Top 200 ReposEXPLORER
Browse agents, categories and pages
Back to results
Planned, not doneThe source describes an intention, not a finished result.

Record and summarise meetings on your own machine with Meetily

Meetily records calls, transcribes them on the device with Whisper or Parakeet, and writes summaries with a local Ollama model or a cloud model you pick.

Try the promptRead the original (opens in a new tab)

The problem

How it works

Meetily is an MIT-licensed desktop app for Windows and Apple Silicon Macs, with Linux built from source. It captures meeting audio, transcribes it locally through whisper.cpp or an ONNX build of NVIDIA Parakeet, and passes the transcript to a summary model. The README recommends Ollama for fully local summaries, with Claude, Groq, OpenRouter, OpenAI or any OpenAI-compatible endpoint as alternatives.

Results and limitations

The README describes features, not measured outcomes. Its central claim is that audio and transcripts stay on your device, and that only the transcript text leaves it when you choose a cloud summary provider.

Before you try it

Tell participants you are recording and follow local consent law and your employer's policy. Acceleration is automatic on Macs (Metal and CoreML) and uses Vulkan on Windows, which needs a CPU with AVX2; CUDA needs a custom build. The project description and README disagree on speaker identification, which the README lists as a paid Pro feature, so do not count on who-said-what labels in the free edition. Meetily runs Whisper models through whisper.cpp, not OpenAI's Python whisper package. Results depend on your setup and were not independently reproduced by Top 200 Repos.

Tools and repositories

Tools
Meetily desktop app · Ollama (optional, for local summaries)
Prerequisites
Windows x64 with an AVX2 CPU or an Apple Silicon Mac; Linux users build from source.

Try it yourself: Turn a meeting transcript into minutes

Fill the fields to adapt the prompt. Empty fields stay as visible [placeholders].

Preview
Here is a transcript exported from Meetily for the meeting [Meeting title] held on [Meeting date]: [Transcript text]. Write minutes with these sections: decisions made, action items with an owner and due date where the transcript states them, open questions, and a five-sentence summary. Mark anything you inferred rather than read in the transcript as unconfirmed, do not invent owners or dates, and leave out personal remarks unrelated to the agenda. Keep the minutes under [Word limit] words.

Use a local Ollama model for this prompt when the meeting is confidential.

Related videos

About ollama/ollama

Independent creators. Listing a video implies no endorsement, sponsorship or partnership.

Sources

  1. Zackriya-Solutions/meetily README (opens in a new tab)

    Project documentation · github.com · Undated · Source checked 11 Nov 2026, 22:04 UTC

    What this source supports
    • Records meetings, transcribes them and generates summaries, locally by default
    • Transcription runs on Whisper through whisper.cpp, or on Parakeet
    • Ollama is the recommended summary provider; cloud providers are optional
    • Native builds for Windows x64 and Apple Silicon macOS; Linux builds from source
    • Community Edition is MIT licensed; speaker identification is listed under the paid Pro tier
Report a problem

Planned, not done

Auto-tag receipts and bills in Paperless-ngx with paperless-ai

paperless-ai suggests titles, tags, correspondents and dates for documents in a Paperless-ngx archive, using a local Ollama model or a cloud LLM, with manual review and undo.

github.comollama/ollama
Reported by source

Extract invoice fields locally with a vision model on Ollama

Stephen Sebastian replaced a paid cloud OCR API with Gemma 4 E4B on Ollama to pull date, amount and description from contractor invoice photos on his laptop.

dev.toollama/ollama
Reported by source

Run an open-weight model locally and call it from your code

Install Ollama, pull an open model and call it through the local REST API so prompts stay on your machine.

github.comollama/ollama
Reported by source

Transcribe and translate recordings locally with Whisper

Use OpenAI Whisper on your own machine to transcribe audio in many languages or translate speech into English text.

github.comopenai/whisper
Reported by source

Control smart-home devices with a local LLM voice assistant

Connect Home Assistant to a local Ollama model as its conversation agent so you can ask it to control exposed devices privately.

github.comhome-assistant/core, ollama/ollama
Planned, not done

Import recipes and plan the week's meals in self-hosted Mealie with an AI provider

Mealie is a self-hosted recipe manager and meal planner; with an OpenAI-compatible provider it can turn web pages, pasted text or photos into recipes, parse ingredients and suggest tags.

github.comollama/ollama