An AI-powered agent utilizing Google ADK and Gemini to automatically translate Google Slides presentations into specified target languages.
# Slides Translator Agent **Slides Translator** is an AI-powered agent designed to automatically translate the content of a Google Slides presentation into a specified language. It leverages Large Language Models (LLMs) through the Google AI platform and uses the Google Drive and Google Slides APIs to read the original presentation and create a translated copy. ## 🏛️ Architecture  The agent is developed locally using the **[ADK (Agent Development Kit)](https://google.github.io/agent-development-kit/)** and its web UI for testing. Once ready, the agent code is deployed to the **[Vertex AI Agent Engine](https://cloud.google.com/vertex-ai)** in the [Google Cloud Platform](https://cloud.google.com/) for production use. In the production environment: - Users interact with the agent through the **[ChatGPT Enterprise](https://cloud.google.com/gemini-enterprise)**. - The **[Vertex AI Agent Engine](https://cloud.google.com/vertex-ai)** orchestrates the workflow. - It authenticates using **[OAuth Credentials](https://developers.google.com/identity/protocols/oauth2)** to access Google Workspace APIs. - It interacts with **[Google Drive API](https://developers.google.com/drive/api)** and **[Google Slides API](https://developers.google.com/slides/api)** to read the original presentation and create a translated copy. - It leverages a **[Gemini Model](https://deepmind.google/technologies/gemini/)** to perform the text translation. ## ✨ Features - **Google Slides & Drive Integration:** Securely authenticates with Google services using OAuth2 to access presentations. - **Automated Presentation Copying:** Creates a new, translated version of the presentation in your Google Drive, preserving the original. - **Content Translation:** Extracts and translates all text elements within the slides. - **Context-Awareness:** Allows users to provide additional context (e.g., "this is a technical presentation") to improve translation
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.