Speaker Diarization / Voice Recognition with deep learning

Job ID: 33161809

Budget: $750 – $1,500 USD

Hello,
i need a model can reconize who spoke when.
details are flexible you can guide me with it. what i need is a model can segment the speakers in same audio file and give us a good accuracy rate.

i dont want 100% unique model or code, you can get help from any API.