This Audio Recognition application leverages Deep Learning algorithms to analyse audio files in order to detect the Gender and Emotions. For any audio clip uploaded (.wav) or recorded on the fly, the application classifies emotions into Happy, Sad, Angry or Neutral at a 3-second level. Please try adding an audio file that is between 3 to 25 seconds long, and has preferably a single voice in the clip.

Upload or Select your Audio

OR

GENDER

FEMALE female icon
MALE male icon
Did I get it right?

EMOTIONS

HAPPY
SAD
ANGER
NEUTRAL
BAR LENGTH : H - HIGH | M - MEDIUM | L - LOW each bar is a 3 second
Overall Emotion
happy icon NEUTRAL
Did I get it right?