菜单
Deploy Nemotron Voice Agent on Workstation (x86), Jetson Thor, or Cloud NIMs. Real-time speech-to-speech using NVIDIA ASR, TTS, LLM with WebRTC/WebSocket transport.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/autohandai/community-skills --skill nvidia-nemotron-voice-agent-deploy命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Build, convert, validate, and install Autohand extensions, including Pi adaptations.
Run Weizhena's Deep Research workflow in Autohand Code for outline generation, deep web investigation, structured evidence capture, and final research reports.
Use Aaronontheweb dotnet-skills for Claude Code-oriented .NET maintenance, refactoring, and agent workflows.
基于 SOC 职业分类
正在显示 SKILL.md
| name | nvidia-nemotron-voice-agent-deploy |
| description | Deploy Nemotron Voice Agent on Workstation (x86), Jetson Thor, or Cloud NIMs. Real-time speech-to-speech using NVIDIA ASR, TTS, LLM with WebRTC/WebSocket transport. |
| license | Apache-2.0 AND CC-BY-4.0 |
| metadata | {"author":"NVIDIA"} |
Real-time conversational AI voice agent using NVIDIA NIMs (ASR, TTS, LLM) with WebRTC (default) or WebSocket transport.
Always verify hardware first, even if user mentions a specific platform.
nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>/dev/null
| Result | Action |
|---|---|
| Command fails / No output | → Cloud NIMs |
| GPU detected | → STEP 2: Platform Detection |
cd nemotron-voice-agent
git submodule update --init
cp config/env.example .env
Export your NVIDIA API key:
export NVIDIA_API_KEY=your-api-key # Get from https://build.nvidia.com
Then edit .env:
NVIDIA_LLM_MODEL=nvidia/nemotron-3-nano-30b-a3b # Cloud model name
If user requests WebSocket transport, also add to .env:
TRANSPORT=WEBSOCKET
docker compose up --build --no-deps -d python-app ui-app
# WebRTC: http://localhost:9000
# WebSocket: http://localhost:7860/static/index.html
Note: Deployment may take 30-60 minutes on first run.
If user requests Multilingual mode, also add to .env:
ENABLE_MULTILINGUAL=true
ASR_CLOUD_FUNCTION_ID=71203149-d3b7-4460-8231-1be2543a1fca
ASR_MODEL_NAME=parakeet-rnnt-1.1b-unified-ml-cs-universal-multi-asr-streaming
Remote Access: ssh -L 9000:localhost:9000 user@host or http://<HOST_IP>:9000
uname -m # x86_64 → Workstation, aarch64 → Jetson
cat /etc/nv_tegra_release 2>/dev/null && echo "Jetson"
| Platform | Reference | Requirements |
|---|---|---|
| Workstation (x86_64) | workstation-deployment.md | 2x GPU (24GB+ VRAM), NIM containers |
| Jetson Thor (aarch64) | jetson-deployment.md | JetPack 7.0, Nemotron Speech ASR and TTS, vLLM |
Note: Multilingual mode available on Workstation with WebRTC transport only.