mylxsw/typeflux

Typeflux is a macOS menu bar voice input tool built with Swift. It is designed for a fast "hold to talk, release to insert" workflow: press a hotkey, speak naturally, let the app transcribe your speech, and send the resulting text back into the currently focused app.

What it solves

Typeflux is a macOS application that eliminates the friction of voice-to-text by injecting transcribed text directly into any active application at the cursor position. It removes the need to switch between a dictation app and the target application, allowing users to speak their thoughts faster than they can type.

How it works

Users interact with the app via hotkeys: holding the Fn key allows for direct dictation, while double-pressing Fn activates an AI assistant for Q&A, rewriting, and translation. The app supports both cloud-based speech-to-text (STT) providers (like OpenAI Whisper and Groq) and fully local inference on macOS using models such as SenseVoice, FunASR, and WhisperKit, ensuring that voice data can remain entirely on-device.

Who it’s for

MacOS users who want a high-speed, privacy-focused voice input method for any text field across browsers, code editors, and native apps, as well as those who seek an integrated AI voice assistant for content editing and agentic workflows.

Highlights

  • Direct Text Injection: Transcribes and inserts text instantly into any app without copying and pasting.
  • Local-First Privacy: Supports on-device models (SenseVoice, WhisperKit, etc.) so no data leaves the machine.
  • Ask Anything: A voice-driven AI agent for Q&A, rewriting selected text, and complex workflows.
  • Flexible Backends: Compatible with multiple cloud providers and local models for varying accuracy and language needs.
  • Streaming Preview: Provides real-time feedback of the transcription as the user speaks.
  • History & Replay: Local storage of sessions for review, audio replay and Markdown export.

Related

  • Project
    TypeWhisper/typewhisper-mac

    A system-wide speech-to-text and AI text processing utility for macOS that supports local and cloud transcription engines with customizable AI workflows.

  • Project
    kdsz001/typefree

    An AI-powered voice input tool for macOS that converts spoken language into polished, formatted text and provides a floating AI assistant for quick queries.

  • Project
    marswaveai/TypeNo

    A privacy-first, local voice-to-text tool for macOS that transcribes speech and pastes it directly into any active application.

  • Project
    tornikegomareli/Talkify

    A private, on-device voice dictation and transcription tool for macOS that uses local Apple frameworks and LLMs to provide speech-to-text, translation, and text refinement.

  • Project
    cyx2333hhh/talk-type

    A macOS voice input tool that combines real-time speech recognition, local Whisper fallback, and AI-driven text cleanup for seamless bilingual input across applications.