Numbers with
boundaries

A latency number without its start and end points is an adjective with digits. Every figure here says what was measured.

What the homepage numbers mean

These figures describe different parts of the running system. They should not be added together or treated as one end-to-end fixture.

01 / EXPRESSION

Turn state stays off the speech path

0.65 ms0.83 ms p95

Expression inference on CPU, measured with a 25 ms causal analysis window and recurrent updates every 10 ms.

02 / VIDEO

The rendered face reaches the call

~155 msat 30 fps

Source canvas to decoded WebRTC. This is the visual transport boundary, not speech-response latency.

03 / FULL TURN

A warm conversation answers

1.8–2.1 sp50

Microphone speech to first returned audio, stable from one to eight concurrent sessions. At two conversations per T4, p95 was 2.183 seconds. A native-live baseline was faster on the same fixture: 1.054 seconds versus 1.955 seconds.

04 / SPECULATION

Silence is spent generating

~1.2 swhen applicable

Microphone speech to first returned audio when speculative endpointing applies. If speech resumes, the speculative work is discarded.

05 / ASYNC WORK

Tools do not stall the turn

22.1 sand 9.7 s

Two concurrent background think calls in the recorded homepage demo. Both returned while the conversation continued; neither blocked a turn.

What happens
on turn forty

One scripted conversation, forty turns, retained context verified at the end. The latency boundary is final speech sample leaving the client to first response-audio byte arriving.

SETTLED-STATE LATENCY1,395 ms

Presence p50. It was slower to first audio than both hosted realtime APIs in this run.

INTERRUPT A PENDING TOOL2.6 s

Presence answered while its long-running tool continued. The same probe took 5.8 seconds on one hosted API and remained blocked on another.

TURN 40 / TURN 1 COST17.3×

Measured on one hosted realtime API. The other measured 1.25×. Presence remained 1.0× because it bills occupied time.

These are single runs on one fixture, not a universal ranking. Models, prices, caching, regions, and serving paths change. The public harness and raw per-turn data are the durable claim.

Numbers explain it.
A live session makes it obvious

Try Presence free Agent-readable measurements