Private & open-source
Private, open-source dictation
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.
How it works
Three steps. That’s it.
01.
Download
Get the app from GitHub releases — no sign-up.
02.
Choose where AI runs
Cloud with your key, local on your device, or your own server.
03.
Keep control
History and recordings stay on your computer; you can turn off recording replay.
Details
What you should know.
- Recordings
- The last 50 dictation recordings are kept on your device for replay; turn it off and audio is deleted after transcription.
- Open source
- Every line is on GitHub under the MIT licence — read it, fork it or build it yourself.
FAQ
Good questions.
Is TapWisper an open-source alternative to Wispr Flow or Superwhisper?
Yes. TapWisper covers the same core workflow — hold a key, speak, get clean text in any app — plus bot-free meeting notes, voice triggers and a choice of local or cloud models. It is free and open-source under the MIT licence.
Does TapWisper send my voice to its own servers?
No. TapWisper has no servers in the middle; audio goes only to the provider you chose, or nowhere with local models.
More features
Everything else in the app.
AI voice dictation
Hold a key, speak, and TapWisper types clean, punctuated text into any app — Slack, Gmail, Notion, Cursor and more. Free and open-source for Mac and Windows.
Learn moreEdit by voice
Select text, hold your key and say “make it shorter” or “translate to Spanish”. TapWisper rewrites the selection in place with AI, in any app.
Learn moreAI meeting notes
TapWisper records your mic and meeting audio on your computer for a live transcript and an AI summary with decisions and next steps. No bot joins the call.
Learn moreOffline local models
Run 18 speech and 24 language models locally with whisper.cpp and llama.cpp — Whisper, Parakeet, Qwen, Gemma, Llama. Free, private and fully offline.
Learn moreCloud & self-hosted models
Bring your own API key for OpenAI, Anthropic Claude, Google Gemini, Together AI and Soniox — or connect Ollama, LM Studio or vLLM. 46 cloud models supported.
Learn moreSmart formatting & tone
TapWisper removes filler words, fixes punctuation and adapts tone by app: casual in WhatsApp and Slack, formal in email. You choose the tone for each.
Learn moreDownload · v1.2.0
Start talking in a minute.
Free and open-source, no account. Setup walks you through permissions, your microphone and a speech engine — then you just talk.