Skip to main content
Google Vertex AI is Google Cloud’s fully managed AI platform that provides access to Gemini and other foundation models. This guide shows how to set up Google Vertex AI and integrate it with Emby.

Prerequisites

  • A Google Cloud account with billing enabled
  • Emby account (Pro plan required for provider keys) or self-hosted instance (free)

Overview

Google Vertex AI provides access to Google’s latest AI models including Gemini Pro, Gemini Flash, and other foundation models with enterprise-grade security and scalability. Emby integrates seamlessly with Vertex AI deployments.

Create Google Cloud Project & Enable Vertex AI

1

Create or Select a Google Cloud Project

  1. Go to the Google Cloud Console
  2. Click on the project dropdown at the top of the page
  3. Click New Project or select an existing project
  4. If creating new:
    • Enter a Project name
    • Select a Billing account
    • Click Create
2

Enable Vertex AI API

  1. In the Google Cloud Console, navigate to APIs & Services > Library
  2. Search for Vertex AI API
  3. Click on Vertex AI API
  4. Click Enable
  5. Wait for the API to be enabled (usually takes a few seconds)
3

Create Service Account

  1. Navigate to IAM & Admin > Service Accounts
  2. Click Create Service Account
  3. Configure the service account:
    • Service account name: Enter a name (e.g., emby-vertex-ai)
    • Service account ID: Auto-generated
    • Description: Optional description
  4. Click Create and Continue
  5. Grant the following role:
    • Vertex AI User (roles/aiplatform.user)
  6. Click Continue, then Done
4

Generate API Key (Service Account Key)

  1. In the Service Accounts list, find your newly created service account
  2. Click on the service account email
  3. Go to the Keys tab
  4. Click Add Key > Create new key
  5. Select JSON as the key type
  6. Click Create
  7. Important: The JSON key file will be downloaded automatically - keep it secure!
The JSON file contains your credentials and looks like this:
{
  "type": "service_account",
  "project_id": "your-project-id",
  "private_key_id": "...",
  "private_key": "...",
  "client_email": "...",
  ...
}
5

Note Your Project ID

You’ll need your Google Cloud Project ID for the integration. You can find it:
  • In the downloaded JSON key file (project_id field)
  • In the Google Cloud Console header
  • On the project dashboard

Add to Emby

1
  1. Log into Emby Dashboard
  2. Select your organization and project
  3. Go to Provider Keys in the sidebar
2

Add Google Vertex AI Provider Key

  1. Click Add for Google Vertex AI
  2. Enter your Project ID from Google Cloud
  3. Upload or paste the contents of your Service Account JSON key file
  4. Select your preferred Region (e.g., us-central1, europe-west1, asia-southeast1)
  5. Click Add Key
The system will validate your credentials and confirm the connection.
3

Test the Integration

Test your integration with a simple API call:
curl -X POST https://dev.emby.ai/v1/chat/completions \
  -H "Authorization: Bearer EMBY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "vertex/gemini-3.0-flash",
    "messages": [
      {
        "role": "user",
        "content": "Hello from Google Vertex AI!"
      }
    ]
  }'
Replace EMBY_API_KEY with your Emby API key.

Available Models

Once configured, you can access Google Vertex AI models through Emby:
  • Gemini 3.0 Flash: vertex/gemini-3.0-flash
  • Gemini 3.0: vertex/gemini-3.0
  • Gemini 2.0 Flash: vertex/gemini-2.0-flash-exp
Note: Model availability may vary by region. Check the Google Cloud documentation for the latest model availability. Browse all available models at emby.ai/models

Troubleshooting

”Permission denied” error

  • Verify your service account has the Vertex AI User role
  • Check that the Vertex AI API is enabled in your project
  • Ensure your service account key is valid and not expired

”Project not found” error

  • Verify the project ID is correct
  • Ensure billing is enabled for your Google Cloud project
  • Check that you have access to the project

”Model not available” error

Rate limiting

  • Google Vertex AI has quota limits per project and region
  • Monitor usage in the Google Cloud Console under Vertex AI > Quotas
  • Request quota increases through the Google Cloud Console if needed

Region availability

  • Not all models are available in all regions
  • Check Vertex AI locations for model availability
  • Consider using multiple regions for better availability

Need Help?