https://retellai.com/?utm_source=discord&utm_medium=seo logo
I have a question. From your experience, what is t...
# 💬・general
r
I have a question. From your experience, what is the ideal call duration for Retell to handle reliably without LLM timeouts, conversation stops, audio distortion, or tool issues? We're currently running calls of around 20 minutes, but we're trying to reduce them to 8–12 minutes because the context grows too large. I was surprised to see that Retell supports calls up to one hour, while our context starts becoming an issue much earlier. We're trying to capture rich, high-quality content from each client, and GPT-5.5 is giving us excellent results. However, we're running into frequent LLM timeouts and tool-related issues, especially during longer conversations. I'd really like to understand how you guys implement long calls while keeping them stable and avoiding these timeout and tool issues. Any best practices or recommendations would be greatly appreciated.