Staging environment

Launch Your First Voice AI Agent in 90 Minutes

Hosted by Valentine Zavadskiy

125 students

Share this lesson

Go deeper with a course

AI for Developers: From Assistant to System Core
Valentine Zavadskiy and Olga Lavrentieva
View syllabus

What you'll learn

How voice AI agents process real-time speech: STT, LLM, TTS

In this intensive 1.5-hour session, you’ll dive into voice agents and uncover the core components that power them

Compare LiveKit, Daily, and OpenAI's voice solutions

Learn which voice framework—LiveKit, Daily, or OpenAI—best fits your specific use case

Design voice interfaces with proven production patterns

You’ll master key architecture patterns for building robust and scalable voice interfaces

Build a working voice assistant: live demo + how-to guide

You’ll see a live demo of a personal voice assistant in action and leave with a clear understanding of how to create one

Why this topic matters

AI is everywhere — but the next big leap is voice. As wearable devices and personal AI companions evolve, natural voice interaction is becoming the new standard. According to the State of Voice AI 2025 report: 👉 97% of companies already use voice technologies in some form 👉 67% say voice is fundamental to their business strategy Join us and learn how to build powerful voice-based AI systems.

You'll learn from

Valentine Zavadskiy

Co-founder at evy.so, former co-founder of Awerty & Narrative BI & Rubyroid Labs


Co-founder at evy.so — a single proactive voice assistant for teams. It speaks, listens, and remembers context across everything you work on, helping teams stay focused and productive hands-free — whether at their desks or on the go.


Software Engineer with 15+ years of experience. Serial entrepreneur with successful exit. Taught more than 1000 students how to code. Co-host of the podcast with 200+ episodes live. His current focus is on building AI solutions and exploring a unique, highly efficient way of developing software using voice.


For the past three years, Valentine has been creating commercial AI solutions where large language models (LLMs) are at the center. His journey began in a startup that developed a system allowing users to gain insights and analytics simply by talking to their data. Since then, he has worked with:

  • Different LLMs, from OpenAI to specialized models.
  • Fine-tuning models for specific business needs.
  • Designing and applying advanced patterns for effective AI interaction.


His extensive practical experience is combined with an ability to explain complex concepts in simple language and to create engaging, effective educational solutions.

Previously at

Narrative BI
Rubyroid Labs

Watch this lesson for free

By continuing, you agree to Maven's Terms and Privacy Policy.