Speaker Verification

We have proposed a deep learning-based method for speaker verification. In contrast with other methods they are text-dependent, our model is text and language independent. On the other hand, the processing speed of our model is less than 1 sec and the model verifies a person by just two voices with a length of 4 secs. We have trained the model on more than 50,000 speakers which consist of 15,000,000 tracks with English, French, Spanish, German, Persian, and Arabic languages. Another detail of our model is robust to the environment and virtual noises. The accuracy of our model achieved more than 96%.

How to try demo?

Read the passage shown on the screen.
Drop the file in the box
See the result
For developer, Json result is available too

Free Try


1- wav , m4a , ogg , flac, mp3
2- sample rate : 16kh or upper
3- bit rate : 16bit or upper
Say the following text

PresentID | SpeakerVerificationDemo
Upload First Voice
  • I like to travel to paris and visit Eiffel tower.

PresentID | SpeakerVerificationDemo
Upload Second Voice
  • I want to try your speaker verification service free. Please show me the result.

json output

Try Speaker Verification in PresentID - RapidAPI

PresentID | Loading