Extract 179 acoustic dimensions to identify speaker gender, age group, and detect AI-cloned audio in real time.
Benchmark Reading Script
Read aloud while recording to stress-test formant transitions:
"Please call Stella to verify our appointment. Ask her to bring six spoons of fresh snow peas, five thick slabs of blue cheese, and three bags of bright yellow oranges from the market."
Acoustic Input & Visualizer
00:00
-∞ dB
00:00 · 0 KB
📁
Drop your audio file here or browse
Supports .wav, .mp3, .ogg, .webm, .m4a (Up to 50 MB)