OpenSuperWhisper
SHA-256OpenSuperWhisper is a free, open-source macOS dictation app that transcribes audio in real-time using Whisper and Parakeet models, with global keyboard shortcuts and drag-and-drop file support.
Smart Download
Download Download Version
v0.1.0 · 11.1 MB
Free, open-source real-time speech-to-text for macOS with dual engines and keyboard shortcuts.
Core Features
- Dual transcription engines: Whisper and Parakeet, with in-app model download
- Global hotkeys with hold-to-record mode
- Drag & drop audio files for batch transcription with queue
- Microphone selection: built-in, external, Bluetooth, iPhone (Continuity)
- Multi-language auto-detection and Asian language autocorrect
What It Can't Do
- •Requires Apple Silicon (M1/M2/M3) Mac – Intel Macs are not supported. First launch downloads models; ensure internet connectivity. Hold-to-record mode needs manual hotkey configuration in settings.
Use Cases
- Transcribe meetings in real-time by holding a shortcut key
- Record interviews and get instant text without waiting for complete files
Detailed Introduction
OpenSuperWhisper is a free, open-source macOS application designed for real-time audio transcription using the Whisper and Parakeet models. Unlike paid tools like MacWhisper, it is completely free and offers two transcription engines directly selectable in-app. It features global keyboard shortcuts (including hold-to-record mode), microphone selection (built-in, external, Bluetooth, iPhone via Continuity), drag-and-drop audio file processing with queue, multiple language support with auto-detection, and Asian language autocorrect. Ideal for journalists, students, and professionals who need instant, offline speech-to-text on Apple Silicon Macs.
Tags
Getting Started
Install the software
Open the downloaded dmg file, then drag the app to Applications
Install via Homebrew: brew install opensuperwhisper
Or download the .dmg from GitHub Releases and drag to Applications
On first launch, the app automatically downloads the default model (takes ~1-2 min), then you can start recording with the configured hotkey
- Install via Homebrew: brew install opensuperwhisper
- Or download the .dmg from GitHub Releases and drag to Applications
- On first launch, the app automatically downloads the default model (takes ~1-2 min), then you can start recording with the configured hotkey
SHA-256 checksum verified
Checksum extracted from GitHub official Release page
SHA256 Checksum
af5ca5142c22e5bed3ba7d2642223c0a481e49935f5a5a6cf1bc766c7ecd9d69This checksum is extracted from the GitHub Release page. Verify file integrity after download.
All SHA-256 checksums on this platform are extracted from the project's official GitHub Release page, without any modification. You can independently verify them on the GitHub Releases page.
Open Source Transparency
View GitHub SourceUninstall Info
Uninstall with Homebrew: brew uninstall opensuperwhisper; or manually delete the app and remove ~/Library/Application Support/OpenSuperWhisper.
No Extra Dependencies
Ready to use after download. No additional runtime required.
Similar Projects
ollama
Ollama lets you download, run, and manage large language models locally. One command, multiple platforms, endless possibilities.
Chatbox
Chatbox Community Edition is an open-source desktop client for interacting with multiple large language models. It supports OpenAI (ChatGPT), Azure OpenAI, Claude, Google Gemini Pro, Ollama (local models like Llama 2, Mistral), and ChatGLM-6B. All your chat data is stored locally on your device, ensuring privacy and preventing data loss. The app features a clean, ergonomic UI with dark mode, keyboard shortcuts, streaming replies, and full Markdown/LaTeX rendering with code highlighting. It also includes a prompt library, message quoting, and team collaboration for sharing API resources. Available on Windows, macOS, Linux, Web, iOS, and Android. The community edition is fully functional but may lack some advanced features from the pro version.
llama.cpp
High-performance LLM inference engine in C/C++ with minimal dependencies, supporting quantized models (1.5–8 bit) and diverse hardware (Apple Silicon, CUDA, Vulkan, etc.).