Appofficial publisher

Meetily

App : A product you use directly

Meeting assistant that records, transcribes (Whisper or Parakeet) and summarises your meetings on your machine, with no bot and no cloud.

The local alternative to Otter or tl;dv: 100% on-device transcription, summaries via Ollama locally. The right choice when meetings are confidential.

Official site GitHub · 32,132 ★ Docs

Overall score

9.0 /10

Security: nothing to flag

Utility

8.0

Reliability

10.0

Security

No caveat on record

Ease

1 click · Beginner

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Traditional meeting transcription tools send your recordings and transcripts to remote servers, raising privacy concerns for sensitive discussions, medical data, or information covered by professional secrecy. Meetily addresses this by processing everything locally, on your own machine.

In practice, the application captures microphone and system audio simultaneously, then transcribes in real time using Whisper or Parakeet models running directly on your device. Summaries can be generated by Ollama locally, or via an external provider of your choice (Claude, OpenAI, Groq, OpenRouter) if you supply your own API key. No bot joins your meetings: audio is captured like a screen recording, without appearing in the participant list.

Meetily is aimed at professionals and teams handling confidential information: consultants, lawyers, healthcare providers, and companies subject to GDPR or HIPAA. The Community Edition (MIT) is free and covers local transcription and AI summaries. The PRO version adds higher accuracy, advanced exports (PDF, DOCX, Markdown), custom summary templates, and automatic meeting detection.

The tool is not suited for users who want a plug-and-play solution with no configuration: optimal local operation requires a machine with at least 8 GB of RAM, and using larger Whisper models demands more resources. On Linux, compilation from source is required, as no native installer is currently available.

What it offers

·Real-time transcription on your machine using Whisper models (tiny to large-v3) or Parakeet, with no internet connection required after setup.
·AI summaries generated locally via Ollama, or via your own API key (Claude, OpenAI, Groq, OpenRouter).
·Simultaneous microphone and system audio capture, compatible with Zoom, Google Meet, Microsoft Teams, and any other video conferencing software.
·Import of existing audio files to generate or enhance a transcript with a different model (beta feature).
·Automatic GPU acceleration: Metal and CoreML on macOS, Vulkan on Windows.
·Advanced exports in PDF, DOCX, and Markdown with formatting, and custom summary templates (paid).
·Automatic speaker identification (diarization) to distinguish who said what (paid, announced for mid-June).
·Automatic meeting detection and joining, and calendar integration (paid, coming soon).

Our tips

To keep all your data on your machine, select Ollama as the summary provider in the settings: no data will then leave your device, neither for transcription nor for summarization.
If you need better transcription accuracy, switch from a small Whisper model (tiny, base) to a larger one (medium, large-v3) in the settings; plan for more RAM (up to 8 GB depending on the model).
The audio import feature (beta) lets you re-transcribe an already recorded meeting with a different model or in another language, without having to start a new session.
On Windows, the standard installer uses Vulkan for GPU acceleration; if you have an NVIDIA card and want CUDA, you need to build from source with the appropriate CUDA configuration.
Always inform participants that the meeting is being recorded, regardless of the platform used, in accordance with local recording laws.

Watch out

On Linux, no native installer is available: the application must be compiled from source, which requires technical skills.
If you choose an external provider (Claude, OpenAI, Groq, OpenRouter) for summaries, the transcript text is sent to that provider; the audio, however, always stays on your machine.

In practice

Price: Freemium
Commercial use: Commercial use: yes
Available on: macos, windows
Licence: MIT
FR interface: No

Security and data

Rating: Security: nothing to flag
Your data: Data stays local
Maintenance: Active
Last release: 12 September 2026

Links and repository checked on 25 October 2026 · added on 23 September 2026

How to install Meetily

1. Go to https://github.com/Zackriya-Solutions/meeting-minutes/releases/latest 2. On macOS, download the .dmg file (aarch64), open it, and drag Meetily to the Applications folder. 3. On Windows, download the x64-setup.exe file and run the installer (requires an AVX2-capable x64 CPU). 4. On first launch, choose your transcription model (Whisper or Parakeet) and your summary provider in the settings. 5. For fully local operation, select Ollama as the summary provider and make sure Ollama is installed and running on your machine. 6. Inform participants that the meeting is being recorded before starting a session.

git clone https://github.com/Zackriya-Solutions/meeting-minutes
cd meeting-minutes/frontend
pnpm install --frozen-lockfile
./build-gpu.sh

Official documentation ↗

In the same category

Whole category Meetings & notes →