#Speaker Verification

PresentID Speaker verification API checks whether two voices belong to one person or not. This capability is potentially useful in Call centers.

*Send Data via Base64 or a voice URL or voice file
*The voice must be between three seconds and one minute
The voices must not exceed 5 MB
Supported file types: wav,mp3,m4a,flac,aac,ogg
*Due to the high accuracy of the core of the Speaker Verification API, the audio file must be recorded and sent in wav, m4a and flac formats. Notice that *mp3, aac, ogg files don’t give you high accuracy due to compression and lost data.

• Accuracy higher than 90% in real world

Speaker Verification Tutorial Youtube Video

###Python Quick Start

  import requests

 api_url = 'Speaker Verification URL'
 api_key = 'Your API Key'

sound1_path = 'Path to sound1 directory'
 sound1_name = 'Sound name1'
 sound2_path = 'Path to sound2 directory'
 sound2_name = 'Sound name2'

 files = {'sound1': (sound1_name, open(sound1_path + sound1_name, 'rb'), 'multipart/form-data'), 
          'sound2': (sound2_name, open(sound2_path + sound2_name, 'rb'), 'multipart/form-data')}
 header = {
     "x-rapidapi-host": "speaker-verification1.p.rapidapi.com",
     "x-rapidapi-key": api_key
 }
 response = requests.post(api_url, files=files, headers=header)