cd /news/artificial-intelligence/this-week-at-romi-2-latency-and-voic… · home topics artificial-intelligence article
[ARTICLE · art-122920] src=dev.to ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

This week at Romi #2 - Latency and Voice AI

Romi, an ADHD-focused voice AI startup, reduced pipeline latency by 200–300 milliseconds by making tool execution asynchronous, cutting deduplication layers from seven to two, and switching to a faster model optimized for tool invocation. The company also added a push-to-talk toggle to complement the backend speedups.

read1 min views1 publishedSep 8, 2026

Welcome back to This Last week at Romi. We've been really busy so this post hits a bit late than our scheduled Friday one!

In Voice AI, saving 200–300 milliseconds sounds tiny on paper. In practice, it’s the difference between an awkward robotic delay and a natural conversation.

This week, we took a hard look at our pipeline to eliminate latency and clean out old code that was getting in the way. Here is what we changed:

Sync to Async Tools: Originally, tool execution was synchronous. When a user created a task, the pipeline froze waiting for database writes. Making our tools asynchronous means the voice keeps flowing naturally while items are saved in the background. #

7 Dedup Layers Down to 2: To stop duplicate tasks from hitting the database, we kept piling on safeguards over time until we had 7 layers of deduplication. They slowed down the pipeline and began contradicting each other. With stronger prompt reinforcement and a quick backend cleanup, we cut that down to just 2 layers. #

Ditching "Thinking" Models: Since our agent relies heavily on fast tool calls, thinking models added unnecessary reasoning delay before speaking. We swapped to a model optimized strictly for speed and accurate tool invocation. #

Push-to-Talk Toggle: To complement these backend speedups, we added a toggle betweenNatural Flow andPush-to-Talk . Now users can think out loud or speak in noisy rooms without the model prematurely triggering unwanted tasks.

Sometimes performance wins aren't about writing complex new code—they're about deleting redundant safeguards, running tasks in the background, and picking the right model for the job.

What's the worst bit of legacy "safety code" you've had to clean out of your stack?

By Vlad - CTO@RomiADHD

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @romi 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/this-week-at-romi-2-…] indexed:0 read:1min 2026-09-08 ·