🍎 Meetily for macOS: Now with Homebrew Support & Multi-Language Transcription! 🌍

[sujithatzackriya]

We're thrilled to announce two major enhancements for Meetily on macOS: Homebrew installation support and multi-language transcription capabilities!

🚀 One-Command Installation for macOS

macOS users can now enjoy a streamlined installation process with Homebrew:

# Install Meetily using Homebrew (macOS only)
brew tap zackriya-solutions/meetily
brew install --cask meetily

# Start the backend server with your preferred language
meetily-server --language en --model medium

🌐 Multi-Language Transcription Support

Our backend now supports transcription in over 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

# Japanese
meetily-server --language ja --model medium

# Chinese
meetily-server --language zh --model medium

# Auto-detect language (may be less accurate)
meetily-server --language all --model medium

🔄 Model Selection for macOS

Choose from various Whisper models based on your needs:

# Download your preferred model
meetily-download-model medium

# Available options:
# - tiny (fastest, least accurate)
# - base (fast, moderate accuracy)
# - small (balanced performance)
# - medium (recommended for most users)
# - large-v3 (highest accuracy, requires more resources)

✨ Why Use Homebrew on macOS?

• Native macOS Experience: Integrates perfectly with your macOS workflow
• Simplified Installation: No more manual downloads or permissions issues
• Automatic Updates: Stay current with brew upgrade
• Clean Removal: Uninstall completely with brew uninstall

🚀 Getting Started on macOS

After installation:

1. Start the backend server with your language preference: meetily-server --language [your_language_code]
2. Launch Meetily from your Applications folder
3. Begin capturing and transcribing your meetings in your preferred language!

🔧 Advanced Configuration for macOS Users

Fine-tune your experience with additional parameters:

# Set logging level
meetily-server --language en --model medium --log-level debug

# Specify custom model path (if you've downloaded models elsewhere)
meetily-server --language en --model /path/to/your/model.bin

💬 Feedback

macOS users, we'd love to hear about your experience with these new features! Please share your feedback on our GitHub repository.

---

Note: These features are currently optimized for macOS. Windows users can refer to our standard installation instructions in the README.

[Li-l484]

In the settings of the meeting client, the language setting button 'configure' cannot be clicked

[sujithatzackriya]

The UI does not have that option yet. We are actively working on it. If you would like to change the language, please restart the server.

Language change options

# 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

# Japanese
meetily-server --language ja --model medium

# Chinese
meetily-server --language zh --model medium

# Auto-detect language (may be less accurate)
meetily-server --language all --model medium

[Li-l484]

Okay, thank you, but there's one more question. I haven't configured GROQ_SPI_KEY and
ANTHROPIC_SPI_KEY, and after executing the command: meeting server -- language zh -- model medium, is this considered a successful startup

[sujithatzackriya]

You can set up API keys during installation or manually:

echo "ANTHROPIC_API_KEY=your_key_here" > $(brew --prefix)/opt/meetily-backend/backend/.env
echo "GROQ_API_KEY=your_key_here" >> $(brew --prefix)/opt/meetily-backend/backend/.env

You may keep the ANTHROPIC_API_KEY as a random value if needed (This is a bug that we are fixing right now). Which model provider are you planning to use?

[Li-l484]

I saw that there is an ollama option on the client side, but after I set it up, there will be an error message on the client side

[sujithatzackriya]

Smaller ollama models hallucinate and are not very good at tool calling. So the output will be unstructured, Hence summary generation using smaller ollama models will fail. We are however finetuning a smaller LLM for this specific purpouse and hopefully we'll be able to launch this soon.

[Li-l484]

Okay, thank you very much for your patient answer. Wishing you a happy life and smooth work

[sujithatzackriya]

Thank you. That's very kind of you. Hope the tool would add value to you. Wishing you a happy life as well.