Free Lesson

Building a Production Voice Agent End-to-End w/ Deepgram

Part of The AI Builders Summit

Hosted by Kiriti & Aish and Ed Charbeneau

Mon, Aug 24, 2026

5:00 PM UTC (1 hour)

Virtual (Zoom)

Free to join

Invite your network

Go deeper with a course

Featured in Lenny’s List
Building Agentic AI Applications with a Problem-First Approach
Aishwarya Naresh Reganti and Kiriti Badam
View syllabus

What you'll learn

Build a voice agent end-to-end

Wire speech-to-text, the model, and text-to-speech into one working agent you can actually ship

Design for real-time latency at scale

The streaming architecture that keeps a voice agent fast enough to feel natural under real production load.

Handle interruptions and barge-in

Voice UX patterns for when users talk over the agent, so the conversation keeps flowing naturally.

Evaluate speech models for enterprise

How to judge accuracy, latency, and cost when choosing a speech stack for production use.

Why this topic matters

Voice is fast becoming a primary interface for AI, but most voice demos fall apart the moment real users show up: latency creeps in, people talk over the agent, accents and background noise break the transcript. This session walks through building a voice agent end-to-end, from speech-to-text to response to speech, with the architecture and trade-offs that actually hold up at enterprise scale.

You'll learn from

Kiriti & Aish

AI practitioners with combined 20+ years of experience

Aishwarya Naresh Reganti is the founder and CEO of LevelUp Labs, a human-first AI startup that helps develop and deploy production-ready generative AI solutions for mid to large enterprise clients. With over 9 years of experience in machine learning, she has published more than 35 research papers at top-tier AI conferences, including NeurIPS, AAAI, and CVPR.

Kiriti Badam is a member of the technical staff at OpenAI Codex, with over a decade of experience designing high-impact enterprise AI systems. He specializes in AI-centric infrastructure, with deep expertise in large-scale compute, data engineering, and storage systems.

Ed Charbeneau

Developer Relations Lead

Ed Charbeneau leads developer relations at Deepgram, the voice AI platform behind many production speech-to-text and voice-agent systems. A Microsoft MVP and longtime developer advocate, he has spent more than a decade helping engineers build and ship real applications, and he speaks regularly at major developer conferences around the world.

See all products from Kiriti & Aish

Sign up to join this lesson

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