OpenWhispr
Desktop app that turns your speech into text at the cursor, with local or cloud models.
- Stars
- 10.5k
- Forks
- 1.4k
- Licence
- MIT
- Language
- JavaScript
- Last update
- 4 days ago
- Type
- App
What it is
OpenWhispr is a desktop app for dictation. You press a hotkey, speak, and your words are typed or pasted where your cursor is. You can run speech recognition fully on your own device with local models such as Whisper or NVIDIA Parakeet, or use cloud providers if you bring your own API keys. The README also describes meeting transcription and notes features.
- Dictate emails, documents, or chat messages into any app using a global hotkey
- Transcribe meetings from Zoom, Teams, or FaceTime with speaker labels
- Transcribe existing audio or video files, or a YouTube or audio URL
- Ask an AI assistant questions by voice using a dedicated hotkey
Great for
- People who want dictation in any app without sending audio to a cloud service
- Users who want to bring their own OpenAI, Anthropic, Gemini, or Groq API keys
- Mac, Windows, or Linux users looking for a free alternative to paid dictation tools
- Developers who want to read or modify a desktop speech-to-text app
Not ideal for
- Users who need a mobile-only tool: the README describes a separate Expo mobile app with its own setup
- Intel Mac users who need speaker identification: the README says live speaker identification and voice fingerprinting are unavailable on Intel Macs
- People who want a simple no-setup install with no API keys: cloud features require your own keys, and local models depend on your hardware
How to get it
- 1
Download the app
Install via Homebrew (macOS or x86_64 Linux, community-maintained)
brew install --cask openwhispr - 2
Run it
- Download the installer for your platform from the releases page, or install with Homebrew on macOS or x86_64 Linux.
- Open OpenWhispr and follow its setup for permissions and models.
- Choose a local model for offline transcription, or add an API key for a cloud provider.
- Press the global hotkey, speak, and check that your text appears at the cursor.
- 3
Get the most out of it
- Use the Voice Assistant hotkey to send spoken commands to your AI assistant, and edit highlighted text in place.
- Enable dictation translation to speak in one language and paste text in another.
- Connect your AI assistant through the MCP server documented at docs.openwhispr.com.
- Use the public API to manage notes and transcriptions programmatically.
- Use GPU-accelerated local Whisper on Metal, CUDA, or Vulkan if your hardware supports it.
Downloads
Strengths
- Local transcription keeps audio on your device, according to the README
- Open source under the MIT license, free for personal and commercial use
- Available for macOS, Windows, and Linux with prebuilt installers
Trade-offs
- Cloud features and some AI features require your own API keys, per the BYOK model
- Some features, such as speaker identification, have platform limits like Intel Macs
- Setup for development needs Node.js 24+ and the README points to external docs for platform details
How it compares
| Project | Stars | Type | Level | Updated | Best for |
|---|---|---|---|---|---|
| openwhispr (this) | 10.5k | App | beginner | 4 days ago | People who want dictation in any app without sending audio to a cloud service |
| whisper.cpp | 54.9k | Library | intermediate | 7 days ago | Developers who want to embed offline speech-to-text in a C, C++, or other native app |
| Handy | 37k | App | beginner | 4 days ago | People who want dictation without sending their voice to a cloud service |
| LibreChat | 46.6k | App | intermediate | 4 days ago | Teams that want one shared chat interface across several AI providers |
| langchain | 149k | Framework | intermediate | 4 days ago | Python developers building LLM-powered applications |
| faster-whisper | 26.4k | Library | intermediate | 5 days ago | Python developers who need to add speech-to-text to an application |
Stats synced from GitHub. The assessment above was drafted with AI from the project's README on 2026-10-29 and may miss recent changes — check the README before relying on a command. MIT licence: free to use, modify and distribute, including commercially, as long as you keep the copyright notice.