Most dictation tools quote one latency number without saying what they measured. Here is ours, measured on real dictations in September 2026: transcribing and cleaning a typical dictation took 1.4 seconds at the median and 2.4 seconds for nine in ten, on our servers. That excludes the upload from your machine, which depends on your connection — so we report it separately rather than folding it into a friendlier number.
At the median, over a week of real dictations in September 2026 (a typical clip ran about 17 seconds): transcription about 470 ms, the AI cleanup pass about 640 ms, checking your account about 100 ms and preparing the request about 60 ms — roughly 1.4 seconds of server-side work in total, and 2.4 seconds for nine dictations in ten. Every /transcribe response also carries a Server-Timing header and a per-stage timings field, so these are numbers you can read back yourself rather than take on trust.
Because it would not mean anything. Your total wait is upload time plus processing, and upload depends on your connection, your clip length, and where you are. A single headline figure is always somebody's best case on a good network with a short clip. We would rather give you the half we control and be explicit that the other half is yours.
Processing starts the moment you release the hotkey — never while you are still speaking. When it finishes, the whole transcript is delivered in one go by writing it to the clipboard and pasting it, so a long dictation appears as a block instead of trickling in word by word while you watch. If the clipboard path is unavailable, Pithflow falls back to typing the text character by character, which is slower but still lands.
Longer clips take longer — the processing scales with how much audio you recorded. A slow or congested connection adds upload time before any of the above starts. And a cold start after a long idle period costs more than the warm numbers quoted here. None of that is unusual for cloud dictation; it is just rarely stated.
No. Processing starts when you release the hotkey, and the finished text arrives all at once, usually a second or two later.
From a week of real dictations in September 2026, measured on our servers: 1.4 seconds at the median and 2.4 seconds for nine in ten. The upload from your computer is not included.
Longer clips take longer to process, a slow connection adds upload time, and the first dictation after a long idle period can be slower.
No. Transcription and cleanup run on Pithflow's servers, so you need an internet connection. The audio is not stored afterwards.
