NVIDIA-Nemotron-3.5-Transcribe-30B-A4B
Nemotron 3.5 Transcribe is an open-weight 30B-A4B speech-augmented language model from NVIDIA for offline transcription in 40 languages.
audio → text · made by NVIDIA
$0.000033per second
DeepInfra
Sold by 1 way
| Seller | Lane | Rate |
|---|---|---|
| DeepInfra aggregator | standard | $0.002per minuteapi.deepinfra.com · read 2026-10-30 |
About
NVIDIA-Nemotron-3.5-Transcribe-30B-A4B — a text model from NVIDIA, sold by one company from $0.002 per minute.
It takes audio and returns text. It was published in October 2026. The catalogue files it under transcribe and translate. Its weights are published under the other licence, which attaches conditions the plain open licences do not. Only DeepInfra sells it, at $0.002 per minute.
Every current figure
- Maker
- NVIDIA
- Register
- model
- Takes
- audio
- Returns
- text
- Published
- October 2026
- Parameters
- 34 billion · read from its own weights
- Licence
- other
- Sellers
- 1
- Maker's own price
- not read
- Price
- $0.002 per minute — DeepInfra
Known as 1 name
nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B