← Directory

OpenWhispr

OpenWhispr is open-source dictation software you can rely on.

  • AI
  • Productivity
  • Tools & Utilities
OpenWhispr is open-source dictation software you can rely on. Dictate, transcribe, and capture meeting notes with fast, accurate AI speech-to-text. OpenWhispr turns your voice into text, notes, and actions from your desktop. Press a hotkey, speak, and your words appear at your cursor. Choose between fully private offline transcription with local speech-to-text models like Orukeet, Whisper, NVIDIA Parakeet, and Cohere Transcribe — where your audio never leaves your device — or cloud processing for speed. No data collection, no telemetry, fully open source.

Platform availability

Available on 3 of 9 platforms

  • Unraid (not listed)
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS (not listed)
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac
  • Windows
  • Linux

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

76/100 Good

Maintained
100last commit 2 days ago
Popular
799,280 GitHub stars
Easy to install
251 install platform, install notes
Light to run
No data

Based on 3 of 4 factors.

GitHub stars
9,280
Open issues
449
Last commit
2026-10-09
Latest release
v1.10.2
License
MIT
Activity
declining

Checked yesterday - source: GitHub (OpenWhispr/openwhispr)

Resources & Compatibility

Requirements not published yet.

First-install notes

  • Install the OpenWhispr CLI first If you’ll use the command-line tool, install Node.js 20 or newer (which includes npm, the package installer), then run npm install -g @openwhispr/cli and check openwhispr --version; without that install, the openwhispr command won’t be available. source
  • Team spaces need a workspace key If you use team spaces, use a workspace key that starts with ow_wks_live_ and keep the space ID handy, because OpenWhispr API calls to list or create notes fail without the right key and space. source

Fetched yesterday - each note links to its source

Alternatives (9)

  • FUTO Voice Input - FUTO Voice Input is an application that lets you do speech-to-text on Android, integrating with third party keyboards or apps that use the…
  • FluidVoice
  • FnScribe - Speak freely.
  • Google AI Edge Eloquent - Powered by Google's latest Gemma technology, Google AI Edge Eloquent is an advanced dictation app engineered to bridge the gap between natu…
  • Handy STT - Free, open source speech-to-text app for desktop, works fully offline, prioritizes privacy, extensibility, cross-platform support, and acce…
  • SpeakoFlow - Local-first, open-source voice assistant offering on-device dictation, AI writing, translation, screen context, and floating panel chat for…
  • Spokenly - Real-time voice dictation for Mac with instant transcription, customizable shortcuts, advanced voice recognition, no data collection, and b…
  • TypeWhisper - Private macOS speech-to-text tool with offline system-wide dictation, audio and video file transcription, batch processing, profiles, autom…
  • Vibe Transcribe - Provides fully offline audio and video transcription with local AI models, batch processing, real-time preview, multi-format export, transl…

Checked yesterday - source: AlternativeTo

Common questions

How do I install the OpenWhispr command-line tool?

Install Node.js 20 or newer, run npm install -g @openwhispr/cli, and verify the command with openwhispr --version. Without that installation, the openwhispr command is not available.

What API credentials are needed for OpenWhispr team spaces?

Use a workspace key that starts with ow_wks_live_ and keep the space ID handy. API calls that list or create notes fail without the right key and space.

Why does OpenWhispr not show a screen-share chooser for Linux system audio?

On Linux, OpenWhispr captures the default PipeWire sink monitor directly instead of showing a screen-share chooser. If meeting audio stops, restart OpenWhispr and start meeting transcription again.

What OpenWhispr features are unavailable on Intel Macs?

Live speaker identification and voice fingerprinting are unavailable on Intel Macs because ONNX Runtime stopped shipping macOS x86_64 binaries in 1.24. Meetings still record and transcribe, and notes search falls back to keyword matching.

Does local OpenWhispr dictation send my audio to a server?

No. Local dictation runs on your computer, with nothing sent to OpenWhispr or anyone else. Cloud transcription is optional when you choose it.

Answers sourced from github.com, github.com, github.com, github.com, openwhispr.com

Community

Collected yesterday - public community threads