// 02 · Service
AI voice agent development
Voice agents that survive real calls, not just the demo — a latency budget that counts the phone leg, turn-taking that doesn't talk over people, and evals that catch a regression before your customers do.
- LiveKit
- WebRTC
- SIP
- Go
// The problem
Why this is hard
A voice agent demos beautifully over a laptop microphone and then meets a phone line. The transport it now runs on was designed for humans talking to humans, not for a model waiting to take a turn, and the gap shows up as the things a demo can never surface: half a second of silence before every reply, an agent that interrupts a caller mid-sentence, a carrier leg that transcodes the audio into something the recogniser mishears.
Most of that latency is not the model. A misconfigured voice-activity detector alone can add hundreds of milliseconds without a single token being generated — which is why a latency number measured from the browser, excluding the SIP and PSTN legs, tells you almost nothing about what your caller experiences.
// What we build
What you get
Latency budget, phone leg included
Every hop measured and attributed — capture, VAD, transport, recogniser, model, synthesis, carrier — so you know which one to fix rather than guessing.
Turn-taking & barge-in
Detection tuned past naive silence thresholds, so the agent yields when a caller interrupts and doesn't leave dead air when they pause to think.
Telephony & system integration
SIP trunks, number provisioning, DTMF, and the CRM and backend wiring that is usually most of the engineering — not the model prompt.
Replay evals
A golden set of real calls replayed on every change, so a provider's silent model update fails a gate instead of reaching your customers.
// How it fits together
The system we build
- Call inSIP / PSTN or web
- Transportself-hosted, tuned
- Turn detectionbarge-in aware
- Agenttools + your systems
- Speech outstreamed, budgeted
- Replay evalsgate every change
// Deliverables
- Latency budget incl. the SIP/PSTN leg
- Turn-taking and barge-in tuning
- Telephony and backend integration
- Replay eval harness on a golden set
// How we work
From prototype to production, in four moves.
Discovery
We map the problem, the data, and the eval that defines "done".
Prototype
A working slice in weeks — real model, real data, measured.
Production
Hardened, observable, evaluable. Shipped where users live.
Scale
Cost, latency and reliability tuned as load and scope grow.
// Typical engagement
What it takes to work together
Architecture Sprint
$2–4kfixed · 1–2 wks
1–2 weeks
De-risk before you build — measured latency budget, architecture, and a costed fix list. Credited against the build.
Build
from$12kfixed scope or pod
typically 1–3 months
Ship it end-to-end and take it to production, in your repo and conventions.
Run & Scale
from$1.5k/ month
ongoing
Keep it working after launch — evals, latency and cost tracking, and incident response.
Indicative ranges — the final price and timeline depend on your project's scope, complexity, and integrations. A paid Architecture Sprint pins them down.
// FAQ
Common questions
// Related
Related services
Real-Time AI Audit
A fixed-scope diagnostic of a real-time or voice system already in flight: where the latency actually goes, what breaks under load, what it costs per minute — and a prioritised, costed fix list you can act on with or without us.
Real-Time Ops
Real-time systems degrade quietly: an encoder falls back to software, a provider reprices, a model is deprecated. Monitoring aimed at the counters that actually move, alerting on the degradation that precedes failure, and a person who answers inside stated hours.
RAG & Knowledge Systems
Retrieval grounded in your own data, with an eval harness that proves the answers are faithful to the source — not plausible-sounding guesses.
// Industries
Where teams put this to work:
// Let's build
Ready to build with voice agents in production?
Tell us where you are. We reply within a day with a concrete next step.