--- title: The NEW Best ASR - NVIDIA Nemotron 3.5 ASR | daily.dev description: NVIDIA released Nemotron 3.5 ASR, a 600M parameter streaming speech-to-text model supporting 40 languages from a single checkpoint. Key features include... canonical: https://daily.dev/posts/the-new-best-asr---nvidia-nemotron-3-5-asr-tzbbxav0j twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: The NEW Best ASR - NVIDIA Nemotron 3.5 ASR | daily.dev og:description: NVIDIA released Nemotron 3.5 ASR, a 600M parameter streaming speech-to-text model supporting 40 languages from a single checkpoint. Key features include... og:url: https://daily.dev/posts/the-new-best-asr---nvidia-nemotron-3-5-asr-tzbbxav0j og:image: https://api.daily.dev/og/posts/tzBBxAV0J.png og:image:alt: The NEW Best ASR - NVIDIA Nemotron 3.5 ASR 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. # The NEW Best ASR - NVIDIA Nemotron 3.5 ASR **[Sam Witteveen](https://daily.dev/sources/samwitteveenai)** · 20 min read · 0 upvotes · 0 comments ## Summary NVIDIA released Nemotron 3.5 ASR, a 600M parameter streaming speech-to-text model supporting 40 languages from a single checkpoint. Key features include cache-aware streaming (reusing encoder self-attention states instead of reprocessing overlapping audio chunks, up to 17x faster), configurable chunk sizes (80ms to 1s) trading latency for accuracy, word boosting for injecting custom vocabulary at decode time without retraining, and speaker diarization via the NeMo framework. The video demonstrates all three features running locally, showing word boosting successfully correcting rare proper nouns and model names that the base model transcribes incorrectly. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent](https://daily.dev/posts/how-to-fine-tune-nemotron-3-5-asr-for-your-language-domain-or-accent-lmayxxp44) · Hugging Face · 0 upvotes · 0 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 - [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 --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#self-hosting](https://daily.dev/tags/self-hosting) [View this post on daily.dev](https://daily.dev/posts/the-new-best-asr---nvidia-nemotron-3-5-asr-tzbbxav0j) ```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":"The NEW Best ASR - NVIDIA Nemotron 3.5 ASR","url":"https://daily.dev/posts/the-new-best-asr---nvidia-nemotron-3-5-asr-tzbbxav0j","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/the-new-best-asr---nvidia-nemotron-3-5-asr-tzbbxav0j"},"datePublished":"2026-06-07T14:29:56.644Z","dateModified":"2026-06-07T14:30:15.215Z","description":"NVIDIA released Nemotron 3.5 ASR, a 600M parameter streaming speech-to-text model supporting 40 languages from a single checkpoint. Key features include...","image":"https://i.ytimg.com/vi/7BwSG_r9Jxg/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/7BwSG_r9Jxg/sddefault.jpg","isAccessibleForFree":true,"articleSection":"Sam Witteveen","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":"Sam Witteveen","logo":"https://media.daily.dev/image/upload/s--gJm-KsgL--/f_auto/v1711727006/logos/samwitteveenai","url":"https://daily.dev/sources/samwitteveenai"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/the-new-best-asr---nvidia-nemotron-3-5-asr-tzbbxav0j","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,self-hosting","timeRequired":"PT20M","video":{"@type":"VideoObject","name":"The NEW Best ASR - NVIDIA Nemotron 3.5 ASR","description":"NVIDIA released Nemotron 3.5 ASR, a 600M parameter streaming speech-to-text model supporting 40 languages from a single checkpoint. Key features include...","thumbnailUrl":"https://i.ytimg.com/vi/7BwSG_r9Jxg/sddefault.jpg","uploadDate":"2026-06-07T14:29:56.644Z","duration":"PT20M","url":"https://api.daily.dev/r/tzBBxAV0J","embedUrl":"https://www.youtube.com/embed/7BwSG_r9Jxg"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Sam Witteveen","item":"https://daily.dev/sources/samwitteveenai"},{"@type":"ListItem","position":3,"name":"The NEW Best ASR - NVIDIA Nemotron 3.5 ASR"}]} ```