AI Meeting Tools Documentation

process_meeting.py

This script processes meeting audio files by:

1. Transcribing audio using Whisper (speech-to-text)
2. Generating a structured meeting protocol using Ollama

Command Line Usage

python process_meeting.py <path_to_audio> [OPTIONS]

Options

Option	Description	Example
--yes / -y	Answer yes to all prompts automatically	python process_meeting.py meeting.mp4 --yes
--force / -f	Force overwrite of existing files without prompt	python process_meeting.py meeting.mp4 --force
--overwrite / -o	Overwrite existing files	python process_meeting.py meeting.mp4 --overwrite
--no-protocol	Skip protocol generation, only transcribe	python process_meeting.py meeting.mp4 --no-protocol
--skip-transcript	Skip transcript generation (use existing)	python process_meeting.py meeting.mp4 --skip-transcript
--overwrite-protocol	Overwrite existing protocol	python process_meeting.py meeting.mp4 --overwrite-protocol
--protocol-only	Only generate protocol, skip transcription	python process_meeting.py meeting.mp4 --protocol-only

Examples

Basic usage - process audio file with prompts

python process_meeting.py /path/to/meeting.mp4

Answer yes to all prompts

python process_meeting.py /path/to/meeting.mp4 --yes

Force overwrite existing files

python process_meeting.py /path/to/meeting.mp4 --force

Overwrite and skip protocol

python process_meeting.py /path/to/meeting.mp4 --overwrite --no-protocol

Skip transcript and overwrite protocol

python process_meeting.py /path/to/meeting.mp4 --skip-transcript --overwrite-protocol

Input Requirements

• Valid audio file (MP3, MP4, M4A, WAV, etc.)
• Ollama server running on localhost:11434 for protocol generation
• Sufficient GPU memory for Whisper model loading

Output Files

• meeting_transcript.txt - Contains the transcribed text
• meeting_protocol.txt - Contains the generated meeting protocol

Both files are saved in the same directory as the audio file.