TypeWhisper 1.4,
now on macOS.
Private speech-to-text for your Mac with system-wide dictation, file transcription, workflows, history, dictionary, snippets, and integrations.
Windows Beta and iOS Alpha are available for early testing.
Made in GermanyWrite a message
Press the hotkey. Speak. Finished text is inserted.
1.5kGitHub starsNeed it for work?Commercial license
See it in action.
Press a hotkey. Speak. Text appears.
The macOS 1.4 release.
The stable release brings the new Integrations hub, community plugins, model management, local APIs, and more reliable workflows.
Private by default.
Run speech-to-text locally on your Mac with no telemetry, no subscriptions, and no mandatory cloud dependency.
Faster dictation.
Use multiple global hotkeys per action, stronger capture paths, and lower startup latency for daily dictation.
More controllable workflows.
Reorder workflows with drag and drop, run watch-folder jobs, and override the engine or model per dictation.
Integrations and models.
Install official, community, and manual plugins in the new hub, with downloaded local models managed in one place.
Files, APIs, and automation.
Transcribe files, automate watch folders, and control recorder or dictionary behavior through local HTTP APIs.
Faster dictation.
Use multiple global hotkeys per action, stronger capture paths, and lower startup latency for daily dictation.
Integrations and models.
Install official, community, and manual plugins in the new hub, with downloaded local models managed in one place.
More controllable workflows.
Reorder workflows with drag and drop, run watch-folder jobs, and override the engine or model per dictation.
Files, APIs, and automation.
Transcribe files, automate watch folders, and control recorder or dictionary behavior through local HTTP APIs.
An open ecosystem.
Extend TypeWhisper with add-ons: speech engines, LLM integrations, automations, and community plugins - or build your own with the SDK.
Groq
TypeWhisper
Ultra-fast cloud transcription and LLM processing powered by Groq's custom LPU hardware.
Parakeet
TypeWhisper
Ultra-fast local transcription using NVIDIA's Parakeet TDT model, optimized for Apple Silicon.
Reson8
Y. Vos
Cloud transcription via the Reson8 speech-to-text API with real-time WebSocket streaming. Requires an API key.
WhisperKit
TypeWhisper
Local on-device transcription using WhisperKit with CoreML, optimized for Apple Silicon.
Apple Speech
TypeWhisper
Native on-device transcription using Apple's Speech framework with real-time streaming results.
AssemblyAI
TypeWhisper
Cloud transcription using AssemblyAI's Universal models with real-time WebSocket streaming and REST fallback.
Why not just use built-in dictation?
Per-app workflows
Automatically switch language, engine, prompt, 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.
What people say.
From the press and the community.
“Listed among the 12 best AI apps for dictation.”
F.A.Z.
Frankfurter Allgemeine Zeitung
“If you regularly transcribe audio and value privacy, speed, and accuracy, TypeWhisper is worth installing immediately.”
All Things Geek
allthingsgeek.me
“TypeWhisper emphasizes local processing, engine choice, open-source licensing, and user control.”
implicator.ai
implicator.ai
Available now, with clear release stages.
macOS 1.4 is the supported stable path. Windows and iOS remain preview releases.
Windows
Public beta for Windows 10 and 11. Expect ongoing polish and rapid iteration.
Download Windows BetaFree for everyone.
Every feature is free for personal use. Commercial use and supporter tiers keep the project going.
Personal
Free
All features, all engines, no account. Free forever for personal use.
Commercial
from €5/month
Same app, fair license for work use. Monthly or lifetime, for individuals and teams.
Supporter
from €10one-time
Love the app? A one-time contribution supports open development.
Commercial licensing works on the honor system - no license checks, no nagging.
Ready for TypeWhisper 1.4 on macOS?
Download the stable macOS 1.4 release with the new Integrations hub, local APIs, and more reliable workflows.
Free under GPLv3, including internal use of the GPL app. Commercial licenses for non-GPL terms and support start at 5 EUR/mo. See pricing