Baseten hosts NVIDIA Nemotron 3.5 Transcribe
NVIDIA Nemotron 3.5 Transcribe is an open-weight speech-understanding model that combines multilingual transcription, speaker attribution, speech-to-text translation, contextual prompting, and audio questions into a single workflow for recorded audio. Hosted on Baseten, the model processes audio recordings alongside text prompts to generate transcripts, speaker labels, and insights for applications such as post-call analytics and meeting tools. Open article →
- nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B · Hugging Face
- NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt
- Voice AI in vogue: Nvidia releases new open transcription model
- Nvidia's open Nemotron 3.5 Transcribe combines transcription, translation, and speaker recognition
- Nvidia releases all-in-one adaptable Nemotron 3.5 audio transcription and translation model
- Nvidia releases an open speech model that transcribes 40 languages
- NVIDIA Launches Open-Weight Transcription Model for 40 Languages
- Nvidia launches a promptable transcription model
- NVIDIA's Nemotron 3.5 Transcribe ties for #1 among open weights Speech to Text models with 2.8% W...
- NVIDIA released Nemotron 3.5 Transcribe, a new open-weight, 30B MoE model with ~4B active paramet...
- Meet NVIDIA Nemotron 3.5 Transcribe 🎙️ An open-weight, promptable 30B MoE model with ~4B active ...
- NVIDIA is releasing an open speech model that can transcribe a meeting, label who said what, tran...
- Nvidia Nemotron 3.5 Transcribe: open ASR for 40 languages
- Nvidia just released a free speech-to-text model that can transcribe up to 40 languages, but it o...
- You can dub or subtitle any podcast, video, or audio for free. Open-weight 30B MoE model (4B act...
- Wow open source NVIDIA Nemotron 3.5 is mind blowing transcription! i will bring this to my live...