AITOPAI热报
ModelsMulti-sourceSelected71°

NVIDIA Releases Nemotron 3.5 Transcribe Open Speech Model

kimmonismus@kimmonismus
Post· 11 sources
View the post
Why we picked it

Combining transcription, speaker labelling, translation and audio Q&A in one self-hostable model reduces the need to chain multiple speech tools on a single GPU. Teams handling multilingual meetings or recorded calls across Southeast Asia get 40-language coverage plus translation into English from 31 languages. Compared with closed APIs from providers like OpenAI, it can run on your own NVIDIA hardware, keeping sensitive recordings in-house.

NVIDIA has launched Nemotron 3.5 Transcribe, an open speech model with roughly 30B parameters and about 4B active per token. It transcribes audio in 40 languages, translates between English and 31 languages, and labels up to eight speakers across recordings of up to an hour. Users can supply custom names and technical terms to guide transcripts and ask questions about the audio, with audio Q&A trained in English. NVIDIA reports it ranks first among open-weight models on Hugging Face's English Open ASR leaderboard and leads VoiceArena's 14-system test of transcription with speaker attribution.

Original · kimmonismus

NVIDIA is releasing an open speech model that can transcribe a meeting, label who said what, translate it and answer questions about the recording:

Nemotron 3.5 Transcribe supports: - Transcription in 40 languages - Translation between English and 31 languages - Up to eight speakers, with speaker labels in 13 languages - Recordings up to an hour long

You can give it names and technical terms to guide the transcript, or ask questions about the audio. Audio Q&A is trained in English.

It has roughly 30B parameters, with about 4B active per token, and can run on your own NVIDIA GPU.

According to NVIDIA's launch materials, it ranks first among open-weight models on Hugging Face's English Open ASR leaderboard and leads VoiceArena's 14-system test of transcription with speaker attribution.

Built for recorded audio. Live streaming uses a separate model.

Super cool to see!

Model: https://t.co/jEe0LRZoqg Demo: https://t.co/xIr5mf0PCV Blog: https://t.co/mQk95Waudq

#NVIDIA#Nemotron 3.5 Transcribe#speech recognition#open-source models#multimodal

Keep reading

Recent stories with the same tag or section
ModelsBuildersMulti-sourceSelected23:32
NVIDIA Nemotron 3.5 Transcribe speech model launches on vLLM

Day-0 vLLM support means teams can self-host a multilingual transcription model immediately instead of routing audio through paid APIs. The NVFP4 quantised weights are notable for developers running inference on NVIDIA GPUs, cutting memory costs at scale. Teams building voice agents across Southeast Asian languages can compare it with Whisper-based pipelines on their target locales.

#NVIDIA#Nemotron#vLLM#speech recognition
Event
官方账号vLLM@vllm_project11 sourcesSource
ModelsBuildersMulti-sourceSelected23:10
NVIDIA Nemotron 3.5 Transcribe ties for #1 open-weight STT

Efficiency, not just accuracy, is the story: matching top open-weight transcription quality at 4B active parameters cuts inference cost substantially for voice pipelines. Teams building voice agents should shortlist it, since it leads specifically on conversational agent audio (1.8% vs 2.3% for Voxtral Small). The open weights licence also lets companies self-host transcription instead of relying on API vendors.

#NVIDIA#Nemotron 3.5 Transcribe#Voxtral#speech-to-text
Event
官方账号Artificial Analysis@ArtificialAnlys11 sourcesSource
ModelsBuildersMulti-sourceSelected23:00
NVIDIA MotionBricks generates character motion at 15,000 fps

Real-time motion synthesis at 2ms latency removes the offline-baking step that usually separates generated animation from playable game or robot loops. Game studios and robotics teams can prototype character interactions on a single RTX 5090 instead of maintaining retraining pipelines. It positions NVIDIA's consumer GPUs as the deployment target for motion generation workflows.

#NVIDIA#MotionBricks#video generation#game characters
Event
kimmonismus@kimmonismus10 sourcesSource