Model dossier

NVIDIA: Nemotron 3.5 Transcribe

Nemotron 3.5 Transcribe is an open-weight speech recognition model from NVIDIA, a 30B mixture-of-experts with about 4B active parameters. It transcribes recordings of up to one hour in 40 languages,...

ProviderNVIDIA Start comparison

Context0

Max output0

Pricing viewTVP price

Identity

NVIDIA: Nemotron 3.5 Transcribe

Model ID: nvidia/nemotron-3.5-transcribe
Canonical slug: nvidia/nemotron-3.5-transcribe-20261028
Knowledge cutoff: n/a
Created: 10/29/2026

Capabilities

audiotranscription

Modalities

audio->transcriptionaudiotranscription

Capacity

Context0

Max output0

TokenizerOther