Nemotron Voice Agent Builder — Agent Skill by NVIDIA

From the author

Create, refine, or fix NVIDIA voice agents (Cascaded or Omni) with Pipecat or LiveKit. Use when building, scaffolding, or iterating on a real-time voice-agent pipeline, including speech (ASR/TTS) customization and cloud or local deployment. Not for offline/batch speech-to-text, text-only chat or RAG, or generic Docker or CUDA work unrelated to a voice agent.

— the description by NVIDIA Voice Agent Team

Install

Get the skill from its source (we cannot redistribute it):
https://github.com/NVIDIA/skills/tree/fce3cca4170be75e82c64920654d56ee2811b005/skills/nemotron-voice-agent-builder

Documentation by NVIDIA Voice Agent Team

The licence of this skill does not allow us to copy its documentation. Read it at the source

Files

BENCHMARK.md(opens on GitHub)Not mirrored: opens on GitHub10.6 KiB
SKILL.md(opens on GitHub)Not mirrored: opens on GitHub3.3 KiB
evals/EVAL.md(opens on GitHub)Not mirrored: opens on GitHub2.8 KiB
evals/evals.json(opens on GitHub)Not mirrored: opens on GitHub4.6 KiB
references/domain/agent-behavior.md(opens on GitHub)Not mirrored: opens on GitHub3.1 KiB
references/domain/speech-customization.md(opens on GitHub)Not mirrored: opens on GitHub8.2 KiB
references/frameworks/livekit.md(opens on GitHub)Not mirrored: opens on GitHub6.0 KiB
references/frameworks/omni.md(opens on GitHub)Not mirrored: opens on GitHub7.8 KiB
references/frameworks/pipecat.md(opens on GitHub)Not mirrored: opens on GitHub5.3 KiB
references/intake.md(opens on GitHub)Not mirrored: opens on GitHub8.3 KiB
references/models/asr.md(opens on GitHub)Not mirrored: opens on GitHub7.6 KiB
references/models/catalog.md(opens on GitHub)Not mirrored: opens on GitHub4.2 KiB
references/models/language-routing.md(opens on GitHub)Not mirrored: opens on GitHub5.6 KiB
references/models/llm.md(opens on GitHub)Not mirrored: opens on GitHub18.3 KiB
references/models/tts.md(opens on GitHub)Not mirrored: opens on GitHub5.7 KiB
references/networking/remote-webrtc.md(opens on GitHub)Not mirrored: opens on GitHub5.0 KiB
references/operations/iterate.md(opens on GitHub)Not mirrored: opens on GitHub4.6 KiB
references/operations/observability.md(opens on GitHub)Not mirrored: opens on GitHub3.1 KiB
references/operations/run.md(opens on GitHub)Not mirrored: opens on GitHub4.5 KiB
references/operations/troubleshoot.md(opens on GitHub)Not mirrored: opens on GitHub11.5 KiB
references/output-contract.md(opens on GitHub)Not mirrored: opens on GitHub10.4 KiB
references/platforms/deployment.md(opens on GitHub)Not mirrored: opens on GitHub13.8 KiB
references/platforms/dgx-spark.md(opens on GitHub)Not mirrored: opens on GitHub2.3 KiB
references/platforms/jetson-thor.md(opens on GitHub)Not mirrored: opens on GitHub3.2 KiB
references/platforms/readiness.md(opens on GitHub)Not mirrored: opens on GitHub4.7 KiB
references/platforms/single-gpu.md(opens on GitHub)Not mirrored: opens on GitHub18.9 KiB
references/preflight.md(opens on GitHub)Not mirrored: opens on GitHub18.1 KiB
skill-card.md(opens on GitHub)Not mirrored: opens on GitHub6.2 KiB
skill.oms.sig(opens on GitHub)Not mirrored: opens on GitHub10.2 KiB

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

What our scanner noticed· Medium risk

Phrasing that asks for actions without confirmation
Large base64-encoded blobs

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Claude API
AnthropicOfficial
Comprehensive reference for integrating Anthropic's Claude API, SDKs, and Managed Agents into your applications.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskHas scriptsGitHub stars of the source repository188.6k
Transformers
K-Dense· Community
Integrate Hugging Face Transformers for model loading, inference, and fine-tuning across NLP, vision, and audio tasks.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskGitHub stars of the source repository56.4k
Open Notebook
K-Dense· Community
Integrate with the self-hosted Open Notebook platform to automate research ingestion, context-aware chat, and AI-driven analysis.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskHas scriptsGitHub stars of the source repository56.4k
Vision Sft
Seth Hobson· Community
A structured workflow for supervised fine-tuning of vision-language models, focusing on adapter configuration and silent failure prevention.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository42.3k
LLM Evaluation
Seth Hobson· Community
A comprehensive framework for evaluating LLM application performance using automated metrics, human feedback, and LLM-as-a-judge techniques.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository42.3k
Lora Qlora Recipes
Seth Hobson· Community
Provides configuration recipes and best-practice hyperparameters for LoRA and QLoRA supervised fine-tuning.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository42.3k