Suits professionals and privacy-minded teams who want meeting notes kept local; installing the app needs no coding, but local summaries mean setting up Ollama, and building from source needs Rust and Node.js.

What can you build with meetily?

Record and transcribe a work call without uploading the audio to a third-party service. Generate meeting minutes with a local Ollama model for sensitive discussions. Turn an existing audio recording into a transcript and summary. Re-transcribe an old meeting with a different Whisper or Parakeet model or language. Route summaries to your organization's own OpenAI-compatible endpoint.

Zackriya-Solutions /

meetily

Desktop app that records, transcribes and summarizes meetings on your own machine

32.1k stars
714 stars since 3 Oct
Rust
Updated yesterday
Beginner friendly
Productivity & personal

Open on GitHub (opens in a new tab) Website (opens in a new tab)

Meeting note tools usually send your audio to a cloud service. Meetily runs the whole pipeline on your computer instead: it captures audio, turns speech into text, and then asks a language model to write a summary.

It is one Tauri app. A Rust backend handles audio capture and transcription, and a Next.js frontend provides the interface. Transcription uses Whisper or NVIDIA's Parakeet models. For summaries, the README recommends Ollama running locally. You can also point it at Claude, Groq, OpenRouter, OpenAI, or any OpenAI-compatible endpoint, though those send text to an outside service.

The community edition is MIT licensed. The README also describes a separate paid product, Meetily PRO, built on a different codebase. It lists features such as custom summary templates, advanced exports and self-hosted team deployment. Speaker identification is listed as coming soon for PRO.

What it does

Live local transcription
Transcribes the meeting as it happens using Whisper or Parakeet models on your device, with no cloud needed.
Choice of summary provider
Summaries can come from local Ollama, or from Claude, Groq, OpenRouter, OpenAI, or your own OpenAI-compatible endpoint.
Mic and system audio together
Captures your microphone and the computer's audio at the same time, with ducking and clipping prevention when mixing.
Import and re-transcribe
In beta: bring in existing audio files, or re-transcribe a recorded meeting with a different model or language, all locally.
GPU acceleration
macOS packages use Metal and CoreML. Windows packages use Vulkan. Linux users build from source with the acceleration that suits their system.

What you could build

Record and transcribe a work call without uploading the audio to a third-party service.
Generate meeting minutes with a local Ollama model for sensitive discussions.
Turn an existing audio recording into a transcript and summary.
Re-transcribe an old meeting with a different Whisper or Parakeet model or language.
Route summaries to your organization's own OpenAI-compatible endpoint.

Get started

On Windows, download the x64-setup.exe from the Releases page and run it. On macOS, download the .dmg from Releases and drag Meetily into Applications. On Linux, build from source using the commands below.

git clone https://github.com/Zackriya-Solutions/meeting-minutes

cd meeting-minutes/frontend

pnpm install --frozen-lockfile

Commands are copied from the project's README. Read it on GitHub for the full setup.