Meetily
SHA-256Privacy-first AI meeting assistant that captures, transcribes, and summarizes meetings entirely offline using local AI models like Whisper and Ollama.
Smart Download
Download Download Version
v0.4.0 · 46.8 MB
A fully offline, privacy-first AI meeting assistant that transcribes and summarizes meetings locally.
Core Features
- 100% local processing: transcription and summarization happen entirely on-device
- Real-time speech-to-text: supports Whisper and Parakeet models (up to 4x faster)
- AI-powered summaries: integrates with Ollama, Claude, Groq, and custom OpenAI endpoints
- Cross-platform: macOS, Windows, Linux with easy installers and source build options
- GPU acceleration: auto-detects Metal, CUDA, Vulkan for faster inference
What It Can't Do
- •Initial setup requires downloading AI models (2–5 GB). GPU acceleration only works on machines with NVIDIA/AMD GPUs or Apple Silicon. Speaker diarization and advanced export templates are PRO-only features.
Use Cases
- Enterprise meetings: protect sensitive data and stay compliant without uploading to cloud
- Remote teams: capture transcripts offline, avoiding latency and data leaks across borders
Detailed Introduction
Meetily is a privacy-first AI meeting assistant that runs entirely on your local machine. It captures meetings, transcribes them in real-time with Whisper or Parakeet models, and generates AI-powered summaries using Ollama or other providers—all without sending data to the cloud. Built on Rust with Tauri, it supports macOS, Windows, and Linux. Unlike cloud-based tools like Otter.ai or Fireflies.ai, Meetily ensures complete data sovereignty, zero vendor lock-in, and works offline. It also offers GPU acceleration (Metal, CUDA, Vulkan), speaker diarization (PRO), and custom OpenAI endpoint support. With over 15K GitHub stars and an MIT license, it's the leading open-source meeting note taker for enterprises and privacy-conscious individuals.
Tags
Getting Started
Download installer
Click the button above to download the installer for your system
Install the software
Open the downloaded dmg file, then drag the app to Applications
Windows: download x64-setup.exe and double-click to run the installer
macOS: download the .dmg file, drag Meetily to Applications folder
Launch Meetily, grant microphone and system audio permissions, and start recording
- Windows: download x64-setup.exe and double-click to run the installer
- macOS: download the .dmg file, drag Meetily to Applications folder
- Launch Meetily, grant microphone and system audio permissions, and start recording
SHA-256 checksum verified
Checksum extracted from GitHub official Release page
SHA256 Checksum
9c0d30802b5d7b097372b3c8969ea0f8ae5aa4e0028c4bb6fc1856fd5adcd8c8This checksum is extracted from the GitHub Release page. Verify file integrity after download.
All SHA-256 checksums on this platform are extracted from the project's official GitHub Release page, without any modification. You can independently verify them on the GitHub Releases page.
Open Source Transparency
View GitHub SourceUninstall Info
Windows: uninstall via Settings or Control Panel. macOS: drag Meetily from Applications to Trash and empty it.
No Extra Dependencies
Ready to use after download. No additional runtime required.
Similar Projects
ollama
Ollama lets you download, run, and manage large language models locally. One command, multiple platforms, endless possibilities.
Chatbox
Chatbox Community Edition is an open-source desktop client for interacting with multiple large language models. It supports OpenAI (ChatGPT), Azure OpenAI, Claude, Google Gemini Pro, Ollama (local models like Llama 2, Mistral), and ChatGLM-6B. All your chat data is stored locally on your device, ensuring privacy and preventing data loss. The app features a clean, ergonomic UI with dark mode, keyboard shortcuts, streaming replies, and full Markdown/LaTeX rendering with code highlighting. It also includes a prompt library, message quoting, and team collaboration for sharing API resources. Available on Windows, macOS, Linux, Web, iOS, and Android. The community edition is fully functional but may lack some advanced features from the pro version.
llama.cpp
High-performance LLM inference engine in C/C++ with minimal dependencies, supporting quantized models (1.5–8 bit) and diverse hardware (Apple Silicon, CUDA, Vulkan, etc.).