TypeWhisper 1.6Stable for macOS

Speak once.
Keep writing everywhere.

Dictate into your apps and turn spoken thoughts into finished text. On your Mac or with providers you choose.

Download for macOS Read the macOS docs

Set up TypeWhisper

macOS 1.6 is the current stable direct-download release.

Made in Germany

Example: dictation and finished text

You say

“um hey sarah just wanted to say the uh the new design is done and um could you take a look before friday”

TypeWhisper types

Hi Sarah, the new design is done. Could you take a look before Friday?

2kGitHub starsNeed it for work?Commercial license

Known from

One connected workflow

From your voice to something you can use.

On Mac, TypeWhisper joins capture, transcription, workflows, and delivery into a dependable flow that starts with a hotkey.

Capture

Hotkeys, microphone, files, or calendar-aware meeting recordings.

Transcribe

Local engines such as WhisperKit, Parakeet, and Apple Speech, or cloud providers you deliberately choose.

Shape

Workflows, translation, Whisper Mode, and app-aware formatting.

Deliver

Insert, copy, save, or trigger integrations and local APIs.

Currently shown: macOS 1.6On-device processing remains the default. Cloud providers are optional.

See it in action.

Press a hotkey. Speak. Text appears.

What macOS 1.6 changes day to day.

The current stable release combines faster capture with workflows, meeting automation, Backup & Restore, and expanded integrations.

Local first, providers by choice.

Process speech with local engines and no telemetry. Cloud ASR and LLM providers are used only after you configure and select them.

Faster, more resilient capture.

Lower startup latency, stronger audio capture, live transcript updates, and a clear recording indicator support everyday dictation.

Workflows instead of cleanup.

Polish dictation, format meeting notes, translate text, or run follow-up steps through your own workflow rules.

Integrations, backup, and CLI providers.

Manage add-ons and authenticated CLI providers centrally, and protect settings with Backup & Restore.

Files, history, and automation.

Transcribe audio and video, search results, and connect the recorder, dictionary, or workflows through local APIs.

Faster, more resilient capture.

Lower startup latency, stronger audio capture, live transcript updates, and a clear recording indicator support everyday dictation.

Integrations, backup, and CLI providers.

Manage add-ons and authenticated CLI providers centrally, and protect settings with Backup & Restore.

Workflows instead of cleanup.

Polish dictation, format meeting notes, translate text, or run follow-up steps through your own workflow rules.

Files, history, and automation.

Transcribe audio and video, search results, and connect the recorder, dictionary, or workflows through local APIs.

Premium features

Cloud sync and a dictionary that learns.

A Commercial license unlocks advanced features including Cloud Folder Sync, Automatic Correction Learning, and calendar automation on macOS.

Cloud Folder Sync

Sync dictionaries and snippets through your own iCloud Drive, Dropbox, OneDrive, Syncthing, or custom folder.

Keep the same dictionary on every desktop
Sync snippets without a TypeWhisper account
Use the cloud folder you already trust

Dictionary autocorrection

TypeWhisper can learn confident corrections after insertion, then apply them automatically the next time recurring words, names, or typos appear.

Learns only from confident single-word edits
Fixes repeated names, jargon, and misspellings
Works alongside the existing dictionary pipeline

Premium features require an active Commercial license. The core app stays open source and local-first.

See Premium licensing

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

Bundled

Ultra-fast cloud transcription and LLM processing powered by Groq's custom LPU hardware.

TranscriptionLLMmacOSWindows

View Details

OpenAI / ChatGPT

TypeWhisper

Bundled

Cloud transcription, OpenAI/ChatGPT prompts, and text-to-speech. Use an API key for STT/TTS or ChatGPT login for prompts.

TranscriptionLLMText-to-SpeechmacOSWindows

View Details

Parakeet

TypeWhisper

Bundled

Ultra-fast local transcription using NVIDIA's Parakeet TDT model, optimized for Apple Silicon.

TranscriptionmacOS

View Details

Reson8

Y. Vos

Bundled

Cloud transcription via the Reson8 speech-to-text API with real-time WebSocket streaming. Requires an API key.

TranscriptionmacOSWindows

View Details

WhisperKit

TypeWhisper

Bundled

Local on-device transcription using WhisperKit with CoreML, optimized for Apple Silicon.

TranscriptionmacOS

View Details

Apple Speech

TypeWhisper

Bundled

Native on-device transcription using Apple's Speech framework with real-time streaming results.

TranscriptionmacOS

View Details

Browse all add-ons Build your own

Compare local engines

Choose your engine

Three local engines compared. More engines are available as add-ons.

Feature	WhisperKitVersatile	Parakeet TDT v3Fast	Apple SpeechAnalyzerZero Setup
Languages	99+	25 European	System-dependent
Streaming
Translation	Via Apple Translate	Via Apple Translate	Via Apple Translate
Model Sizes	Tiny to Large v3	0.6B params	System-managed
Model Download	Manual in-app	Manual in-app	Automatic by macOS
Best For	Multilingual and translation	European languages	Quick setup

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

Versatile

Apple-optimized Whisper models. Best for multilingual use and streaming preview.

Languages99+

Streaming

TranslationVia Apple Translate

Model SizesTiny to Large v3

Model DownloadManual in-app

Best ForMultilingual and translation

Parakeet TDT v3

Fast

NVIDIA's latest TDT architecture. Extremely fast transcription for European languages with excellent accuracy.

Languages25 European

Streaming

TranslationVia Apple Translate

Model Sizes0.6B params

Model DownloadManual in-app

Best ForEuropean languages

Apple SpeechAnalyzer

Zero Setup

Apple's native speech recognition. No manual model downloads - models are managed by macOS. Requires macOS 26+.

LanguagesSystem-dependent

Streaming

TranslationVia Apple Translate

Model SizesSystem-managed

Model DownloadAutomatic by macOS

Best ForQuick setup

Additional engines (Qwen3 ASR, Groq Whisper, OpenAI Whisper) are available as add-ons.

View all three editions

Distinct platform editions

One product family. Three distinct editions.

macOS 1.6, Windows 1.0.9, and iOS 1.0 are stable editions, each designed for its platform.

macOS

1.6 Stable

Stable 1.6 release with faster and more resilient recording, Backup & Restore, calendar-aware meeting capture, and expanded integrations.

Faster, more resilient capture with live transcript updates
Calendar-aware meetings, workflows, and integrations
Backup & Restore with local API and CLI

Download for macOS Open documentation

Windows

1.0.9 Stable

Stable 1.0.9 release for Windows 10 and 11 with system-wide dictation, files, app and website rules, workflows, integrations, and automation.

System-wide dictation with overlay and global hotkeys
App and website rules with OR and AND matching
File queue, watch folders, local API, and CLI

Install from Microsoft Store Open documentation

iOS

1.0 Stable

A distinct edition for iPhone, iPad, and Apple Watch with on-device engines, voice keyboard, files, Shortcuts, and Capture Inbox.

Voice keyboard, live text, and on-device models
Capture Inbox, widgets, Shortcuts, and Apple Watch
Profiles, files, dictionary, snippets, and optional sync

Download on the App Store iOS guide and status

TypeWhisper History and Capture Inbox on iPhone

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

Free core. Premium when you need it.

Core dictation stays free and open source. Commercial licenses unlock Premium sync, dictionary autocorrection, and business-friendly terms.

Personal

Free

System-wide dictation, local engines, workflows, add-ons, history, snippets, and APIs.

Commercial

from €5/month

Unlock Premium: Cloud Folder Sync, dictionary autocorrection, and commercial license terms.

Supporter

from €10one-time

Love the app? A one-time contribution supports open development.

Commercial licensing stays simple: monthly or lifetime, for individuals and teams.

See Premium pricing

Ready for TypeWhisper?

Download the stable edition for macOS, Windows, iPhone, or iPad.

Download for macOS View release status

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

Speak once.Keep writing everywhere.

From your voice to something you can use.

Capture

Transcribe

Shape

Deliver

See it in action.

What macOS 1.6 changes day to day.

Local first, providers by choice.

Faster, more resilient capture.

Workflows instead of cleanup.

Integrations, backup, and CLI providers.

Files, history, and automation.

Faster, more resilient capture.

Integrations, backup, and CLI providers.

Workflows instead of cleanup.

Files, history, and automation.

Cloud sync and a dictionary that learns.

Cloud Folder Sync

Dictionary autocorrection

An open ecosystem.

Groq

OpenAI / ChatGPT

Parakeet

Reson8

WhisperKit

Apple Speech

Choose your engine

WhisperKit

Parakeet TDT v3

Apple SpeechAnalyzer

One product family. Three distinct editions.

macOS

Windows

iOS

What people say.

Free core. Premium when you need it.

Ready for TypeWhisper?

Speak once.
Keep writing everywhere.