VoiceTypr

Voicetypr is a voice dictation tool for macOS and Windows that transcribes your speech directly into whatever app your cursor is in. Hold a hotkey, talk, and the text appears. No per-app setup, no copy-pasting.

Transcription runs locally by default using on-device Whisper and Parakeet models. Your audio never leaves your machine unless you choose a cloud engine. That matters for anyone handling sensitive work or who just doesn't want their voice data on someone else's server.

Key capabilities:

• Global hotkey drops text wherever your cursor sits, across Gmail, Slack, Notion, Cursor, Word, and anywhere else you type
• 99+ languages with automatic detection, no manual switching
• Push-to-talk or toggle mode depending on how you prefer to work
• AI text cleanup using your own OpenAI, Anthropic, or Gemini key. It only ever sends the final text, never audio
• Cloud fallback via Groq, Deepgram, or OpenAI for lighter machines that can't run local models comfortably
• Network transcription lets a more powerful desktop handle transcription for a lighter laptop over your own Wi-Fi
• CLI and Agent API for scripting and piping audio through AI workflows
• Audio and video file transcription with searchable local history
• Six formatting modes and per-app rules for consistent output

The pricing model is a deliberate break from tools like Superwhisper or AudioPen that charge monthly. Voicetypr is a one-time purchase covering two devices, with lifetime updates on the version you own.

It's aimed at founders, developers, and writers who type heavily all day. Speaking runs around 130 words per minute versus roughly 40 for typing, so the gap is real for anyone producing large volumes of text. Custom vocabulary support helps with technical terms or names that generic models tend to mangle.