What do you want to verify?
Each modality has its own forensic playbook. Pick one to begin.
Text
liveBurstiness, lexical tics, n-gram repetition, sentence-start variety, punctuation patterns.
Open detector →
Image
liveError Level Analysis, FFT spectrum, channel decomposition, noise residual, C2PA provenance.
Open detector →
Audio
soonSpectrogram analysis, formant patterns, vocoder artifacts, phase coherence. Coming after text/image stabilize.
Video
soonFrame consistency, optical-flow flicker, lip-sync drift, face-landmark stability.