The open-source alternatives to Superwhisper are VoiceInk, Handy, OpenWhispr and Whispering. VoiceInk is the closest match: a macOS app with modes per application, a personal dictionary and an optional language-model cleanup, under GPL-3.0. Handy and OpenWhispr add Windows and Linux. All four run Whisper on your own machine, and three also run NVIDIA's Parakeet on a CPU. VoiceInk's own README calls it an alternative to Superwhisper and Wispr Flow. A team switches when it wants the dictation to stay on the device and the code to be readable.
Superwhisper, in the vendor's own words: an app that lets you "just speak, write faster" and "turn your voice into polished text" in Slack, Gmail and any other site or app, by its own description. superwhisper.com.
| Project | Openness | Licence | Runs as | Platforms | Self-host | Hosted option | Last release | Stars |
|---|---|---|---|---|---|---|---|---|
| Handy | OSI | MIT | Desktop app | macOS (Intel and Apple Silicon), Windows x64, Linux x64 | Yes | No | Aug 24, 2026 | 31,790 |
| OpenWhispr | OSI | MIT | Desktop app | macOS (Apple Silicon and Intel), Windows, Linux | Yes | Yes | Sep 15, 2026 | 8,286 |
| VoiceInk | OSI | See LICENSE | Desktop app | macOS 14.4 or later | Yes | Yes | Aug 27, 2026 | 6,435 |
| Whispering | OSI | See LICENSE | Built from source (Bun), Desktop app (Tauri), Browser | Desktop via Tauri, browser build | Yes | Yes | Dec 27, 2025 | 4,801 |
Licence, release and star figures read from GitHub on September 16, 2026. Openness labels: The code, and the weights where the project is a model, carry a licence on the OSI approved list. The code is public, and the licence limits what you may do with it. Read the LICENSE file before commercial use. The model weights can be downloaded and run. The training data or code is closed, or the weights carry a restriction the code does not.
A free, offline push-to-talk dictation app for macOS, Windows and Linux that runs Whisper or NVIDIA Parakeet on your own machine and pastes the text at your cursor, under MIT.
Desktop app · macOS (Intel and Apple Silicon), Windows x64, Linux x64 · Runs on your own machines
A dictation and meeting-notes app under MIT that runs Whisper or Parakeet locally or cloud models with your own key, detects Zoom, Teams and FaceTime calls, and labels speakers on device.
Desktop app · macOS (Apple Silicon and Intel), Windows, Linux · Runs on your own machines · Hosted version available from the maintainers
A macOS dictation app under GPL-3.0 whose README names Superwhisper and Wispr Flow as the tools it replaces, with local models, per-app modes, a personal dictionary and an AI assistant mode.
Desktop app · macOS 14.4 or later · Runs on your own machines · Hosted version available from the maintainers
A speech-to-text app inside the Epicenter monorepo under AGPL-3.0 that records, transcribes with a provider you choose, cloud or local, optionally polishes the text, and pastes it at the cursor.
Built from source (Bun), Desktop app (Tauri), Browser · Desktop via Tauri, browser build · Runs on your own machines · Hosted version available from the maintainers
VoiceInk. It is a macOS app whose README names Superwhisper and Wispr Flow as the tools it replaces, with push-to-talk, per-application modes, a personal dictionary, and an AI assistant mode. It is GPL-3.0, installable through Homebrew or built from source, and the maintainers also sell a compiled build with automatic updates.
Handy and OpenWhispr. Handy ships an x64 Windows installer and a winget package; OpenWhispr ships a Windows .exe. Both run Whisper locally with GPU acceleration where available, and both run NVIDIA's Parakeet on a CPU.
Handy and VoiceInk are offline only: the speech model runs on your machine and no audio leaves it. OpenWhispr runs offline with local models and can also use cloud models with your own key. Whispering can use a local model in its desktop build or a cloud provider you choose.
VoiceInk has a personal dictionary with custom words and text replacements. Handy references a dictionary through its Raycast integration. OpenWhispr and Whispering do not describe a dictionary in their READMEs.
OpenWhispr lets you pick GPT, Claude, Gemini, Groq, OpenRouter or a local model for the cleanup step. VoiceInk has an AI assistant mode and context-aware modes, and its README does not name which model runs them. Whispering has an optional polish step tied to the provider you configure.
Running one of these inside your own environment, with your own data and your own security rules, is the kind of work Reveneau does. Read how a forward deployed engagement works.