The blog

Notes from production.

Voice AI engineering, written for people who have to ship it and defend it in a security review. New posts two to three times a week.

Latest Production engineering June 12, 2026 5 min read

Three Attempts at Masking a Voice Agent's Thinking Silence

After a caller stops talking, a production voice agent we run at Taritas has about 2.2 to 2.5 seconds of dead air before its first audio frame. We made three serious attempts to mask it: a classifier-driven filler, a state-change-driven filler, and preemptive generation. All three are disabled in production today, each for a different structural reason, and the usable lesson is about speech queue ordering: the only filler insertion point that works is the one where the reply does not exist yet.

Read the post →

All posts

Production engineering June 12, 2026 5 min read

Rate Limiting a Voice Agent With One Postgres UPDATE

A real-time voice agent's daily call cap has to be checked before the greeting plays, survive concurrent calls, and roll over at midnight. At Taritas we do all three in one Postgres UPDATE: a CASE expression handles the midnight rollover, the WHERE clause enforces the cap, and RETURNING reports which case fired. One round trip, no race condition, no scheduled job.

Production engineering June 12, 2026 7 min read

A 15-Second Default Timeout Broke Our Voice AI's Call Transfers

A production voice AI agent we run at Taritas stopped transferring callers to staff. Every transfer failed with a 504 at exactly 15 seconds, Envoy Gateway's default route timeout, while the destination line had developed a 13-second post-dial delay. The failed API calls left dials ringing in the background, so staff answered ghost calls. One scoped timeouts block on the HTTPRoute fixed it.

Reading this because a client asked for voice AI?

That is the conversation we are built for. taritas engineers it behind your brand.

What taritas does for partners