Skip to main content

Overview

GoogleImageGenService provides high-quality image generation capabilities using Google’s Gemini image models. It supports generating multiple images from text prompts with various customization options and advanced prompt understanding for photorealistic and artistic image creation.

Google Image Generation API Reference

Pipecat’s API methods for Google image generation

Example Implementation

Browse examples using Google image generation

Gemini Image Generation Documentation

Official Google Gemini image generation documentation

Google Cloud Console

Access Gemini models and manage API keys

Installation

To use Google image generation services, install the required dependencies:

Prerequisites

Google Cloud Setup

Before using Google image generation services, you need:
  1. Google Cloud Account: Set up at Google Cloud Console
  2. API Key: Generate a Google API key with Gemini API access
  3. Project Configuration: Enable Gemini API for your project
  4. Model Access: Ensure access to Gemini image models

Required Environment Variables

  • GOOGLE_API_KEY: Your Google API key for authentication

Configuration

str
required
Google AI API key for authentication.
InputParams
default:"None"
deprecated
Deprecated since 0.0.105, removed in 2.0.0. Use settings=GoogleImageGenService.Settings(...) instead.
Any
default:"None"
HTTP options for the Google AI client.
GoogleImageGenService.Settings
default:"None"
Runtime-configurable generation settings. See Settings below.

Settings

Runtime-configurable settings passed via the settings constructor argument using GoogleImageGenService.Settings(...). See Service Settings for details.

Usage

Basic Setup

With Settings

Notes

  • RGB output: Generated images are converted to RGB format for compatibility with output transports that render RGB video by default.
  • Sequential generation: When number_of_images is greater than 1, each image is generated in a separate request, processed one after another.
  • No HTTP session needed: Google returns image data directly in the API response, so no separate HTTP session is required for downloading.
  • Metrics support: Google image generation supports TTFB metrics tracking.