Cloud & self-hosted models
Use OpenAI, Claude, Gemini or your own server
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.
How it works
Three steps. That’s it.
01.
Pick an engine
Choose Cloud, Local or Self-hosted separately for speech-to-text and for language models.
02.
Add your key or server
Paste an API key and click Test key, or enter your server URL and click Test connection.
03.
Choose a model
Select from the provider's models; switch any time.
Details
What you should know.
- Language models
- OpenAI GPT-5.2, GPT-5, GPT-5 Mini and GPT-4.1; Claude Opus 4.6, Sonnet 4.5 and Haiku 4.5; Gemini 3 Pro, Gemini 3 Flash, 2.5 Pro and 2.5 Flash; and 27 open-weight models on Together AI.
- Speech-to-text
- OpenAI GPT-4o Transcribe, GPT-4o Mini Transcribe and Whisper-1; Whisper Large v3 and Voxtral Mini 3B on Together AI; and Soniox STT Async v4.
- Keys stay private
- API keys are encrypted with your operating system's keychain and only sent to the provider. Requests never pass through TapWisper servers.
- Self-hosted
- Any OpenAI-compatible endpoint works: Ollama, LM Studio, vLLM, LocalAI, speaches or whisper-server.
FAQ
Good questions.
Do I need to pay for TapWisper to use GPT or Claude?
No. TapWisper is free; you pay the provider directly for what you use with your own key.
Can I use Ollama with TapWisper?
Yes. Choose Self-hosted and enter your Ollama server's OpenAI-compatible URL.
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 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 moreCustom dictionary
Teach TapWisper your name, company, product names and technical terms, plus what they're often misheard as, so dictation spells them right every time.
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.