SillyTavern

About

SillyTavern is a locally installed user interface that allows you to interact with text generation LLMs, image generation engines, and TTS voice models. Integration with the AI/ML API currently applies only to LLMs.

Installing SillyTavern (Fresh Setup)

Windows (Recommended: SillyTavern Launcher)

1. Make sure Node.js (latest LTS) and Git are installed.

2. Open Run (Win + R) and execute:

   Copy

   cmd /c winget install -e --id Git.Git

3. In File Explorer, navigate to a non‑system folder (e.g. C:\SillyTavern), click the address bar, type cmd and press Enter.

4. Clone the release branch and launch SillyTavern:

   Copy

   git clone https://github.com/SillyTavern/SillyTavern -b release
   cd SillyTavern
   start Start.bat

5. After the installer finishes, a browser window will open with the SillyTavern interface.

Linux / macOS

1. Install Git and Node.js (via your distro’s package manager or Homebrew).

2. In a terminal, run:

   Copy

   # Clone the release branch
   git clone https://github.com/SillyTavern/SillyTavern -b release
   cd SillyTavern

3. Make the startup script executable and run it:

   Copy

   chmod +x start.sh
   ./start.sh

4. Open your browser to the URL shown in the console (default: http://localhost:8000).

Connecting AI/ML API in SillyTavern

Step 1. Launch SillyTavern → Set Persona

• On first launch you'll see "Welcome to SillyTavern"

• Enter AI/ML API as the Persona Name for example

• Click Save

This step is required to unlock the chat UI.

Step 2. Go to Connection Settings

• Open ⚙ Settings tab → Connection Profile (Second tab)

• Configure:

  • API: Chat Completion

  • Chat Completion Source: AI/ML API

Step 3. Enter API Key

1. Copy your API key from https://aimlapi.com/app/keys

2. Paste into the AI/ML API Key field.

3. Click 🔑 icon to save — it should show a timestamp.

Step 4. Choose a model

Click the dropdown next to AI/ML Model and pick any model such as:

• gpt-4o-mini-2024-07-18

• claude-3-5-sonnet

• gemini-1.5-flash

Step 5. Test Connection

Click Connect and then the Test Message.

• You should see API connection successful.

• 🟢 Status: Valid.

💬 Step 6. Send a Message

Use the input box below to send a test message:

If all is set up, you’ll see the assistant reply like this:

🎉 Step 7. Done – You’re All Set!

You’re now connected to AI/ML API and can start chatting with any of 200+ models.

✅ Config checklist

🔗 Internal Links

• AI/ML API Model Catalog

• Your API Keys Page

• Community & Feedback