Nemotron ASR Streaming
Nemotron Speech Realtime Overview
Description:
Nemotron-ASR is a major step forward in the evolution of conversational AI. Its exceptional accuracy, coupled with the flexibility and ease of use offered by NeMo, empowers developers to create more natural and intuitive voice-powered applications. The possibilities are endless, from enhancing the accuracy of virtual assistants to enabling seamless real-time communication.
This container ships two model variants:
- Nemotron 3 ASR — optimized for high-quality English transcription.
- Nemotron 3.5 ASR — multilingual model supporting 40 languages with automatic language detection.
The container components are ready for commercial/non-commercial use.
License/Terms of Use:
GOVERNING TERMS: Use of this model is governed by the NVIDIA Community Model License Agreement.
You are responsible for ensuring that your use of NVIDIA provided models complies with all applicable laws.
Deployment Geography: Global
Release Date: Mar-12, 2026
Build.Nvidia.com 03/12/2026 via https://build.nvidia.com/nvidia/nemotron-speech-realtime
NGC 03/12/2026 via https://catalog.ngc.nvidia.com/orgs/nim/teams/nvidia/containers/nemotron-speech-realtime
Program Classes:
The Nemotron Speech Realtime Container includes the following models:
| Model Name & Link | Use Case | NIM_TAGS_SELECTOR value |
|---|---|---|
| rmir-bs64-26.05.8 | en-US Streaming ASR | type=en-US,batch_size=64 |
| rmir-bs32-26.05.8 | en-US Streaming ASR | type=en-US,batch_size=32 |
| rmir-multi-bs64-26.06.1 | multi-lingual Streaming ASR | type=multi,batch_size=64 |
| rmir-multi-bs32-26.06.1 | multi-lingual Streaming ASR | type=multi,batch_size=32 |
Deployment Details:
For details on how to deploy the model, please refer to the deployment tutorial.
Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.
Reference(s):
https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/models.html#fast-conformer
Container Version(s):
1.0.0, 1.2.0
Security Common Vulnerabilities and Exposures (CVEs)
Please review the Security Scanning tab on NGC to view the latest security scan results. For certain open-source vulnerabilities listed in the scan results, NVIDIA provides a response in the form of a Vulnerability Exploitability eXchange (VEX) document. The VEX information can be reviewed and downloaded from the Security Scanning tab.
Ethical Considerations:
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal developer team to ensure these software components meet requirements for the relevant industry and use case and address unforeseen product misuse.
Please report quality, risk, security vulnerabilities or NVIDIA AI Concerns here.
Get Help
Getting started with the NIM
Deploying and integrating the NIM is straightforward thanks to our industry standard APIs. Visit the NIM Container page for release documentation, deployment guides and more https://docs.nvidia.com/nim/speech/latest/index.html.
Enterprise Support
Get access to knowledge base articles and support cases or submit a ticket.