Individual skill

nemotron-voice-agent-builder

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.

skills/nemotron-voice-agent-builder/SKILL.md

Read pinned source

Source commit fce3cca4170be75e82c64920654d56ee2811b005

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: No
Observed behavior: Instructions only
Last checked: Nov 9, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 3,931
Repository last updated: Nov 11, 2026
License: Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

agent-skills Repository topic
agentic-ai Repository topic
ai-agents Repository topic
claude-code Repository topic
codex Repository topic
coding-agents Repository topic
cuda Repository topic
developer-tools Repository topic
llm Repository topic
omniverse Repository topic
devops Derived category
devops-containers Derived category

Declared tags are partial or unavailable.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

BENCHMARK.mddoc · 10,861 bytes
SKILL.mdcore · 3,395 bytes
evals/EVAL.mddoc · 2,872 bytes
evals/evals.jsonasset · 4,753 bytes
references/domain/agent-behavior.mddoc · 3,125 bytes
references/domain/speech-customization.mddoc · 8,421 bytes
references/frameworks/livekit.mddoc · 6,131 bytes
references/frameworks/omni.mddoc · 7,961 bytes
references/frameworks/pipecat.mddoc · 5,394 bytes
references/intake.mddoc · 8,526 bytes
references/models/asr.mddoc · 7,815 bytes
references/models/catalog.mddoc · 4,283 bytes
references/models/language-routing.mddoc · 5,698 bytes
references/models/llm.mddoc · 18,771 bytes
references/models/tts.mddoc · 5,831 bytes
references/networking/remote-webrtc.mddoc · 5,095 bytes
references/operations/iterate.mddoc · 4,676 bytes
references/operations/observability.mddoc · 3,170 bytes
references/operations/run.mddoc · 4,593 bytes
references/operations/troubleshoot.mddoc · 11,767 bytes
references/output-contract.mddoc · 10,608 bytes
references/platforms/deployment.mddoc · 14,090 bytes
references/platforms/dgx-spark.mddoc · 2,387 bytes
references/platforms/jetson-thor.mddoc · 3,245 bytes
references/platforms/readiness.mddoc · 4,773 bytes
references/platforms/single-gpu.mddoc · 19,381 bytes
references/preflight.mddoc · 18,547 bytes
skill-card.mddoc · 6,370 bytes
skill.oms.sigasset · 10,477 bytes

Read excerpt


# Create Voice Agent

Creates a working NVIDIA voice agent or updates an existing project:

- **Cascaded**: ASR transcribes, a text LLM answers, TTS speaks.
- **Omni**: one audio-in LLM replaces ASR and the text LLM. TTS still speaks.

## When to Use This Skill

Use this skill when the user wants to build, scaffold, configure, refine, or fix an
NVIDIA voice agent — a real-time speech pipeline with audio input and spoken output — on
Pipecat or LiveKit. This covers Cascaded (ASR → LLM → TTS) and Omni (audio-in LLM + TTS)
pipelines, speech customization (ASR word boosting, TTS pronunciation), multilingual
routing, and cloud or local deployment (NIM, vLLM, NeMo-Speech.cpp) on workstations, DGX