Release Highlights

What's New in Community 0.0.3

Pre-release with Windows Support — our first cross-platform release!

Download Statistics

Major New Features

Windows Support

• Fixed audio capture issues on Windows
• Added both .exe and .msi installers
• Full Windows 10/11 compatibility

Improved Error Handling

• Better error handling and logging for audio devices
• More robust audio device detection across platforms

Enhanced Device Detection

• More reliable audio device detection across Windows and macOS
• Improved Bluetooth device support

Multi-Language Transcription

Meetily now supports transcription in 90+ languages! Specify your preferred language when starting the server:

# English (default)
meetily-server --language en --model medium
 
# Spanish
meetily-server --language es --model medium
 
# French
meetily-server --language fr --model medium
 
# German
meetily-server --language de --model medium
 
# Auto-detect language
meetily-server --language all --model medium

Model Selection

Choose from various Whisper models based on your needs:

• tiny — Fastest, least accurate
• base — Fast, moderate accuracy
• small — Balanced performance
• medium — Recommended for most users
• large-v3 — Highest accuracy, requires more resources

Homebrew Installation (macOS)

brew tap zackriya-solutions/meetily
brew install --cask meetily
meetily-server --language en --model medium

Why Use Homebrew?

• Native macOS experience
• Simplified installation
• Automatic updates with brew upgrade
• Clean removal with brew uninstall

Other Improvements

• Improved transcription quality
• Bug fixes for frontend
• Better backend build process
• Enhanced documentation

Known Issues

• Smaller LLMs can hallucinate; use models above 32B parameter size for best summarization
• Backend build process requires CMake, C++ compiler, etc.
• Backend requires Python 3.10 or newer

Download

• Windows (.exe): Download(opens in new tab)
• Windows (.msi): Download(opens in new tab)
• macOS (Apple Silicon): Download(opens in new tab)

Full Changelog

View on GitHub(opens in new tab)