input0

Input0 — A macOS voice input tool: hold a hotkey to record, release to transcribe locally via STT, refine with LLM, and auto-paste into the active text field.

What is input0?

Input0 — A macOS voice input tool: hold a hotkey to record, release to transcribe locally via STT, refine with LLM, and auto-paste into the active text field.

Overview of input0

What it is

Input0 is a macOS voice input tool. It allows users to hold a hotkey to record speech, release to transcribe locally via speech-to-text (STT), refine the text with a large language model (LLM), and auto-paste the result into the active text field. The project is built with Harness Engineering.

Key features

  • Press & Speak: Hold a customizable hotkey (default Option+Space) to record, release to transcribe, optimize, and paste. No window switching needed.
  • Privacy-First Local STT: Six AI engines (Whisper, SenseVoice, Paraformer, Moonshine, FireRedASR, Zipformer CTC) run entirely on Mac via Metal GPU. Audio never leaves the device.
  • AI-Powered Polish: LLM auto-corrects grammar, removes filler words, and structures text. Built-in technical term correction with custom vocabulary support.
  • Auto-Paste Anywhere: Optimized text is automatically pasted into the active input field (Slack, WeChat, VS Code, browsers, any app).
  • 99+ Languages: 6 engines, 12 models, covering 99+ languages. The system recommends the best model based on the user's language.
  • On-Demand Models: Lightweight app; download only the needed STT models. One-click switch, progress display, smart recommendations.
  • ESC to Cancel: Cancel at any stage (recording, transcribing, optimizing) by pressing ESC.
  • History: Review past transcriptions with original and AI-optimized text side by side.
  • Custom Vocabulary: Add professional terms, names, and product names. Auto-learning detects corrections and validates via LLM.
  • Dark & Light Themes: Dual theme support.

Use cases

Input0 is designed for anyone who wants to input text by voice on macOS. It can be used for dictation in messaging apps (Slack, WeChat), code editors (VS Code), browsers, or any application that accepts text input. The local STT ensures privacy, and the LLM polish improves text quality. It is suitable for multilingual users, professionals needing technical term correction, and those who prefer hands-free text entry.

Getting started

Download the latest .dmg from GitHub Releases, open it, and drag Input 0 into the Applications folder. Alternatively, install via Homebrew:shellbrew install --cask input0On first launch, grant Microphone and Accessibility permissions in System Settings → Privacy & Security. Then configure an LLM API key (required for AI optimization) and download at least one STT model. After setup, hold Option+Space (or custom hotkey) to record, speak, and release to get auto-pasted text.

License and pricing

This project is licensed under CC BY-NC 4.0. It is open source and free for non-commercial use.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/10xchengtuinput0.svg)](https://yunodb.com/tools/10xchengtuinput0?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/10xchengtuinput0?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/10xchengtuinput0.svg" alt="Featured on YunoDB" height="20"></a>