The open-source voice-to-text app that turns speech into clean, polished text in every macOS app. Fully offline. No cloud. No subscriptions.
macOS 14+ · Apple Silicon · MIT License
Why VibeFlow
Unlike cloud-based dictation tools, VibeFlow runs entirely on your Mac. Your voice never leaves your device.
Works across any macOS app — Slack, VS Code, Notion, browsers, terminals. Hold a hotkey, speak, release. Done.
Apple Speech Recognition for speed, or WhisperKit for offline Whisper-quality transcription via Neural Engine.
Local Qwen 0.5B via MLX polishes your speech — removes filler words, fixes grammar, formats text. All on-device.
WhisperKit + Local SLM = zero network dependency. Dictate on a plane, in a tunnel, anywhere.
Add technical terms — Kubernetes, Terraform, gRPC — for accurate recognition of your domain vocabulary.
Casual, Professional, Creative, or Technical. VibeFlow adapts its text cleanup to your preferred tone.
How It Works
Press and hold Fn (or your custom key). The Dynamic Island HUD appears with a live waveform.
Talk normally. Say "um" and "like" all you want — the filler removal pipeline strips them out.
Let go. VibeFlow transcribes, cleans, and pastes polished text into whatever app you're using.
Engine Options
Two stages, two choices each. Pick what fits your workflow — switch anytime in Settings.
| Component | Disk | RAM |
|---|---|---|
| App binary | ~20 MB | ~50 MB |
| WhisperKit (base) | ~80 MB | ~100 MB |
| Qwen 0.5B (4-bit) | ~350 MB | ~500 MB |
| Total (fully offline) | ~450 MB | ~650 MB |
Runs comfortably on a base MacBook Air M1 with 8 GB RAM.
Architecture
Protocol-based engine system lets you hot-swap speech and text processing at runtime. Add your own engines by conforming to a protocol.
protocol SpeechRecognitionService protocol TextProcessingService ConversationController Open source voice dictation for engineers. 100% local. 100% free.
git clone https://github.com/agarwalvivek29/VibeFlow.git && cd VibeFlow && open VibeFlow.xcodeproj