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.
A factual comparison of LangSmith and Currai for LLM tracing, production monitoring, evaluations, prompts, OpenTelemetry, pricing, hosting, and agent infrastructure.
Read more ›Design and evaluate agent interrupts, approvals, state edits, resumptions, timeouts, and audit trails for safe long-running workflows.
Read more ›Understand LangGraph's stateful orchestration strengths and instrument nodes, edges, handoffs, checkpoints, tools, subgraphs, model calls, latency, and cost.
Read more ›Measure AI platform engineering by reliable outcomes, lead time, reuse, incident reduction, and cost—not model-call volume or lines of generated code.
Read more ›Use a decision framework and head-to-head evaluations to determine whether multiple agents improve specialization, isolation, or parallelism enough to justify the complexity.
Read more ›