Open-source, local-first AI dictation app that turns speech into text on macOS and Windows, working offline with Whisper.
Zackriya-Solutions/meetily
Privacy-first AI meeting assistant that records, transcribes and summarizes meetings locally on macOS and Windows, with optional Ollama or cloud LLM summaries.
Open-source alternative to:Otter.ai
Fireflies.ai
Fathom
- Stars
- 31,924
- Forks
- 3,640
- Open issues
- 380
- Last commit
- last month
What is it?
Meetily is a desktop meeting assistant that captures microphone and system audio, transcribes speech in real time, and generates meeting summaries. Transcription runs locally using Whisper or Parakeet models, so recordings and transcripts stay on the user's machine by default.
Summaries can be produced with a local Ollama model, or with providers such as Claude, Groq, OpenRouter, OpenAI, or any OpenAI-compatible endpoint. The app also supports importing existing audio files to generate transcripts, and re-transcribing a recording with a different model or language.
The application is built with Tauri, with a Rust backend and a Next.js frontend. Packaged installers are provided for macOS and Windows, and Linux users build from source. Acceleration varies by platform: Metal and CoreML on macOS, Vulkan for Whisper on Windows, and CUDA through a custom NVIDIA source build.
Key features
- 01Real-time transcription of microphone and system audio using local Whisper or Parakeet models.
- 02Meeting summaries via Ollama locally, or Claude, Groq, OpenRouter, OpenAI and custom OpenAI-compatible endpoints.
- 03Import existing audio files and re-transcribe recordings with a different model or language.
- 04Mixes microphone and system audio capture in one session.
- 05Recordings, models and transcripts are stored on the local machine.
Use cases
- Recording and summarizing confidential internal meetings without sending audio to a cloud service.
- Transcribing previously recorded audio files into text with a local model.
- Running a fully offline meeting note workflow paired with a local Ollama model.
- Teams that want to point summaries at their own OpenAI-compatible inference endpoint.
Quick start
- 1
Clone the repository
git clone https://github.com/Zackriya-Solutions/meeting-minutes - 2
Enter the frontend folder
cd meeting-minutes/frontend - 3
Install dependencies
pnpm install --frozen-lockfile - 4
Run the GPU build script (Linux build from source)
./build-gpu.sh
Things to know
- Pre-built installers are only provided for Windows and macOS; Linux requires building from source.
- The macOS release listed is for Apple Silicon (aarch64).
- CUDA acceleration needs a manual source build with a compatible NVIDIA toolchain.
- Windows installer requires an AVX2-capable x64 CPU.
Topics
FAQ
- What is meetily?
- Privacy-first AI meeting assistant that records, transcribes and summarizes meetings locally on macOS and Windows, with optional Ollama or cloud LLM summaries. Meetily is a desktop meeting assistant that captures microphone and system audio, transcribes speech in real time, and generates meeting summaries. Transcription runs locally using Whisper or Parakeet models, so recordings and transcripts stay on the user's machine by default.
- Is meetily free to use? What license does it have?
- meetily is open source under the MIT license. Check the license terms before using it in commercial products.
- Is meetily still maintained?
- Updated within 6 months. The last commit to meetily was on Sep 15, 2026.
- What can I use meetily for?
- Recording and summarizing confidential internal meetings without sending audio to a cloud service. Transcribing previously recorded audio files into text with a local model. Running a fully offline meeting note workflow paired with a local Ollama model. Teams that want to point summaries at their own OpenAI-compatible inference endpoint.
- How do I install meetily?
- Clone the repository: git clone https://github.com/Zackriya-Solutions/meeting-minutes Enter the frontend folder: cd meeting-minutes/frontend Install dependencies: pnpm install --frozen-lockfile Run the GPU build script (Linux build from source): ./build-gpu.sh
- Where can I get meetily?
- The source code and installation instructions are on GitHub: https://github.com/Zackriya-Solutions/meetily
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Local-first AI subtitle generator that runs offline and plugs into DaVinci Resolve, Premiere Pro and After Effects.
Local-first open-source AI voice studio for cloning voices, generating speech, dictating into any app, and giving AI agents a voice.
Desktop app that transcribes audio and video fully offline on your own device, using Whisper and other speech models.
Native macOS speech-to-text app that transcribes dictation on-device or via cloud APIs, then reprocesses text with reusable AI workflows.
Open-source local subtitling for any video: Whisper transcription, translation, styling and burn-in, in the browser, desktop app or CLI, without uploading the video.