The Fifth Elephant 2025 Annual Conference CfP

Realtime Voice AI has disrupted the conversational voicebot landscape and made it trivial to create exciting demos. Unfortunately, deploying useful voice AI in production is an entirely different story. In this talk, we will present our findings from working with state of the art voice AI agents.

How do we balance latency, costs and scaling while ensuring the voicebot continues to be helpful? What are some common tradeoffs that teams will face? How do we manage complexity and orchestration of various actions that AI can take? It turns out the same kind of engineering maturity that defines the strongest tech teams also helps navigate the uncharted territory in the volatile field of voice AI.

Takeaway

Give a sense of the current challenges that product, engineering and business teams will face when deploying cutting-edge realtime voice agents, with pointers on how to manage these challenges.

Intended audience

This talk will benefit engineering, product, design and business teams building on top of realtime voice AI that are looking to go beyond the tech demo phase.

Bio

Atharva is an AI aficionado. He has been tinkering with AI of all modalities to figure out how to build products that deliver on the hype in production.

When he isn’t debugging like a stoic, he usually publishes strange essays online, creates grimy digital art and produces questionable beats with Indian truck horns.

His first exposure to serious software development was with the Git project, where he rewrote parts of the submodule functionality by emailing patches to the maintainer.

While at nilenso, he helped a hyperlocal delivery startup revamp their payout systems and solved data integration challenges at a non-profit building population-scale software.

links

Link to an outline on what I intend to cover:
https://www.notion.so/nilenso-software/5thEl-talk-notes-navigating-the-challenges-of-voice-AI-1fb0f0425dae8085b23ee0f956cca821?pvs=4

update: I also have a link to some extremely skeletal slides, to demonstrate the flow of the talk
https://docs.google.com/presentation/d/1gX0WovWnTwFKg3-pSPNRB9_kjQJSo_N2c0G48oSkupQ/edit?usp=sharing

Link to a blog post I wrote in January on realtime voice AI, covers more of the PoC side of things:
https://blog.nilenso.com/blog/2025/01/13/i-built-an-ai-prototype-that-can-participate-in-our-internal-meetings-in-a-week/