Nemotron 3.5 Transcribe
Released
2026-10-28
Last refreshed
2026-10-29
Status
Researched today
Open weightsCommercial use: permittedMultimodalVision
NVIDIA AI releases · 27 in the last 12 months · this family litChangelog →
Specifications
- Family
- Nemotron 3.5
- Released
- 2026-10-28
- Context
- 64K
- Parameters
- 34B (4.3B active)
- Architecture
- Mixture of Experts
- Specialization
- speech-recognition
- Openness
- Open weights
- License
- OpenMDW 1.1Permitted
- Weights
- Available
- Code
- Unknown
- Training
- Pretrained
Created by
Pricing
Audio / min
$0.001998/min
List rate of 2 routes · OpenRouter
Links
About
Nemotron 3.5 Transcribe is NVIDIA's open-weight, promptable speech model: a mixture-of-experts model with 34B total and 4.3B active parameters (including the audio encoder) that does transcription in 40 languages, speaker attribution, translation, contextual prompting and audio understanding in one checkpoint. It handles recordings up to one hour (65,536-token context) and is released under the OpenMDW 1.1 license for commercial or non-commercial use.
Providers(2)
Compare all 2Compare published per-minute API pricing across 2 tracked provider routes.
| Provider | Audio / min | Route |
|---|---|---|
| OpenRouter | $0.001998/min | Serverless |
| DeepInfra | $0.002/min | Serverless |
Capabilities
MultimodalAudio
Benchmark peer barsfor Vision
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
API versions
nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4Bnvidia/nemotron-3.5-transcribeNemotron-3.5-Transcribe-30B-A4BCreated by
Pricing
Audio / min
$0.001998/min
List rate of 2 routes · OpenRouter
Links