Deploy, test, and tune Nemotron Speech workflows.
What it does
Guides deployment, inference, testing, and configuration of NVIDIA speech recognition, speech synthesis, and translation NIMs.
When to use it
Use for Nemotron Speech or Riva NIM deployment, testing, custom model builds, system requirements checks, or model selection.
How to use it
Give it a Nemotron Speech task; it returns shell commands, configuration instructions, or analysis for the relevant workflow.
Uses
What you need · 3
Requires the Riva Python client for self-hosted deployment and cloud-hosted inference.
Cloud-hosted inference requires a valid key from build.nvidia.com; the files do not specify how the agent reads it.
Access · 3
This skill
NVIDIA documentation
Reads current NVIDIA documentation
nvidia-riva-client
Installs the Riva Python client