lexicaps

www.lexicaps.com
Transcription and Diarization based on OpenAI's Whisper

It augments Whisper's transcription, by adding "speaker tags", so you know who says what. Perfect for podcasts and interviews - currently supports 2 speakers in English.

SOTA diarization on top of Whisper's native features - no other diarization model needed.

Try it out or view the Samples.

Thanks @karpathy for the fun project

Please 📧 contact me if you have special needs.