In one line: ~0.7 seconds, median, to the first spoken word, measured end to end on the live system, network included, on the turns a real conversation is made of.
The headline numbers
0.56s
Best
The fastest turn in a session.
~0.7s
Typical
The median turn, what a normal back-and-forth feels like.
What you're actually waiting for
~30 ms
Network
The round trip between your device and our servers.
~0.5 s
The reply
The AI composing the opening line of its answer.
~0.2 s
The voice
Our own speech engine turns it into the first audio you hear.
All three are measured, not estimated. It's the gap a person feels: from the moment you finish speaking to the moment you hear the reply begin, not the time to the full answer, and not a synthetic benchmark.
The voice engine is ours
Every number here includes the voice. Where most apps hand the text to an outside text-to-speech service — adding a network hop and a queue we don't control — we generate speech on our own engine, on our own GPUs, in the same region as the app.
⚡First sound out
~0.07s at the engine (measured in-region); ~0.2s on the full path with your network included.
📈Stays fast under load
In a stress test we pushed well past normal concurrency through a single pair of GPUs with zero failures — the voice held its speed where a rented API slides into multi-second delays.
👂What it means for you
The voice starts almost immediately, and it doesn't degrade when the app gets busy.
How we measured it: a closed-loop load test against the live voice service — real synthesis of a real line, timed to the first audible sample, reported as median and 95th-percentile across many runs at each concurrency level. No warm-up cherry-picking; the one-time cold start is excluded and noted.
A real 14-turn run, every value shown
0.5s
median 0.71s
.59
.61
.64
.67
.69
.69
.70
.71
.78
.78
.81
.88
.90
.95
14 consecutive turns, sorted fastest → slowest
Best 0.59s
Median 0.71s
Mean 0.74s
Slowest 0.95s
Every value from one real run, measured across the country, and every turn came back in under a second. We report the median (0.71s), not the average, so a normal turn is represented by where turns actually land, not dragged by an occasional slow one. Most cluster between 0.6 and 0.9 seconds.
How it's measured
🟢On the live system
The exact pipeline real users hit, same servers, same AI, our own speech engine. No mockup, no pre-recorded or cached reply.
🏠Across the country
A normal web browser on a home internet connection, a long cross-country hop from our datacenter, not a server sitting next to it.
🔁A run of turns, each timed
Each measurement is a run of consecutive turns, timed individually, then summarized to a median.
Why the numbers are honest, not cherry-picked
1
Network time is included. We measure the actual round trip (median of repeated pings) and add it to every number, no flattering constant, never quietly dropped.
2
"Typical" is the median, not the average. One slow turn can drag an average the wrong way. The median is the value a real turn lands near, and it's what we publish.
3
We exclude only the one-time warm-up, and say so. The first reply is prepared on the welcome screens, before you talk, so you never wait for it. The published numbers are warm, mid-conversation turns.
4
One-time setup isn't counted per turn. Placing your AI Friend in your space happens once, behind onboarding, so it isn't part of the per-reply wait.
5
It's reproducible. Because it runs against the live system, anyone can repeat it from any consumer connection, a repeatable result, not a one-off claim.
A note on apples-to-apples
Ours is a stricter measurement than many speed figures you'll see. We measure the complete path to the first audible word, network, thinking, and voice combined, on a warm mid-conversation turn. Some published figures cite only "time to first text token," or a best-case lab run next to the datacenter, or leave the network out entirely. We report the whole thing, the way a person hears it.
