Development prototype: SpeakKit is for invited or
otherwise authorised users only. Do not upload real patient or child
data unless you have appropriate consent and permission to use this
development service.
The following consents help us improve SpeakKit technology, develop therapy resources, support professional training, and carry out research and service improvement activities.
These consents are completely optional. You can create and use a SpeakKit account whether or not you choose to provide them.
Voice Calibration
Speak naturally for a few seconds so we can detect your voice type and
optimise the analysis parameters.
Uses your webcam to track lip shape in real-time. No video is sent to
the server.
Aperture
—
Spread
—
Rounding
—
—
Settings
Not calibrated
The green/blue bar is current mic level. The white line is the
global speech trigger used by Cue Page and speech-triggered
practice. Mic gain is set at the OS level (System Preferences →
Sound → Input).
Not calibrated
These are browser features enabled by default. They distort the
audio signal — uncheck all for accurate spectral analysis.
Re-calibrate noise floor after changing.
Workspaces
Real-time Spectrogram
Scrolling FFT spectrogram with formant tracks overlaid.
F1 ·
F2 ·
F3