Darlingfxx02/no-tipe-releases

Free desktop dictation for macOS and Windows. Speak messages, emails and notes into your apps with local or cloud speech recognition.

What it solves

No Type provides a streamlined, privacy-conscious way to dictate text directly into any application. It eliminates the need for manual typing by converting speech into text, offering flexible processing options to refine, shorten, or translate your dictated input before it appears in your active text field.

How it works

Users trigger the application with a keyboard shortcut to begin recording. The software captures audio and processes it using either local speech-to-text models (running entirely on your computer) or cloud-based providers via your own API keys. Once transcribed, the text is processed through user-defined "writing modes"—which can include custom instructions for tone, formatting, or translation—before being inserted into the focused application window.

Who it’s for

This tool is designed for professionals and individuals who want to accelerate their writing workflow, improve accessibility, or reduce repetitive typing tasks across various desktop applications on macOS and Windows.

Highlights

  • Flexible Model Support: Choose between local models for complete privacy or cloud-based models for potentially higher accuracy.
  • Customizable Writing Modes: Apply specific instructions to your dictation to automatically format emails, tasks, or notes.
  • Personalization: Includes a personal dictionary for custom terms, text snippets for frequent phrases, and a customizable interface with various recorder themes.
  • Privacy-Focused: Supports fully local processing and provides transparent control over data usage and statistics.
  • Productivity Insights: Tracks speaking speed, word counts, and usage patterns to help users optimize their dictation habits.

Related

  • Project
    NeptuneHub/AudioMuse-AI-NV-plugin

    A Navidrome plugin that connects to the AudioMuse-AI engine to provide AI-powered features like automatic song mixes, artist similarity, and discovery tools directly within your music player.

  • Project
    resemble-ai/Perth

    A Python library for embedding and detecting imperceptible watermarks in audio files, utilizing neural network-based approaches to ensure robustness against manipulation.

  • Project
    mikeoliphant/neural-amp-modeler-lv2

    An LV2 plugin for playing back neural network machine learning amplifier models using the NeuralAudio engine.

  • Project
    richardr1126/openreader

    OpenReader is an open-source, self-hostable document reader that converts text files and PDFs into synchronized, read-along audiobooks using local or cloud-based text-to-speech models.