# TapWisper

> TapWisper is free, open-source (MIT) AI voice dictation and meeting-notes software for macOS and Windows, version 1.2.0. Hold a key in any app, speak, and your words are transcribed, cleaned up and pasted at the cursor. It also transcribes meetings without a bot, edits selected text by voice, and runs on cloud models with your own API key, on-device open-source models (fully offline), or a self-hosted server.

Key facts:
- Price: free. No account. No telemetry. Cloud usage is billed by the provider you choose.
- Platforms: macOS 12+ (Apple Silicon and Intel), Windows 10+; Linux builds from source.
- Default shortcut: hold fn (Mac), Ctrl + Win (Windows) or Right Ctrl (Linux); add Space for hands-free.
- Models: OpenAI, Anthropic Claude, Google Gemini, Together AI, Soniox; 18 local speech and 24 local language models via whisper.cpp and llama.cpp; any OpenAI-compatible server (Ollama, LM Studio, vLLM).
- Meeting notes: recognizes Zoom, Google Meet, Microsoft Teams, Slack huddles, Webex, FaceTime, Discord, Whereby and Around; live transcript and AI summary; no bot joins the call. Works on Windows and macOS 13+.
- Download: https://github.com/zeyadelosherey/tapwisper-desktop/releases/download/v1.2.0/tapwisper-desktop-1.2.0-arm64.dmg (Mac Apple Silicon), https://github.com/zeyadelosherey/tapwisper-desktop/releases/download/v1.2.0/tapwisper-desktop-1.2.0-x64.dmg (Mac Intel), https://github.com/zeyadelosherey/tapwisper-desktop/releases/download/v1.2.0/tapwisper-desktop-1.2.0-setup.exe (Windows)
- Source code: https://github.com/zeyadelosherey/tapwisper-desktop

## Features

- [AI voice dictation](https://tapwisper.ai/features/ai-voice-dictation): TapWisper is a free, open-source AI dictation app for Mac and Windows. Hold a shortcut key in any app, speak, and let go: your speech is transcribed, cleaned of filler words, punctuated, matched to the app's tone and pasted at your cursor — in email, chat, documents, code editors or the browser.
- [Edit by voice](https://tapwisper.ai/features/edit-by-voice): Voice Command lets you edit text by speaking. Select any text, hold your TapWisper key and say an instruction such as “make it shorter”, “make it more formal” or “translate to Spanish”. The selected text and your instruction go to the language model, and the result replaces your selection in place.
- [AI meeting notes](https://tapwisper.ai/features/meeting-notes): TapWisper takes AI meeting notes without adding a bot to the call. It recognizes when a Zoom, Google Meet, Microsoft Teams, Slack huddle, Webex, FaceTime, Discord, Whereby or Around call starts, records your microphone and the meeting audio on your computer, shows a live transcript, and writes a summary when you stop.
- [Offline local models](https://tapwisper.ai/features/local-ai-models): TapWisper can run entirely on your computer with open-source models. It bundles whisper.cpp for speech-to-text and llama.cpp for AI cleanup, offers 18 speech models (Whisper, NVIDIA Parakeet, Qwen3-ASR, Voxtral) and 24 language models (Qwen, Gemma, Llama, Phi-4, Mistral, gpt-oss), and works offline with no API key.
- [Cloud & self-hosted models](https://tapwisper.ai/features/ai-models): TapWisper lets you choose the models behind your dictation. Use your own API key with OpenAI, Anthropic Claude, Google Gemini, Together AI (open-weight models such as Kimi, DeepSeek, Qwen and Llama) or Soniox, or point it at any OpenAI-compatible server such as Ollama, LM Studio, vLLM or LocalAI.
- [Smart formatting & tone](https://tapwisper.ai/features/smart-formatting): Smart Formatting cleans up dictation before it's pasted: it removes filler words, applies your corrections and fixes punctuation, and never translates. Tone by app then adapts the wording to where you're typing — Messages, Work, Email or Other — with Formal, Casual or Very casual for each.
- [Custom dictionary](https://tapwisper.ai/features/custom-dictionary): TapWisper's Dictionary holds the names and words dictation should always get right — your name, your company, product names and technical terms. Each entry can list what it's often misheard as; the term is sent to the speech model as vocabulary, and misheard versions are replaced after transcription.
- [Text snippets](https://tapwisper.ai/features/text-snippets): Snippets are voice text expansion. Create a trigger and its full text in TapWisper; when you say the trigger while dictating, the full text is typed instead. Triggers can be slash commands, spoken as “slash sig”, or plain phrases like “my calendar link”.
- [Voice triggers](https://tapwisper.ai/features/voice-triggers): Triggers turn spoken phrases into actions. In TapWisper you can map a phrase to an AI chat, a web search, launching an app, a keyboard shortcut, a terminal command, an Apple Shortcut or window management. Fuzzy matching tolerates transcription errors, and prefix triggers pass the rest of your sentence along.
- [AI actions & 100 mini apps](https://tapwisper.ai/features/ai-actions): AI Actions apply one-click AI transformations to your last dictation or selected text. Built-in categories cover translation, rephrasing (professional, casual, friendly, formal, concise, expand, shorten), formatting (email, letter, report, social post) and grammar. A library of 100 mini apps adds templates for work, social media, writing, education, marketing and more.
- [Voice notes](https://tapwisper.ai/features/voice-notes): Notes in TapWisper turn quick voice recordings into text. Record a thought from the Notes page and it's transcribed into a note you can title, edit and copy. Notes are grouped by day, and if transcription fails the recording is kept so you can retry.
- [Languages & translation](https://tapwisper.ai/features/multilingual-dictation): TapWisper supports multilingual dictation. It auto-detects the spoken language, handles mixed-language speech when you switch mid-sentence, and can translate your dictation into another language as you speak. The speech picker lists 21 languages, local Whisper models cover 99, and the app itself is available in English, Arabic, German, Spanish, French and Italian.
- [Private & open-source](https://tapwisper.ai/features/privacy): TapWisper is free, open-source software under the MIT licence. It needs no account and collects no telemetry. It only listens while you hold your key, encrypts API keys with your operating system's keychain, sends requests directly to the provider you chose, and stores history, notes and meetings on your device. With local models it runs fully offline.

## Comparisons

- [TapWisper vs Wispr Flow](https://tapwisper.ai/compare/wispr-flow): Wispr Flow and TapWisper both let you hold a key to dictate into any app, clean up your speech with AI, edit text by voice and take bot-free meeting notes. Wispr Flow is a polished cloud subscription on Mac, Windows, iPhone and Android. TapWisper is free and open-source, runs offline with local models, and lets you pick the AI model or use your own API key.
- [TapWisper vs OpenWhispr](https://tapwisper.ai/compare/openwhispr): TapWisper and OpenWhispr are both MIT-licensed, open-source dictation apps with local Whisper models, your own API keys and bot-free meeting notes. OpenWhispr also ships Linux builds, a voice agent and an optional paid OpenWhispr Cloud. TapWisper is entirely free, with no paid tier, and builds in tone by app, voice triggers, snippets and 100 AI actions.
- [TapWisper vs Superwhisper](https://tapwisper.ai/compare/superwhisper): Superwhisper and TapWisper both dictate into any app with local or cloud models and your own API keys, and both take bot-free meeting notes. Superwhisper is a paid app (Pro subscription or lifetime licence) with mobile apps and meetings on Mac. TapWisper is free and open-source, includes AI cleanup without a Pro plan, and records meetings on Mac and Windows.
- [TapWisper vs MacWhisper](https://tapwisper.ai/compare/macwhisper): MacWhisper is a Mac transcription app known for transcribing audio and video files with local Whisper models, with dictation and meeting recording in its Pro version. TapWisper is built around dictation into any app — with AI cleanup, tone by app, edit-by-voice and bot-free meeting notes — and is free, open-source and available on Mac and Windows.
- [TapWisper vs VoiceInk](https://tapwisper.ai/compare/voiceink): VoiceInk and TapWisper are both open-source dictation apps with local models, your own API keys and per-app AI modes. VoiceInk is a native Mac app for Apple Silicon (GPL-3.0, paid licence or build it yourself). TapWisper is MIT-licensed and free to download, runs on Mac and Windows, and adds bot-free meeting notes, voice triggers and 100 AI actions.
- [TapWisper vs Otter.ai](https://tapwisper.ai/compare/otter): Otter.ai is a cloud meeting-notes service whose Otter Notetaker bot can join Zoom, Google Meet and Teams calls, with team sharing and a free monthly minute allowance. TapWisper records meetings on your own computer with no bot, keeps transcripts on your device, is free with no minute limits on local models, and is also a dictation app for typing in any app.
- [TapWisper vs Granola](https://tapwisper.ai/compare/granola): Granola and TapWisper both take bot-free AI meeting notes by capturing your mic and system audio, and both blend your own typed notes into the summary. Granola is a cloud service on desktop and mobile with team features. TapWisper is free and open-source, can transcribe and summarize meetings entirely on your computer with local models, and also works as a dictation app in every app.

## FAQ

### What is TapWisper?
TapWisper is a free, open-source AI voice dictation app for Mac and Windows. Hold a key in any app, speak, and your words are transcribed, cleaned up and pasted at your cursor. It also takes bot-free meeting notes, edits selected text by voice, and runs on cloud, local or self-hosted AI models.

### Is TapWisper really free?
Yes. The app is free and open-source under the MIT licence. With cloud models you pay your provider directly for what you use. With local models it costs nothing.

### Can TapWisper transcribe meetings?
Yes. It recognizes Zoom, Google Meet, Microsoft Teams, Slack huddles, Webex, FaceTime, Discord, Whereby and Around calls, records your mic and the meeting audio on your computer, shows a live transcript and writes a summary with decisions and next steps. No bot joins the call.

### Do I need an API key?
Only for cloud providers. Choose Local in onboarding and TapWisper downloads an open-source model that runs on your computer — no key, no account, works offline.

### Which AI models does TapWisper support?
OpenAI (GPT-5.2, GPT-5, GPT-4o Transcribe, Whisper), Anthropic Claude, Google Gemini, 27 open-weight models on Together AI, Soniox, 42 local open-source models such as Whisper, Parakeet, Qwen, Gemma and Llama, and any OpenAI-compatible server like Ollama or LM Studio.

### Which apps does it work in?
Any app with a text cursor: email, chat, docs, code editors, browsers and terminals. TapWisper pastes at the cursor, and Style adjusts the tone to the app you're in.

### Is TapWisper an open-source alternative to Wispr Flow?
Yes. TapWisper covers the same hold-to-talk dictation in any app, AI cleanup, edit-by-voice and bot-free meeting notes — free and open-source under the MIT licence, with offline local models and your own API keys as options.

### Does TapWisper work offline?
Yes, with local models. TapWisper bundles whisper.cpp and llama.cpp and runs speech-to-text and AI cleanup entirely on your computer.

### What does it need permission for?
On macOS: microphone, accessibility (to paste and listen for your shortcut) and screen recording (for meeting audio). On Windows, just the microphone. It only listens while you hold your key.

### Is there a Linux version?
TapWisper runs on Linux (X11, or Wayland with wtype) — build it from the GitHub repo. Prebuilt downloads are available for macOS and Windows.