╔══════════════════════════╗
        ║  )))  AURALIS  (((       ║
        ║   ┌───────────────┐      ║
        ║   │  ◉  ══  ◉    │      ║
        ║   │     ───       │      ║
        ║   └───────────────┘      ║
        ║    ▓▓▓▓▓▓▓▓▓▓▓▓▓        ║
        ╚══════════════════════════╝

Auralis

Voice-controlled household robot assistant with real-time intent recognition

Demo  •  Features  •  Quick Start  •  Architecture  •  Configuration  •  Development  •  Tech Stack  •  License

---

Demo

Hold the mic button, speak a command — Auralis parses intent in real-time, updates device state, and speaks a response back via TTS

---

Features

Feature	Description
Push-to-talk	Hold the mic button to capture voice; release to process
Real-time NLU	Rule-based intent engine maps utterances to structured {intent, slots, confidence} with no LLM latency
Live device dashboard	Six simulated smart-home devices update visually the moment a command is executed
WebSocket pipeline	Full-duplex WS stream between browser and backend — interim transcripts, intent events, device deltas, and TTS payloads
Waveform visualizer	Animated canvas waveform during recording
Intent inspector	Shows parsed intent, extracted slots, and confidence score for every utterance
Command history	Persistent SQLite log of every voice command with execution status
Skill registry	Six built-in skills (Lighting, Climate, Blinds, Media, Scenes, Timers) listed on the Settings page
Browser TTS	Auralis speaks its response back using the Web Speech Synthesis API
One-command setup	docker compose up --build launches the full stack

---

Quick Start

Prerequisites

• Docker Desktop or Docker Engine + Compose v2

Run

git clone https://github.com/StrikeRobot/auralis.git
cd auralis

cp .env.example .env

docker compose up --build

Open http://localhost:3000 — hold the mic button and speak.

Browser note: Web Speech API requires a secure context (HTTPS) or localhost. Chrome/Edge recommended.

---

Architecture

┌─────────────────────────┐          ┌──────────────────────────────┐
│  frontend               │          │  backend                      │
│  Next.js 14 + TS        │          │  FastAPI + Python 3.12        │
│  Tailwind + Zustand      │◄──WS────►│  WebSocket hub (events.py)   │
│  Framer Motion          │  REST    │  Intent NLU (services/intent) │
│  Web Speech API (STT)   │          │  Device engine (state machine)│
│  SpeechSynthesis (TTS)  │          │  SQLModel + SQLite            │
└─────────────────────────┘          └──────────────────────────────┘
        :3000                                    :8000

Data flow for a voice command:

1. User holds the mic button; Web Speech API streams interim transcripts to the backend via WebSocket
2. On release, the final transcript is sent as {type: "transcript", text: "...", interim: false}
3. Backend runs the utterance through the rule-based NLU; emits {type: "intent", data: {intent, slots, confidence}}
4. Device engine matches affected devices and applies state mutations; each update broadcasts {type: "device_update"}
5. Response text is generated and returned as {type: "tts_response"}; the frontend speaks it via SpeechSynthesis
6. Command is persisted to SQLite for the history timeline

---

Configuration

Variable	Default	Description
DB_PATH	/data/auralis.db	SQLite database path (inside container)
ALLOWED_ORIGINS	http://localhost:3000	CORS allowed origins (comma-separated)

---

Development

Backend

cd backend
pip install uv
uv pip install --system -e ".[dev]"
cp ../.env.example ../.env
uvicorn app.main:app --reload --port 8000

Frontend

cd frontend
npm install
cp .env.local.example .env.local
npm run dev

Tests

cd backend
pytest -v

---

Tech Stack

Layer	Technology
Frontend framework	Next.js 14 (App Router)
Language	TypeScript 5
Styling	Tailwind CSS 3
State management	Zustand 4
Animation	Framer Motion 11
Voice input	Web Speech API (browser-native STT)
Voice output	Web Speech Synthesis API (browser-native TTS)
Backend framework	FastAPI
Backend language	Python 3.12
ORM / DB	SQLModel + SQLite
Real-time	WebSocket (FastAPI native)
Container	Docker + Docker Compose

---

License

MIT © 2025 — see LICENSE for details.