Abhishek Sharma
Abhishek is a senior technical product marketing manager at Telnyx, an infra company for real time communications.
South San Francisco, California, United States
Actions
Abhishek Sharma is a Senior Technical Product Marketing Manager at Telnyx, where he focuses on voice AI infrastructure and the economics of real-time AI workloads.
He previously worked on voice AI at Vapi, one of the first developer platforms for building voice agents, and before that at Microsoft.
He has spent the last 5 years in the weeds of AI applications, from streaming architecture to provider routing to the cost-per-minute math that determines whether an AI agent scales or dies.
At work he runs a multi-agent system in production that handles research, content drafting, and operational workflows across multiple platforms, giving him a builder's view of where AI systems break under real load.
His work has been featured in Business Insider, BambooHR, Process Reporter, and Linguistic News, and he writes regularly about voice AI infrastructure, latency, and the shift from demo to production.
Links
Area of Expertise
Topics
Building Voice AI That Doesn't Fall Apart in Production
Real-time voice AI agents look magical in a demo and then fall apart the moment you put them in front of real users on a real phone line. This talk is a field guide to what breaks and how to fix it, drawn from shipping voice AI infrastructure at Vapi and Telnyx and running production agents at scale.
We'll walk through the architecture of a production voice agent pipeline, streaming speech-to-text, LLM orchestration, streaming text-to-speech, and the failure modes that don't show up until you hit scale.
Some topics we'd cover in the session:
- Latency budgets and where they leak. First-token latency, TTS time-to-first-audio, and the cascading delays that turn a snappy agent into a slow one. How to measure each hop and where the real costs hide.
- Interruption handling and full-duplex vs half-duplex. Barge-in, echo, overlapping speech, and why most "real-time" implementations aren't actually real-time.
- Multi-provider routing and fallback. Why single-provider voice AI is fragile, how to route across STT/TTS providers based on latency, cost, and quality, and what the actual tradeoffs look like in production data.
- The cost-per-minute math nobody publishes. STT, LLM tokens, and TTS each have different pricing models and unit economics. We'll break down what a real voice agent minute actually costs at scale and where inference economics are heading.
- What changes when you go from 10 calls to 10,000. Concurrency, queueing, SIP/media handling, regional latency, and the infrastructure decisions that don't matter until they suddenly do
Abhishek Sharma
Abhishek is a senior technical product marketing manager at Telnyx, an infra company for real time communications.
South San Francisco, California, United States
Links
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top