meeting-minutes

Thu, 17 Apr 2025 15:30:04 +0800

Zackriya-Solutions/meeting-minutes

Meetily - AI-Powered Meeting Assistant

Open source Ai Assistant for taking meeting notes

Website • Author • Discord Channel

An AI-Powered Meeting Assistant that captures live meeting audio, transcribes it in real-time, and generates summaries while ensuring user privacy. Perfect for teams who want to focus on discussions while automatically capturing and organizing meeting content without the need for external servers or complex infrastructure.

View full Demo Video

Overview

An AI-powered meeting assistant that captures live meeting audio, transcribes it in real-time, and generates summaries while ensuring user privacy. Perfect for teams who want to focus on discussions while automatically capturing and organizing meeting content.

Why?

While there are many meeting transcription tools available, this solution stands out by offering:

Privacy First: All processing happens locally on your device
Cost Effective: Uses open-source AI models instead of expensive APIs
Flexible: Works offline, supports multiple meeting platforms
Customizable: Self-host and modify for your specific needs
Intelligent: Built-in knowledge graph for semantic search across meetings

Features

✅ Modern, responsive UI with real-time updates

✅ Real-time audio capture (microphone + system audio)

✅ Live transcription using Whisper.cpp

🚧 Speaker diarization

✅ Local processing for privacy

✅ Packaged the app for macOS and Windows

🚧 Export to Markdown/PDF

Note: We have a Rust-based implementation that explores better performance and native integration. It currently implements:

✅ Real-time audio capture from both microphone and system audio

✅ Live transcription using locally-running Whisper

✅ Speaker diarization

✅ Rich text editor for notes

We are currently working on:

✅ Export to Markdown/PDF

✅ Export to HTML

Release 0.0.3

A new release is available!

Please check out the release here.

What’s New

Windows Support: Fixed audio capture issues on Windows
Improved Error Handling: Better error handling and logging for audio devices
Enhanced Device Detection: More robust audio device detection across platforms
Windows Installers: Added both .exe and .msi installers for Windows
Transcription quality is improved
Bug fixes and improvements for frontend
Better backend app build process
Improved documentation

What would be next?

Database connection to save meeting minutes
Improve summarization quality for smaller LLM models
Add download options for meeting transcriptions
Add download option for summary

Known issues

Smaller LLMs can hallucinate, making summarization quality poor; Please use model above 32B parameter size
Backend build process requires CMake, C++ compiler, etc. Making it harder to build
Backend build process requires Python 3.10 or newer
Frontend build process requires Node.js

LLM Integration

The backend supports multiple LLM providers through a unified interface. Current implementations include:

Supported Providers

Anthropic (Claude models)
Groq (Llama3.2 90 B)
Ollama (Local models that supports function calling)

Configuration

Create .env file with your API keys:

# Required for Anthropic
ANTHROPIC_API_KEY=your_key_here  

# Required for Groq 
GROQ_API_KEY=your_key_here

System Architecture

Core Components

Audio Capture Service
- Real-time microphone/system audio capture
- Audio preprocessing pipeline
- Built with Rust (experimental) and Python
Transcription Engine
- Whisper.cpp for local transcription
- Supports multiple model sizes (tiny->large)
- GPU-accelerated processing
LLM Orchestrator
- Unified interface for multiple providers
- Automatic fallback handling
- Chunk processing with overlap
- Model configuration:
Data Services
- ChromaDB: Vector store for transcript embeddings
- SQLite: Process tracking and metadata storage
API Layer
- FastAPI endpoints:
  - POST /upload
  - POST /process
  - GET /summary/{id}
  - DELETE /summary/{id}

Deployment Architecture

Frontend: Tauri app + Next.js (packaged executables)
Backend: Python FastAPI:
- Transcript workers
- LLM inference

Prerequisites

Node.js 18+
Python 3.10+
FFmpeg
Rust 1.65+ (for experimental features)
Cmake 3.22+ (for building the frontend)
For Windows: Visual Studio Build Tools with C++ development workload

Setup Instructions

1. Frontend Setup

Run packaged version

Go to the releases page and download the latest version.

For Windows:

Download either the .exe installer or .msi package
Once the installer is downloaded, double-click the executable file to run it
Windows will ask if you want to run untrusted apps, click “More info” and choose “Run anyway”
Follow the installation wizard to complete the setup
The application will be installed and available on your desktop

For macOS:

Download the dmg_darwin_arch64.zip file
Extract the file
Double-click the .dmg file inside the extracted folder
Drag the application to your Applications folder
Execute the following command in terminal to remove the quarantine attribute:
1

xattr -c /Applications/meeting-minutes-frontend.app

Provide necessary permissions for audio capture and microphone access.

Dev run

# Navigate to frontend directory
cd frontend

# Give execute permissions to clean_build.sh
chmod +x clean_build.sh

# run clean_build.sh
./clean_build.sh

2. Backend Setup

# Clone the repository
git clone https://github.com/Zackriya-Solutions/meeting-minutes.git
cd meeting-minutes/backend

# Create and activate virtual environment
# On macOS/Linux:
python -m venv venv
source venv/bin/activate

# On Windows:
python -m venv venv
.\venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Add environment file with API keys
# On macOS/Linux:
echo -e "ANTHROPIC_API_KEY=your_api_key\nGROQ_API_KEY=your_api_key" | tee .env

# On Windows (PowerShell):
"ANTHROPIC_API_KEY=your_api_key`nGROQ_API_KEY=your_api_key" | Out-File -FilePath .env -Encoding utf8

# Configure environment variables for Groq
# On macOS/Linux:
export GROQ_API_KEY=your_groq_api_key

# On Windows (PowerShell):
$env:GROQ_API_KEY="your_groq_api_key"

# Build dependencies
# On macOS/Linux:
chmod +x build_whisper.sh
./build_whisper.sh

# On Windows:
.\build_whisper.bat

# Start backend servers
# On macOS/Linux:
./clean_start_backend.sh

# On Windows:
.\start_with_output.ps1

Development Guidelines

Follow the established project structure
Write tests for new features
Document API changes
Use type hints in Python code
Follow ESLint configuration for JavaScript/TypeScript

Contributing

Fork the repository
Create a feature branch
Submit a pull request

License

MIT License - Feel free to use this project for your own purposes.

Introducing Subscription

We are planning to add a subscription option so that you don’t have to run the backend on your own server. This will help you scale better and run the service 24/7. This is based on a few requests we received. If you are interested, please fill out the form here.

Last updated: March 3, 2025

Local Processing on Producthunt daily