Your voice,
your device.
On-device speech-to-text for macOS, Windows, and iOS. No cloud, no subscriptions, no data collection.
See it in action.
Press a hotkey. Speak. Text appears.
Everything you need.
Built for privacy, speed, and flexibility.
100% on-device.
All processing happens locally. No cloud, no telemetry, no data collection. Your voice data never leaves your machine.
Extend with add-ons.
Install extra speech engines, AI providers, and tools from the built-in marketplace.
Rewrite, translate, summarize.
8 built-in AI prompts for text processing. Connect Apple Intelligence, Groq, OpenAI, or Gemini.
Context-aware profiles.
Per-app and per-URL overrides for language, engine, and behavior. Profiles activate automatically.
Transcribe files.
Drag and drop audio or video files. Export as SRT or WebVTT subtitles with timestamps.
Why not just use built-in dictation?
Per-app profiles
Automatically switch language, engine, and behavior per app or website.
Six speech engines
Pick the right engine for speed, accuracy, or language support.
Audio and video files
Transcribe full files with drag and drop. Export subtitles as SRT or WebVTT.
History and automation
Searchable transcription history and a local HTTP API for workflows.
Choose your engine
Six speech engines - three built-in, more via add-ons.
| Feature | WhisperKitVersatile | Parakeet TDT v3Fast | Apple SpeechAnalyzerZero Setup |
|---|---|---|---|
| Languages | 99+ | 25 European | ~40 |
| Streaming | |||
| Translation | 20 languages | 20 languages | 20 languages |
| Speed | Fast | Up to 5x faster | Fast |
| Model Sizes | Tiny to Large v3 | 1.1B params | System-managed |
| Model Download | Manual in-app | Manual in-app | Automatic by macOS |
| Best For | Multilingual & translation | European languages | Quick setup |
| Accuracy | Excellent | Excellent | Good |
Apple-optimized Whisper models. Best for multilingual use and streaming preview.
NVIDIA's latest TDT architecture. Extremely fast transcription for European languages with excellent accuracy.
Apple's native speech recognition. No manual model downloads - models are managed by macOS. Requires macOS 26+.
WhisperKit
VersatileApple-optimized Whisper models. Best for multilingual use and streaming preview.
Parakeet TDT v3
FastNVIDIA's latest TDT architecture. Extremely fast transcription for European languages with excellent accuracy.
Apple SpeechAnalyzer
Zero SetupApple's native speech recognition. No manual model downloads - models are managed by macOS. Requires macOS 26+.
Additional engines (Qwen3 ASR, Groq Whisper, OpenAI Whisper) are available as add-ons.
Available on every platform.
Same local privacy everywhere.