ElmiraGhorbani/gpt-speaker-diarization

Conversational Speaker Diarization using OpenAI AI Language Models(gpt-4) and OpenAI Whisper.

23
/ 100
Experimental

This tool helps organize who said what in a conversation. You provide an audio recording, and it gives you a written transcript where each sentence is clearly labeled with the speaker. This is perfect for anyone analyzing interviews, meetings, or customer service calls to understand individual contributions.

No commits in the last 6 months.

Use this if you need to quickly identify and separate speakers in recorded conversations to simplify analysis.

Not ideal if you require extremely precise, timestamped speaker turns for highly complex audio or academic research.

Meeting analysis Interview transcription Call center analytics Qualitative research Content analysis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 10 / 25

How are scores calculated?

Stars

14

Forks

2

Language

Jupyter Notebook

License

Last pushed

Aug 13, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/ElmiraGhorbani/gpt-speaker-diarization"

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