This is an early release preview. You may encounter bugs.
Meetily logo
Unclaimed

Tool voice

Meetily

Desktop meeting assistant that records, transcribes, and summarizes meetings locally with Whisper or Parakeet models

B 73/100 GitHub score ? This grade is derived from GitHub signals, not user votes. Open for the full breakdown.
Discussion

01 / Summary

About Meetily.

Meetily is a desktop meeting assistant that records, transcribes, and summarizes meetings on your own machine. Audio, transcripts, and models stay local, and no bot joins the call, so it suits teams that cannot send meeting content to a cloud service.

Transcription runs live during the meeting using Whisper or Parakeet models, and captures microphone and system audio together with ducking and clipping prevention. Existing audio files can be imported for transcription, and a recorded meeting can be re-transcribed with a different model or language. GPU acceleration uses Metal and CoreML on macOS, Vulkan on Windows, and CUDA in a configured source build.

Summaries come from a provider you choose. Ollama is the local default, and Claude, Groq, OpenRouter, OpenAI, or any custom OpenAI-compatible endpoint can be used instead. The application is a single Tauri app with a Rust backend and a Next.js interface, available for macOS, Windows, and Linux.

A separate paid PRO edition, built on a different codebase, adds higher-accuracy transcription models, custom summary templates, PDF and DOCX exports, automatic meeting detection, and team self-hosting.

  • Local transcription: live transcripts from Whisper or Parakeet models without a cloud service
  • Audio capture: microphone and system audio recorded together, with ducking and clipping prevention
  • Import and enhance: transcribes existing audio files and re-transcribes recordings with another model or language
  • Pluggable summaries: Ollama locally, or Claude, Groq, OpenRouter, OpenAI, or a custom OpenAI-compatible endpoint
  • GPU acceleration: Metal and CoreML on macOS, Vulkan on Windows, CUDA through a source build
  • Cross-platform desktop app: a Tauri application with a Rust backend and Next.js interface for macOS, Windows, and Linux
  • Local storage: models, recordings, and transcripts are stored on the device

02 / Discussion CREDIBILITY-GATED

Discussion

Reading is open to everyone. Posting and voting need a verified identity or a GitHub grade of B or higher.

  • No discussions yet.

04 / Build

Build with Meetily.

Browse the catalog for frameworks, tools, and harnesses, each scored on real GitHub credibility.

Get Meetily →

Browse the catalog