jetson-cuda-voice
nikil511 제작
DevOps & Cloud요약
Fully offline, CUDA-accelerated local voice assistant pipeline for NVIDIA Jetson.
설명
이 스킬이 하는 일
Offline voice assistant pipeline for NVIDIA Jetson devices. Chains wake word detection, voice activity detection, GPU-accelerated speech-to-text, LLM inference, and neural TTS. Only the LLM call requires internet access.
Running STT and TTS fully on-device eliminates round-trip latency and keeps audio data off third-party servers, which cloud-dependent pipelines cannot offer.
사용 시점
- Hands-free home automation control on a Jetson-based device
- Private voice queries without sending audio to cloud STT services
- Multilingual voice assistant that auto-detects spoken language
- Always-on desk assistant with LED visual state feedback
- Embedded voice interface for robotics or kiosk projects
예시 워크플로
User says 'Hey Jarvis, what's the weather like today?'
- 1
openWakeWord detects the wake phrase and triggers a two-tone beep with blue LED
- 2
_measure_ambient() samples 480ms of room noise to set dynamic VAD thresholds
- 3
transcribe_stream() captures speech via VAD, sends audio to whisper.cpp CUDA server, returns transcript
- 4
ask_llm() sends transcript plus 20-turn conversation history to OpenRouter API and receives response
- 5
Piper TTS synthesizes the response offline and aplay outputs it while LED shows cyan then off
Spoken answer played through ALSA speaker, LEDs return to off state
요구 사항
- OPENROUTER_API_KEY environment variable
- OpenRouter account (or self-hosted OpenAI-compatible LLM endpoint)
- NVIDIA Jetson device with JetPack installed
- ReSpeaker USB Mic Array v1.0 or compatible ALSA mic
설치
clawhub install nikil511/jetson-cuda-voiceCLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.