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.
Compare GPT-5.6 Sol and Terra on coding benchmarks, pricing, code review, and agent cost. Learn how production traces and evals reveal which model actually solves more work.
Read more ›Claude Opus pricing is only half the cost equation. Learn how the Opus tokenizer, cache tokens, output length, and routing affect the real cost of every request.
Read more ›AI agents can score well in controlled evals while real users still struggle. Learn how to detect the coverage, context, workflow, and outcome gaps that appear after launch.
Read more ›Even a well-evaluated AI system fails in production through distribution shift, integration and compounding errors, and unmeasured dimensions. Here's how to catch each.
Read more ›G-Eval turns a plain-language quality criterion into a repeatable score by having the judge reason through steps first. Here's how it works, why it beats a bare 1–5 prompt, and where it still needs calibration.
Read more ›