How to use Currai with OpenAI Realtime voice and TTS
A complete, code-first guide to turning OpenAI Realtime voice conversations and text-to-speech generations into readable Currai User Stories and correctly nested traces.
Blog
Highlights from the Currai blog: the posts worth reading first.
A complete, code-first guide to turning OpenAI Realtime voice conversations and text-to-speech generations into readable Currai User Stories and correctly nested traces.
A step-by-step guide to importing completed Retell AI calls into Currai with signed call-ended webhooks—without adding capture code to the live voice agent.
A step-by-step guide to importing completed Vapi calls into Currai with an authenticated webhook—without adding capture code or sharing a Vapi private API key.
Browse implementation notes, observability guides, product decisions, and workflow ideas by topic.
Learn what an AI travel assistant can do, which details still need verification, and how travel companies can build more reliable planning agents.
Read more ›Learn how a 24-hour virtual receptionist answers calls, books appointments, captures leads, and escalates complex conversations—plus what to measure.
Read more ›Use real production conversations to find agent failures, make focused prompt changes, build better evals, and verify that user outcomes improve.
Read more ›Monitor customer success agents with end-to-end traces, conversation outcomes, groundedness, escalation quality, policy compliance, latency, and cost.
Read more ›A beginner-friendly guide to connecting a Next.js chatbot to Currai with the Vercel AI SDK, native HTTP capture, conversation sessions, model traces, and MCP tool events.
Read more ›