• Home
  • Building Live Voice Agents with Google’s ADK

Creating a Voice Agent with Google’s ADK

Course Information

  • Sessions 2 days
  • Duration 157.5 hrs
  • Level Intermediate
  • Assessment NA

Venue

12 Woodlands Square #07-85/86/87 Woods Square Tower 1, Singapore 737715. 5 mins walk from Woodlands (NS9) MRT station.

The venue is disabled-friendly.

Download Course Brochure

Certification

  • Certificate of Completion from Tertiary Infotech - Upon meeting at least 75% attendance and passing the assessment(s), participants will receive a Certificate of Completion from Tertiary Infotech.

Additional Information

Duration

2 months (Full Time)

Assessment

3 hours online assessment after each module

Class (No of teacher : student): 1:20

Intake

  • 3 Nov 2025 to 29 Sep 2026
  • 4 May 2026 to 26 June 2026
  • 2 Jan 2026 to 2 Mar 2026
  • 2 Mar 2026 to 27 Apr 2026

Enrolment Requirement

  • Age: 21 years old and above
  • Language Proficiency: At least C6 for GCE "O" Level English
  • Academic: At least C6 for GCE "O" Level in any 3 subjects

Graduation Requirement

  • Attendance: 75%
  • Assessment: Passed

Building Live Voice Agents with Google’s ADK

Course Code: C881

Be the first to review this product

What's This Course About

Unlock the power of conversational AI with this hands-on course on Building Live Voice Agents with Google's Agent Development Kit (ADK). Starting from foundational concepts, you will set up the ADK environment, configure the Gemini model, and build your first voice agent capable of real-time interactions with Google Search integration. Through practical exercises, you will master the tool-calling flow, debug agent responses, and test live voice interactions using the ADK Web UI — giving you the confidence to create intelligent, responsive voice agents from scratch.

Take your skills further by implementing persistent memory, structured outputs, custom tools, and safety guardrails to build robust, production-grade voice systems. You will explore advanced multi-agent coordination by constructing a podcast agent that generates multi-speaker scripts and converts them to audio using Gemini text-to-speech. The course culminates with deploying your agents on Vertex AI, equipping you with the expertise to implement security, monitoring, and scalable practices essential for real-world AI voice applications.

WSQ Funding

Full Fee $350.00 Before GST
GST $31.50 9% of fee
Baseline Nett $206.50 SG/PR age 21+ · 50% funded
MCES / SME Nett $136.50 SG age 40+ · 70% funded
Funding and Grant Applications

No funding is available for this course.

Course Fee

$350.00 (GST-exclusive)
$381.50 (GST-inclusive)

Course Date

* Required Fields

Additional Note

Please bring your own laptop for hands-on training. If you don't have laptop, we can provide spare laptop for training use.

Post-Course Support

  • We provide free consultation related to the subject matter after the course.
  • Please email your queries to enquiry@tertiaryinfotech.com and we will forward your queries to the subject matter experts.

Cancellation & Reschedule Policy

  • You can register your interest without upfront payment. There is no penalty for withdrawal of the course before the class commences.
  • We reserve the right to cancel or re-schedule the course due to unforeseen circumstances. If the course is cancelled, we will refund 100% for any paid amount.
  • Note the venue of the training is subject to changes due to availability of the classroom.

Course Details

Course Details

What You'll Learn

Topic 1: Building Your First Voice Agent with ADK

  • Introduction to Google ADK architecture (model, tools, sessions, state)
  • Set up ADK environment and create a basic agent
  • Define agent instructions and configure Gemini model
  • Connect the agent to Google Search
  • Understand tool-calling flow and execution logs
  • Test live voice interactions in the ADK Web UI
  • Debug tool selection and response handling

Topic 2: Memory, Tools, Structured Output & Guardrails

  • Use sessions and state for short-term conversation tracking
  • Implement persistent memory for long-term recall
  • Share context between tools
  • Create and integrate custom tools and external APIs
  • Define schemas for structured research reports
  • Rewrite agent instructions to act as a coordinator
  • Save structured outputs as markdown files
  • Add guardrails using callbacks

Topic 3: Advanced Voice Systems & Production Deployment

  • Build a podcast agent using multi-agent coordination
  • Combine schemas, callbacks, and dedicated audio agents
  • Generate multi-speaker scripts
  • Convert scripts to audio using Gemini text-to-speech
  • Create scalable episode generation workflows
  • Add persistent memory and reliability testing
  • Deploy agents on Vertex AI
  • Implement security, monitoring, and safe scaling practices

Course Info

Promotion Code

Your will get 10% discount voucher for 2nd course onwards if you write us a Google review.

Minimum Entry Requirement

Knowledge and Skills

  • Able to operate using computer functions
  • Minimum 3 GCE ‘O’ Levels Passes including English or WPL Level 5 (Average of Reading, Listening, Speaking & Writing Scores)

Attitude

  • Positive Learning Attitude
  • Enthusiastic Learner

Experience

  • Minimum of 1 year of working experience.

Target Age Group: 21-65 years old

Minimum Software/Hardware Requirement

Software:

You can download and install the following software:

Hardware: Windows and Mac Laptops

Job Roles

Job Roles

  • Frontend Developers
  • Web Developers

Trainers

Trainers

Mohamed Afiq: Mohamed Afiq is a ACTA certifed trainer. Mohamed Afiq startup CTO for 3 years building proprietary delivery system from scratch and then managing a team of 20 developers. He builted multiple web apps using MEAN or similar stacks. He is also a founder and sole developer for PlayTours: https://playtours.app/ . He leads instructor at CodeNinja, teaching coding to kids 9-16 years old and teach adults front-end and back-end for web development. Breeze: Breeze has around 10+ years of experience in UI and Front End Development. He has worked on various projects involving Single Page Applications, E-Commerce, Responsive Web Design, Dashboard Development, Website Development and Mobile App Development using tools like Angular.JS, Backbone.JS, Ractive.JS, Twitter Boostrap, Zurb Foundation, Gulp, SASS, LESS, Underscore.JS, JQuery, Mocha, Cucumber etc. His project experience has given him the opportunity to work on various domains involving finance, telco, education, retail, healthcare, auto-mobile and tourism.  

Review

Write Your Own Review

You're reviewing: Building Live Voice Agents with Google’s ADK