← Discover
Discover · GitHub · Openwhispr↑ +121 today

Privacy-focused AI dictation application

OpenWhispr is a dictation application that converts audio files to text (voice-to-text) and combines local models with cloud-based options. With its privacy-focused structure, it allows you to run models like Nvidia Parakeet or Whisper on your own device or use cloud services with your own API key.

Updates

  • September 7, 2026: Stars 7,659 → 7,660, latest release v1.9.2 (August 29, 2026).

What you get

  • Converts audio files and speech to text in real-time
  • Works without an internet connection using local models
  • Automatically records meetings and separates speakers

Installation

Developer environment setup
git clone https://github.com/OpenWhispr/openwhispr.git
cd openwhispr
npm install
npm run dev

If you don't write code

🤖 Paste this into your AI agent (Claude Code · Codex · Antigravity)

I use OpenWhispr to transcribe my voice notes and meeting recordings. I want to create a privacy-focused work environment; how can I most efficiently perform transcription without my audio data leaving my device using local models, and how can I configure the AI assistant features into my workflow?

Related dictionary terms

WhisperAPIArtificial Intelligence
Who it is forFor professionals who want to transcribe their meetings, value the privacy of their data, and prefer working with local models.
LicenseMIT

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-09-07: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. This page was machine-translated from the Turkish original · the Turkish version prevails.