To keep the authentication in a top secure level, on the third part we ask the user to read a randomly shown passage. Comparing the last voice to the new one, our platform can highly confirm if the person is exactly the right user.
Less than 1 seconf proccesing time No need to GPU Accuracy > 90% Language & text independent
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
The voices should not exceed 5 MB
Also, the sound time should not be more than 1 minute
1- wav , m4a , ogg , flac, mp3
2- sample rate : 16kh or upper
3- bit rate : 16bit or upper
Say the following text
Upload First Voice
I want to try your speaker verification service free. Please show me the result.
Upload Second Voice
I like to travel to paris and visit Eiffel tower.
Try Speaker Verification in
With this API, you can check whether two voices belong to one person or not