Build real-time voice agents with Google’s Agent Development Kit (ADK) that can carry natural, real-time conversations while connecting to external tools and data.
We'd like to know you better so we can create more relevant courses. What do you do for work?
Instructors: Lavi Nigam, Sita Lakshmi Sangameswaran
Build real-time voice agents with Google’s Agent Development Kit (ADK) that can carry natural, real-time conversations while connecting to external tools and data.
Design multi-agent systems that use memory, tools, and orchestration patterns to coordinate specialized agents like planners, researchers, and writers.
Take agents to production by adding guardrails, persistent memory, automated evaluations, and review methods for deploying on Google Cloud’s Vertex AI Agent Engine.
Join our new short course, Building Live Voice Agents with Google’s ADK! Learn from Lavi Nigam and Sita Lakshmi Sangameswaran, Machine Learning Engineers at Google.
You’ll learn how to build and deploy AI agents with Google’s open source Agent Development Kit (ADK). ADK provides modular components such as models, tools, memory, and orchestration, that make it easier to create both simple and complex systems.
You’ll start by building a voice agent that takes speech input, reasons with an LLM, and responds with voice output. Then you’ll work with sessions, state, and memory, and extend your agents with tools and APIs to perform real-world tasks.
Next, you’ll add callbacks and guardrails for reliability and orchestrate specialized agents like planners and researchers. You’ll build a podcast agent that researches a topic, drafts a conversational script, and produces multi-speaker audio with Gemini text-to-speech models. Then, you’ll build in guardrails to secure and optimize your agents before reviewing methods for deploying them into production.
In detail, you’ll:
This course is ideal for AI builders seeking to develop agents that extend beyond text. If you’re interested in building voice-based applications like a podcast, adding voice feedback to an agent, coordinating multiple agents, or building production-ready systems, this course will give you the hands-on foundation you need.
Introduction
Running Voice Agents on DeepLearning.AI
Build your first agent
ADK primitives - Session, State, and Memory
Tools for your agent
Adding a research agent
Instruction tuning and guardrails
Multi-agent orchestration
[Optional] Productionize your agent
Conclusion
Extra resources
Quiz
Graded・Quiz
・8 minsCourse access is free for a limited time during the DeepLearning.AI learning platform beta!
Keep learning with updates on curated AI news, courses, and events, as well as Andrew’s thoughts from DeepLearning.AI!