LangChain NY Meetup: How to Evaluate Voice Agents

​Join us for an evening in New York with Caroline di Vittorio, the Software Engineer leading the charge on voice agents at LangChain, and Rohit and Jane form Deepgram, a voice AI platform that provides high-speed, accurate speech-to-text (STT) and text-to-speech (TTS) services for developers and enterprises.

​In this practical session, Caroline will first show how to evaluate voice agents across three dimensions: execution, outcomes, and experience. You’ll learn how to inspect the full interaction, measure whether the agent achieved its intended goal, and identify voice-specific issues such as latency, interruptions, awkward pauses, and conversational friction.

Then, Jane and Rohit will share how deepgram built Flux text-to-speech (TTS). Jane will speak to their experience designing and implementing a conversation-oriented API. Rohit will explain the inference side of things: the orchestration process and how they run all of it with low latency on a single GPU.

​This meetup is designed for developers and technical teams building voice agents and looking for a more complete way to measure, debug, and improve their performance in production.

​Agenda ⏰
6:00 PM: Welcome + Food/Drinks
6:30 PM: Presentation with Caroline (LangChain) - How to Evaluate Voice Agents: Execution, outcomes and experience
6:50 PM: Q&A
7:00 PM: Presentation with Rohit and Jane (Deepgram) - Building and launching Flux Text-to-Speech (TTS)
7:15 PM: Q&A
7:25 PM: Networking
8:30 PM: Event Ends

Event info:
​🎤 Please note this event is fully in-person and will not be live-streamed or recorded.
​​📍 Location: Address is in Manhattan and will be send out to approved registrants.
​🎟️ We can only admit guests with approved registrations. If you’re still on the waitlist or haven’t received a confirmation yet, please stay tuned for future events—but please sit this one out.

​About the host:
LangChain enables every company to own their intelligence. LangChain's open, model-agnostic harnesses give teams choice and control over how they build their agent architecture. LangSmith brings testing, deployment, and monitoring together so teams can continuously improve their agents, compound intelligence, and govern them at scale. More than 7,000 customers, including Nvidia, Bridgewater, LinkedIn, Workday, Harvey, and Rippling trust LangSmith to improve their agents across the Agent Development Lifecycle. Learn more: www.langchain.com