/posts/scaling-real-time-voice-agents-with-cache-aware-streaming-asr-v2urtcsgr) · Hugging Face · 15 upvotes · 0 comments --- Tags: [#open-source](https://daily.dev/tags/open-source), [#nvidia](https://daily.dev/tags/nvidia), [#speech-recognition](https://daily.dev/tags/speech-recognition), [#huggingface](https://daily.dev/tags/huggingface), [#voice-ai](https://daily.dev/tags/voice-ai) [View this post on daily.dev](https://daily.dev/posts/voice-ai-in-vogue-nvidia-releases-new-open-transcription-model-dotdulayg) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Voice AI in vogue: Nvidia releases new open transcription model","url":"https://daily.dev/posts/voice-ai-in-vogue-nvidia-releases-new-open-transcription-model-dotdulayg","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/voice-ai-in-vogue-nvidia-releases-new-open-transcription-model-dotdulayg"},"datePublished":"2026-10-28T15:02:20.411Z","dateModified":"2026-10-28T15:28:41.177Z","description":"Nvidia released Nemotron 3.5 Transcribe, a free, open-weight speech-to-text model supporting up to 40 languages. Nvidia claims it can translate 31 languages to...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/312132b3663a2fbb68a1cd80253cfb6f?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/312132b3663a2fbb68a1cd80253cfb6f?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"TechCrunch","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"TechCrunch","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/tc","url":"https://daily.dev/sources/tc"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/voice-ai-in-vogue-nvidia-releases-new-open-transcription-model-dotdulayg","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"open-source,nvidia,speech-recognition,huggingface,voice-ai","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"TechCrunch","item":"https://daily.dev/sources/tc"},{"@type":"ListItem","position":3,"name":"Voice AI in vogue: Nvidia releases new open transcription model"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/voice-ai-in-vogue-nvidia-releases-new-open-transcription-model-dotdulayg#faq","mainEntity":[{"@type":"Question","name":"What is Nvidia's Nemotron 3.5 Transcribe model and what can it do?","acceptedAnswer":{"@type":"Answer","text":"Nemotron 3.5 Transcribe is a free, open-weight speech-to-text model from Nvidia that transcribes audio in up to 40 languages, translates 31 languages to and from English, handles recordings up to an hour long, and distinguishes up to eight speakers. At 30 billion parameters, it runs on a single chip, from the Jetson AGX Thor to Blackwell datacenter chips, but it only works on recorded audio, not live streams. Developers comparing transcription models for meeting or medical apps can track releases like this on daily.dev."}},{"@type":"Question","name":"Does Nvidia's Nemotron 3.5 Transcribe support real-time audio transcription?","acceptedAnswer":{"@type":"Answer","text":"No, Nemotron 3.5 Transcribe works only with recorded audio, not live streams, which is a stated drawback of the model. This limits it to use cases like meeting and medical transcription rather than real-time voice agents, an area where rivals such as ElevenLabs's Realtime product are positioned instead. Anyone picking between batch and real-time transcription tools can weigh trade-offs like this via daily.dev."}},{"@type":"Question","name":"What open-source speech dataset did Nvidia release alongside Nemotron 3.5 Transcribe?","acceptedAnswer":{"@type":"Answer","text":"Nvidia released Granary version 2, its open-source speech dataset, alongside the Nemotron 3.5 Transcribe model. Nvidia says developers can use the model, the updated Granary dataset, and tools like its NeMo Speech model to customize apps to recognize industry-specific jargon across languages. Teams building multilingual transcription pipelines can follow dataset updates like this on daily.dev."}}]} ```