speak your stack
Read a project description aloud. The page listens, transcribes, and tags what you said as things — then EXIFs the moment with timestamp, duration, words/min, hesitations, and the nouns it heard. Output is a personal database row you've literally spoken into existence.
00:00
your words will appear here…
words0
wpm0
pauses0
hesitations0
your browser doesn't support the Web Speech API — try Chrome, Edge, or Safari.
what's in a row
- timestamp — when you started, ISO format
- duration — total seconds you held the mic open
- wpm — words per minute, computed across the whole take
- pauses — gaps longer than 800ms between words
- hesitations — every um, uh, like, you know
- tags — best-guess nouns, frequency-ranked, dedup'd
Last 5 rows live in your browser's localStorage. Nothing is uploaded.