Gradient Labs @ Replay 2026 | How We Built a Voice Agent with Temporal

Eliot Miller (Backend Engineer, Gradient Labs) explains how his team added voice to their AI support agent for financial services using Temporal, and what they had to trade away to do it. Running LLMs in parallel was too slow for voice latency requirements, so they traded resilience for speed, without touching the AI engineers' code.

Filmed at Replay 2026: The Durable Execution Conference for AI, by Temporal.

---

Temporal is the simple, scalable, open source way to write and run reliable cloud applications. 

Learn more
Blog: https://temporal.io/blog
How Temporal Works: https://temporal.io/how-temporal-works
Community Slack: https://temporal.io/slack

Developer resources
Docs: https://docs.temporal.io
Courses: https://learn.temporal.io/courses
Support forum: https://community.temporal.io