> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/moeru-ai/airi/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Get started with Airi in 5 minutes - from installation to your first conversation

Get your AI companion up and running in minutes. This guide will take you from installation through your first conversation.

## Prerequisites

Before you begin, make sure you have:

<CardGroup cols={2}>
  <Card title="Modern Browser" icon="browser">
    Chrome, Edge, or another Chromium-based browser with WebGPU support (for web version)
  </Card>

  <Card title="LLM API Key" icon="key">
    API key from OpenAI, Anthropic, or another supported provider
  </Card>
</CardGroup>

<Note>
  Don't have an API key? You can use local models with [Ollama](#local-models-with-ollama) or try the free tier from providers like [OpenRouter](https://openrouter.ai).
</Note>

## Choose Your Installation Method

<Tabs>
  <Tab title="Web (Fastest)">
    <Steps>
      <Step title="Open Airi Web">
        Visit [https://airi.moeru.ai](https://airi.moeru.ai) in your browser.

        <Note>
          No installation required! The web version runs entirely in your browser.
        </Note>
      </Step>

      <Step title="Grant Permissions">
        When prompted, allow microphone access for voice chat (optional but recommended).
      </Step>
    </Steps>
  </Tab>

  <Tab title="Desktop (Recommended)">
    <Steps>
      <Step title="Download">
        Download the latest release for your platform:

        <CodeGroup>
          ```bash Windows theme={null}
          # Download from GitHub releases
          https://github.com/moeru-ai/airi/releases/latest

          # Or use winget
          winget install MoeruAI.Airi
          ```

          ```bash macOS theme={null}
          # Download from GitHub releases
          https://github.com/moeru-ai/airi/releases/latest

          # Or use Homebrew
          brew install --cask airi
          ```

          ```bash Linux theme={null}
          # Download AppImage from GitHub releases
          wget https://github.com/moeru-ai/airi/releases/latest/download/airi-linux-x64.AppImage
          chmod +x airi-linux-x64.AppImage
          ./airi-linux-x64.AppImage

          # Or use Nix
          nix run github:moeru-ai/airi
          ```
        </CodeGroup>
      </Step>

      <Step title="Install">
        Run the installer for your platform. On macOS, drag Airi to your Applications folder.
      </Step>

      <Step title="Launch">
        Open Airi from your applications menu or desktop shortcut.
      </Step>
    </Steps>
  </Tab>

  <Tab title="Build from Source">
    <Steps>
      <Step title="Clone Repository">
        ```bash theme={null}
        git clone https://github.com/moeru-ai/airi.git
        cd airi
        ```
      </Step>

      <Step title="Install Dependencies">
        ```bash theme={null}
        # Install pnpm if you haven't already
        npm install -g pnpm

        # Install project dependencies
        pnpm install
        ```
      </Step>

      <Step title="Run Development Server">
        <CodeGroup>
          ```bash Web theme={null}
          pnpm dev:web
          ```

          ```bash Desktop theme={null}
          pnpm dev:tamagotchi
          ```

          ```bash Mobile theme={null}
          pnpm dev:pocket
          ```
        </CodeGroup>
      </Step>
    </Steps>
  </Tab>
</Tabs>

## Configure Your LLM Provider

<Steps>
  <Step title="Open Settings">
    Click the **Settings** icon in the sidebar or press `Cmd/Ctrl + ,`.
  </Step>

  <Step title="Navigate to Providers">
    Go to **Providers** → **LLM Providers** in the settings panel.
  </Step>

  <Step title="Add Your Provider">
    <Tabs>
      <Tab title="OpenAI">
        ```typescript theme={null}
        {
          "provider": "openai",
          "apiKey": "sk-...",
          "model": "gpt-4-turbo-preview",
          "baseURL": "https://api.openai.com/v1"
        }
        ```

        <Accordion title="Get your API key">
          1. Visit [platform.openai.com](https://platform.openai.com)
          2. Sign up or log in
          3. Navigate to **API Keys**
          4. Click **Create new secret key**
          5. Copy and save your key securely
        </Accordion>
      </Tab>

      <Tab title="Anthropic Claude">
        ```typescript theme={null}
        {
          "provider": "anthropic",
          "apiKey": "sk-ant-...",
          "model": "claude-3-opus-20240229"
        }
        ```

        <Accordion title="Get your API key">
          1. Visit [console.anthropic.com](https://console.anthropic.com)
          2. Sign up or log in
          3. Navigate to **API Keys**
          4. Click **Create Key**
          5. Copy your key
        </Accordion>
      </Tab>

      <Tab title="OpenRouter">
        ```typescript theme={null}
        {
          "provider": "openrouter",
          "apiKey": "sk-or-...",
          "model": "anthropic/claude-3.5-sonnet",
          "baseURL": "https://openrouter.ai/api/v1"
        }
        ```

        <Accordion title="Get your API key">
          1. Visit [openrouter.ai](https://openrouter.ai)
          2. Sign up or log in
          3. Navigate to **Keys**
          4. Create a new key
          5. Fund your account with credits (many models have free tiers!)
        </Accordion>
      </Tab>

      <Tab title="Ollama (Local)">
        ```typescript theme={null}
        {
          "provider": "ollama",
          "baseURL": "http://localhost:11434",
          "model": "llama3.2:latest"
        }
        ```

        <Accordion title="Install Ollama">
          1. Install Ollama from [ollama.ai](https://ollama.ai)
          2. Pull a model: `ollama pull llama3.2`
          3. Verify it's running: `ollama list`
          4. Use `http://localhost:11434` as the base URL
        </Accordion>
      </Tab>
    </Tabs>
  </Step>

  <Step title="Test Connection">
    Click **Test Connection** to verify your configuration. You should see a success message.

    <Warning>
      If the test fails, double-check your API key and base URL. Make sure there are no extra spaces or characters.
    </Warning>
  </Step>
</Steps>

## Optional: Configure Voice Synthesis

For voice chat, set up a text-to-speech provider:

<Steps>
  <Step title="Navigate to Voice Settings">
    In **Settings** → **Voice** → **Speech Synthesis**.
  </Step>

  <Step title="Choose a Provider">
    <Tabs>
      <Tab title="ElevenLabs (Best Quality)">
        ```typescript theme={null}
        {
          "provider": "elevenlabs",
          "apiKey": "...",
          "voiceId": "21m00Tcm4TlvDq8ikWAM",
          "model": "eleven_turbo_v2"
        }
        ```

        Free tier: 10,000 characters/month
      </Tab>

      <Tab title="OpenAI TTS">
        ```typescript theme={null}
        {
          "provider": "openai",
          "apiKey": "sk-...",
          "voice": "alloy",
          "model": "tts-1"
        }
        ```

        Uses your OpenAI API key
      </Tab>

      <Tab title="Browser TTS (Free)">
        ```typescript theme={null}
        {
          "provider": "browser",
          "voice": "Google US English"
        }
        ```

        Built-in browser voices (free, no API key needed)
      </Tab>
    </Tabs>
  </Step>

  <Step title="Test Voice">
    Click **Test Voice** to hear a sample. Adjust settings like speed and pitch if needed.
  </Step>
</Steps>

## Have Your First Conversation

<Steps>
  <Step title="Navigate to Chat">
    Click the **Chat** icon in the sidebar or press `Cmd/Ctrl + 1`.
  </Step>

  <Step title="Start Talking">
    <Tabs>
      <Tab title="Text Chat">
        Type your message in the input box and press Enter:

        ```
        Hi! Tell me about yourself.
        ```
      </Tab>

      <Tab title="Voice Chat">
        1. Click the **microphone** icon
        2. Grant microphone permission if prompted
        3. Start speaking naturally
        4. Airi will respond with voice
      </Tab>
    </Tabs>
  </Step>

  <Step title="Try Different Commands">
    Experiment with various interactions:

    * `What can you help me with?`
    * `Tell me a joke`
    * `What's the weather like?` (requires integration)
    * `Remember that my favorite color is blue`
  </Step>
</Steps>

<Note>
  Your conversation history is saved locally and will persist across sessions. Airi uses this context to remember your preferences and previous discussions.
</Note>

## Troubleshooting

<AccordionGroup>
  <Accordion title="API key not working">
    * Verify your API key is correct (no extra spaces)
    * Check that your account has credits/quota remaining
    * For OpenAI, ensure billing is set up
    * Try regenerating your API key
  </Accordion>

  <Accordion title="Voice chat not working">
    * Ensure microphone permissions are granted
    * Check your browser supports Web Audio API
    * Verify TTS provider is configured
    * Try the Browser TTS provider as a fallback
  </Accordion>

  <Accordion title="Slow responses">
    * Some models are slower than others (try GPT-3.5-turbo or Claude Haiku)
    * Check your internet connection
    * For local models, ensure adequate GPU/CPU resources
  </Accordion>

  <Accordion title="Desktop app won't launch">
    * On macOS, right-click and select "Open" to bypass Gatekeeper
    * On Windows, SmartScreen may require clicking "More info" → "Run anyway"
    * On Linux, ensure the AppImage is executable: `chmod +x airi.AppImage`
  </Accordion>
</AccordionGroup>

## Next Steps

<CardGroup cols={2}>
  <Card title="Customize Your Character" icon="user" href="/features/character-models">
    Import Live2D or VRM models and customize personality
  </Card>

  <Card title="Explore Integrations" icon="plug" href="/integrations/overview">
    Connect to Discord, Telegram, or Minecraft
  </Card>

  <Card title="Configure Memory" icon="brain" href="/features/memory-system">
    Set up persistent memory and context management
  </Card>

  <Card title="Join Community" icon="users" href="https://discord.gg/TgQ3Cu2F7A">
    Get help and share your experience on Discord
  </Card>
</CardGroup>