NVIDIA releases Nemotron 3.5 Transcribe with launch-day vLLM serving support
Understand the event
NVIDIA released Nemotron 3.5 Transcribe, an open-weight speech model, with vLLM announcing launch-day serving support through vLLM and NeMo Speech. NVIDIA described it as a promptable 30B mixture-of-experts model with approximately 4B active parameters that combines transcription in 40 languages, speaker attribution, translation, contextual prompting and audio understanding in one checkpoint. The Decoder reported that the model follows text instructions to process recordings up to an hour long with up to eight speakers, but does not support real-time processing. vLLM said its serving support includes promptable transcripts, speaker labels and audio question answering, with model weights available in BF16, FP8 and NVFP4 formats. According to The Decoder, NVIDIA also released Granary v2, a dataset containing about 844,000 hours of speech in 48 languages, along with dataset-building tools and fine-tuning guides.
Generated by AI from reports · Updated 2 days ago
Read next
More changes in today’s briefingMistral releases improved Mistral Large 4 open weights for coding and cybersecurityDevelopments
4 developments
- 10/28 23:26 (UTC+8) · 1 reportsvLLM and NeMo Speech Add Day-One Serving for NVIDIA Nemotron 3.5 TranscribevLLM · X：NVIDIA Nemotron 3.5 Transcribe arrives with day-0 vLLM and NeMo Speech serving
- 10/28 23:14 (UTC+8) · 2 reportsNVIDIA Releases Nemotron 3.5 TranscribeThe Decoder：Nvidia's open Nemotron 3.5 Transcribe combines transcription, translation, and speaker recognition
- 10/15 05:12 (UTC+8) · 1 reportsNathan Lambert asks whether Nemotron 4 is comingNathan Lambert · X：Nathan Lambert asks whether Nemotron 4 is coming
- 10/15 04:29 (UTC+8) · 1 reportsNVIDIA teases an upcoming model launchNVIDIA AI · X：NVIDIA teases an upcoming model launch
Report timeline
Follow the reports to explore different sides of the event.
- The DecoderPicksNvidia's open Nemotron 3.5 Transcribe combines transcription, translation, and speaker recognition
Nvidia released Nemotron 3.5 Transcribe, an open speech recognition model that follows text instructions to transcribe, translate, identify speakers, and answer questions about recorded audio. It transcribes 40 languages and handles recordings up to an hour long with up to eight speakers, but does not support real-time processing. The release includes Granary v2, containing about 844,000 hours of speech in 48 languages, plus dataset-building tools and fine-tuning guides.
- vLLM · XPicksNVIDIA Nemotron 3.5 Transcribe arrives with day-0 vLLM and NeMo Speech serving
vLLM announces day-0 serving for NVIDIA Nemotron 3.5 Transcribe through vLLM + NeMo Speech. 40 languages. Recordings up to an hour. Promptable transcripts, speaker labels and audio Q&A. Open weights in BF16, FP8 and NVFP4. https://t.co/WhcqKqd1jf
- NVIDIA introduces Nemotron 3.5 Transcribe, an open-weight 30B MoE model
Meet NVIDIA Nemotron 3.5 Transcribe 🎙️ An open-weight, promptable 30B MoE model with ~4B active parameters that brings transcription in 40 languages, speaker attribution, translation, contextual prompting, and audio understanding into one checkpoint. Watch it keep track of who https://t.co/PEH1PeURIv
- NVIDIA BlogPicksNVIDIA RTX Spark Laptops Gain Nemotron 3.5 Transcribe, Agent Controls and Gaming Updates
NVIDIA introduced Nemotron 3.5 Transcribe alongside model support, agent resource controls and gaming updates for RTX Spark laptops. The open weight speech model handles transcription, speaker attribution, translation and audio questions, supports 40 languages and is available today on Hugging Face, with quantized versions coming soon. NVIDIA App now lets users allocate GPU resources between foreground applications and background agents, while Liquid AI’s LFM3 models support local execution through llama.cpp and vLLM.
- Nvidia releases Nemotron 3.5 Transcribe, an open-weight model supporting 40 languages
Nvidia released Nemotron 3.5 Transcribe, a free, open-weight model that transcribes recorded audio in up to 40 languages, alongside version 2 of its open source Granary speech dataset. Nvidia says the model translates 31 languages to and from English, handles recordings up to an hour long, and distinguishes up to eight speakers. The 30 billion parameter model works with recorded audio rather than livestreams, and Nvidia says it can run on a single chip.
- Nathan Lambert asks whether Nemotron 4 is coming
Nemotron 4??? https://t.co/5GjFbp1LVs @NVIDIAAI says it has one of its own coming. Nathan Lambert reacts: “So many models launching this week!” https://t.co/s5Z9QZ984W
- NVIDIA teases an upcoming model launch
So many models launching this week! And we have one of our own coming...⌛️ https://t.co/s5Z9QZ984W
Keep up with AI, one email a day
Model releases, price changes and compute developments, with original sources. Free, confirmed by email, and easy to unsubscribe. Read a past issue
Event heat trend
- Current within comparable coverage
- 4
- Peak within comparable coverage
- 3010/29 00:00 (UTC+8)
- 24-hour change
- -83%
Trends compare the same continuously observed participants, which may cover fewer sources than current heat. Point or click to inspect hourly heat, or use left and right arrow keys.