---
id: "nvidia/nemotron-3.5-transcribe"
also: ["nvidia/nemotron-3.5-transcribe-20261028", "nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B"]
cheapest_list_usd_per_m: "16.6667 in, 0.0 out, at primeintellect/bf16 on openrouter"
context: 0
max_output: 0
input: ["audio"]
output: ["transcription"]
released: "2026-10-29"
api: ["/api/v1/audio/transcriptions"]
endpoints: 2
gateways: "openrouter (2)"
no_training: 2
trains: 0
retains_prompts: 0
---
# 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,...