Live demo · runs in your browser

Start demo and say "Hey Assistant"

Your audio never leaves this page. The model highlights "Hey Assistant" while ignoring all other speech — including similar-sounding words and phrases like "Hey sister" or "Assist me".

"Hey Assistant"

Start speaking…
Loading engine…
0.90

    Measure the real-time factor on this device

    RTF (real-time factor) is processing time divided by audio duration — an RTF of 0.01 means one second of audio takes 10 ms to process, so keeping up with live speech uses about 1% of one CPU core. This benchmark generates 60 seconds of audio right in your browser, pushes it through the wake-word engine as fast as your CPU allows, and reports the measured RTF.

    How it works: the ~170 KB WebAssembly runtime and ~100 KB model load from a CDN, then all inference runs on your CPU in this tab. Detection accuracy matches the native SDKs (ROC AUC 0.9966; precision 0.993 / recall 0.982 at the 0.90 threshold). Requirements: a browser with WebAssembly SIMD128 — Chrome/Edge 91+, Firefox 89+, Safari 16.4+ — and microphone permission. Lower the threshold for easier triggering (more false positives); raise it for stricter matching.

    Ship a custom wake word on-device

    Tell us your phrase and which devices it has to run on.

    Get started View on GitHub Compare wake-word engines