Crosstalk is a CAPTCHA built on the cocktail-party effect — the trick your brain already uses to hear a friend across a loud room. People pass it without thinking. Off-the-shelf speech recognition doesn't.
How it works
No distorted letters, no "select all the crosswalks." Just a sentence, spoken once, in a room full of other people talking.
We generate a fresh clip. One voice reads a sentence aloud. Several others talk over it — real background chatter, not static.
Your visitor listens once and types what they heard. No puzzle-solving, no second-guessing which images have a bus in them.
We verify it server-side, in real time. A drop-in API call — pass or fail, same shape as any CAPTCHA check you've integrated before.
Try it
These are real outputs from our pilot — unedited. Press play, then reveal Whisper's actual transcription of the same clip.
Pricing
Placeholder numbers while we're in early access — tell us what you'd actually pay when you join the list.
Early access
We're onboarding a small number of pilot sites before general availability. Tell us where you'd use it.