How to separate voice from different people in audios with whisper?

[rodrigo121998]

For example, i have audios where two people are talking. How can i separate or get the text just from one person?

[glangford]

This has been covered in many past discussions. Search for "diarization". In particular, see

• Extract Speakers Entities #827
• Tag multiple voices #265
• Transcription and diarization (speaker identification) #264