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.
Answers to common questions about using coding agents to instrument, debug, evaluate, and improve production AI applications safely.
Read more ›Trace voice activity, audio preprocessing, streaming transcription, model calls, tools, and synthesis as one user experience.
Read more ›Embedded chat is easy to launch and easy to ignore. Track sessions, intent, tools, failures, and outcomes from the first production conversation.
Read more ›Choose a multi-agent architecture, instrument handoffs and subagents, and evaluate routing, coordination, task success, reliability, latency, and cost.
Read more ›Great voice agents coordinate latency, turn-taking, interruptions, prosody, and recovery so the conversation feels responsive and dependable.
Read more ›