OpenAI API Platform Setup

1. 1. Go to https://platform.openai.com
2. 2. Click Sign Up
3. 3. Create the account using an email address and password
4. 4. Open the verification email from OpenAI
5. 5. Enter the verification code to continue

1. 1. During setup, OpenAI will prompt for an Organization
2. 2. Optionally invite team members (can be skipped initially)
3. 3. Create a Project Name

1. 1. Open the selected project
2. 2. Navigate to API Keys
3. 3. Click Create API Key
4. 4. When prompted for Permissions, select All
5. 5. Copy the key immediately and store it securely

1. 1. Open the project's Billing area
2. 2. Add funds or enable the account's payment method
3. 3. Note: new accounts often start with a low funding limit (e.g., $20)

1. 1. Click the Project Name at the top of the screen
2. 2. Select Manage Projects
3. 3. Click the correct project in the list
4. 4. In the left menu, click Limits
5. 5. Under Model Usage, click Edit
6. 6. Enable all models whose names include the word realtime
7. 7. Click Save

1. 1. Stay on the Limits screen
2. 2. Click Edit Budget
3. 3. Enter a monthly budget appropriate for expected usage
4. 4. Click Save

Once the API Platform account is working, place the API key into your VNS CallStart response as the openAIToken value:

{
  "VoiceElements_Instructions": {
    "openAIUrl": "wss://api.openai.com/v1/realtime?model=gpt-realtime",
    "openAIToken": "sk-YOUR_OPENAI_API_KEY",
    ...
  }
}

If the API key does not work, review the error returned in your VNS logs, especially information captured at or near CallEnd.