MahmoudAshraf97/whisper-diarization

Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper

56
/ 100
Established

This tool helps you automatically transcribe audio recordings and identify who said what. You provide an audio file, and it delivers a text transcript where each sentence is attributed to a specific speaker. This is useful for anyone needing to analyze conversations, meetings, or interviews, such as researchers, journalists, or content creators.

5,437 stars.

Use this if you need a precise, speaker-attributed transcript of an audio recording for tasks like meeting minutes, interview analysis, or podcast show notes.

Not ideal if your audio contains multiple speakers talking over each other frequently, as the tool currently has limitations with overlapping speech.

meeting-transcription interview-analysis audio-to-text speaker-identification podcast-transcription
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

5,437

Forks

500

Language

Jupyter Notebook

License

BSD-2-Clause

Last pushed

Feb 23, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/MahmoudAshraf97/whisper-diarization"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.