By Sagar Shankaran, Founder of CallSphere
Vapi 465ms optimal, Retell 580-620ms, Bland ~800ms, ElevenLabs 400-600ms — but those are best-case. We design a fair benchmark harness, P95 measurement, and a reproducible methodology for 2026.
Key takeaways
TL;DR — Vendor-quoted latency is best-case, single-region, low-load. Real production needs P95 under your peak concurrent load. Build a benchmark harness that drives 1,000+ calls per vendor, measures end-to-end and per-stage, and reports P50/P95/P99 — not averages.
Every vendor cites a number ("465ms!", "<300ms!"), and every number is true under specific conditions. The only fair comparison is your workload, your region, your concurrency. Without a harness you're picking based on marketing.
A fair benchmark must measure five layers separately:
Public 2026 measurements (1,200+ test calls, mixed config):
flowchart LR
HARNESS[Benchmark harness] --> V1[Vendor A]
HARNESS --> V2[Vendor B]
HARNESS --> V3[Vendor C]
V1 --> M[Measure<br/>VAD/ASR/LLM/TTS/RTT]
V2 --> M
V3 --> M
M --> P[P50, P95, P99<br/>per stage]
P --> PICK[Pick best for<br/>your workload]
CallSphere publishes per-tenant latency dashboards: P50, P95, P99 per stage, per vertical, per region. The Healthcare path on OpenAI Realtime PCM16 24kHz (FastAPI :8084) runs at sub-400ms median; other verticals hit 500-700ms depending on TTS/ASR pairing. 37 agents, 90+ tools, 115+ DB tables, 6 verticals, $149/$499/$1,499, 14-day trial, 22% affiliate.
Hear it before you finish reading
Talk to a live CallSphere AI voice agent in your browser — 60 seconds, no signup.
See your numbers — start a 14-day trial and the dashboard populates within 24h.
Q: Can I trust vendor-quoted latency? As a floor, yes. As a production estimate, no — it ignores concurrency, region, and config drift.
Q: What's the minimum sample size? 1,000+ calls per vendor per region. Fewer and your P95 is noise.
Q: Does test audio matter? Yes — short, clean prompts are easy. Use your actual caller distribution (accents, noise, background).
Q: How often should I re-benchmark? Quarterly, plus after any vendor-side model release.
Q: Does CallSphere publish numbers? Per-tenant in the dashboard. Aggregate medians on the marketing site, refreshed monthly.
Latency Benchmarking AI Voice Agent Vendors (2026) is also a cost-per-conversation problem hiding in plain sight. Once you instrument tokens-in, tokens-out, tool calls, ASR seconds, and TTS seconds against booked-revenue per call, the right tradeoff between Realtime API and an async ASR + LLM + TTS pipeline becomes obvious — and it's almost never the same answer for healthcare as it is for salons.
Still reading? Stop comparing — try CallSphere live.
CallSphere ships complete AI voice agents per industry — 14 tools for healthcare, 10 agents for real estate, 4 specialists for salons. See how it actually handles a call before you book a demo.
Production AI agents live or die on three loops: evals, retries, and handoff state. CallSphere runs 37 agents across 6 verticals, each with its own eval suite — synthetic call transcripts replayed nightly with assertion checks on extracted entities (date, time, party size, insurance, address). Without that loop, prompt regressions ship silently and you only find out when bookings drop.
Structured tools beat free-form text every time. Our 90+ function tools all enforce JSON schemas validated server-side; if the model hallucinates an integer where a string is required, we retry with a corrective system message before falling back to a deterministic path. For long-running flows, we treat agent handoffs as a state machine — booking → confirmation → SMS — so context survives turn boundaries.
The Realtime API vs. async decision usually comes down to "is the user holding the phone right now?" If yes, Realtime; if no (callback queue, after-hours voicemail), async wins on cost-per-conversation, which we track per agent in 115+ database tables spanning all 6 verticals.
What's the right way to scope the proof-of-concept? Setup runs 3–5 business days, the trial is 14 days with no credit card, and pricing tiers are $149, $499, and $1,499 — so a vertical-specific pilot is a same-week decision, not a quarterly project. For a topic like "Latency Benchmarking AI Voice Agent Vendors (2026)", that means you're not starting from scratch — you're configuring an agent template that's already been hardened across thousands of conversations.
How do you handle compliance and data isolation? Day one is integration mapping (scheduler, CRM, messaging) and prompt tuning against your top 20 real call transcripts. Day two through five is shadow-mode running, where the agent transcribes and recommends but a human still answers, so you can compare side-by-side. Go-live is the moment your eval pass-rate clears your internal bar.
When does it make sense to switch from a managed model to a self-hosted one? The honest answer: it scales until your tool catalog gets stale. The agent is only as good as the integrations it can actually call, so the operational discipline is keeping schemas, webhooks, and fallback paths green. The platform handles the rest — observability, retries, multi-region routing — without your team owning the GPU layer.
Want to see how this maps to your stack? Book a live walkthrough at calendly.com/sagar-callsphere/new-meeting, or try the vertical-specific demo at escalation.callsphere.tech. 14-day trial, no credit card, pilot live in 3–5 business days.
Written by
Sagar Shankaran· Founder, CallSphere
Sagar Shankaran is the founder of CallSphere, where he builds production AI voice and chat agents deployed across healthcare, hospitality, real estate, and home services. He writes about agentic AI, LLM engineering, and shipping voice agents that handle real calls in production.
See how AI voice agents work for your industry. Live demo available -- no signup required.
WebTransport is Baseline as of March 2026. Media Over QUIC ships in production within the year. Here is what changes for AI voice agents — and what stays the same.
Every 100ms of latency costs you. So does every cent per minute. Here is the decision matrix we use across 6 verticals to pick where to spend and where to save on voice AI infrastructure.
How to stream tokens, tool-call deltas, and intermediate steps from an agent — with code for both the OpenAI Agents SDK and LangChain — and the gotchas that bite in production.
Streaming changes the eval game — final-answer correctness isn't enough when users perceive the answer one token at a time. Here's the metric set that matters.
On May 4 2026 OpenAI published its Realtime stack rebuild — split-relay plus transceiver edge. Here is what changed and what it means for production voice agents.
April 2026's voice AI market is consolidating around five names — CallSphere, Vapi, Retell, Hippocratic AI, and Sierra — each defining a distinct vertical posture.
© 2026 CallSphere LLC. All rights reserved.