本文へスキップ
TakoAPI
スキル一覧に戻る

jetson-cuda-voice

nikil511 作

DevOps & Cloud
314ダウンロード数はclawskills.shが公開している値です
0閲覧数
0件のいいねサインインするとこのスキルにいいねできます
—まだ評価がありません
あなたの評価

概要

Fully offline, CUDA-accelerated local voice assistant pipeline for NVIDIA Jetson.

説明

このスキルでできること

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.

使いどころ

  • 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

ワークフロー例

入力

User says 'Hey Jarvis, what's the weather like today?'

エージェント
  1. 1

    openWakeWord detects the wake phrase and triggers a two-tone beep with blue LED

  2. 2

    _measure_ambient() samples 480ms of room noise to set dynamic VAD thresholds

  3. 3

    transcribe_stream() captures speech via VAD, sends audio to whisper.cpp CUDA server, returns transcript

  4. 4

    ask_llm() sends transcript plus 20-turn conversation history to OpenRouter API and receives response

  5. 5

    Piper TTS synthesizes the response offline and aplay outputs it while LED shows cyan then off

出力

Spoken answer played through ALSA speaker, LEDs return to off state

要件

  • 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

インストール

clawhub install nikil511/jetson-cuda-voice

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク