Nvidia Launches a Promptable Transcription Model
The model can translate 31 languages, handle hourlong recordings and separate eight speakers as Nvidia targets business and medical transcription.
10 Articles
10 Articles
TechCrunch
Voice AI in vogue: Nvidia releases new open transcription model
Nvidia just released a free speech-to-text model that can transcribe up to 40 languages, but it only works on recordings, not live audio, so it’s a big step for meeting and medical transcription tools while still leaving real-time use to rivals like ElevenLabs.
Nvidia presented Nemotron 3.5 Transcribe, a model of open weights that processes audio in up to 40 languages and distinguishes up to eight speakers. Its streaming variant allows transcribing audio while it is received, and the tool points to meeting applications and medical transcription.
NVIDIA Expands Open-Weight Model Family with Nemotron 3.5 Audio Transcription and Translation Release
NVIDIA has officially released its new Nemotron 3.5 audio transcription and translation model, expanding its open-weight ecosystem for enterprise artificial intelligence and agentic workflows. The advanced model is engineered to provide ultra-low latency automatic speech recognition (ASR), robust multilingual translation, and precise speaker adaptation across diverse operating environments. Built for seamless integration with NVIDIA NIM […]
Nvidia publishes with Nemotron 3.5 Transcribe an open language recognition model that combines transcription, speaker recognition and translation by text instruction in one model. It lists several benchmarks and needs only one sixth of the active parameters of its strongest open competitor. To do this, Nvidia provides a record with over 800,000 hours of language and fine-tuning tools. The article Nemotron 3.5 Transcribe: Nvidia's open model comb…
Nvidia's open Nemotron 3.5 Transcribe combines transcription, translation, and speaker recognition
Nvidia has released Nemotron 3.5 Transcribe, an open speech recognition model that handles transcription, speaker recognition, and translation and takes its instructions as text prompts. It leads several benchmarks and uses only a sixth of the active parameters of its strongest open rival. Nvidia is also shipping a dataset with more than 800,000 hours of speech, along with tools for fine-tuning. The article Nvidia's open Nemotron 3.5 Transcribe …
Coverage Details
Bias Distribution
- 100% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
