Skip to content

ApplauseLab/yap

Repository files navigation

Yap

Yap

Dictate anywhere. Free and local-first.
Speech-to-text powered by whisper.cpp or OpenAI Whisper.

About · Download · Features · Installation · Development · Documentation


About

Yap is a desktop application that transcribes your speech and automatically pastes the text into any application. Press a hotkey, speak, and your words appear wherever your cursor is.

Choose between local transcription using whisper.cpp for complete privacy and offline use, or cloud transcription via OpenAI's Whisper API for maximum accuracy.

Built with Wails (Go + React).

Download

Platform Download
macOS (Apple Silicon, Intel via Rosetta) DMG Installer
Windows Installer
Linux AppImage · DEB

See all versions on the Releases page.

Features

  • Global Hotkey — Start recording with a single keypress (Option key on macOS)
  • Local Transcription — Offline, private speech-to-text using whisper.cpp
  • Cloud Transcription — OpenAI Whisper API for higher accuracy (optional)
  • Auto-Paste — Transcribed text is automatically pasted into the active application
  • Multiple Models — Choose from tiny, base, small, medium, or large models
  • Transcription History — Review, replay, and copy past transcriptions
  • System Tray — Quick access from the menu bar
  • Audio Device Selection — Choose your preferred microphone

Whisper Models

Model Size Speed Accuracy
tiny ~75 MB Fastest Basic
base ~150 MB Fast Good
small ~500 MB Medium Better
medium ~1.5 GB Slow High
large-v3 ~3 GB Slowest Highest

English-only models (e.g., base.en) are faster and more accurate for English.

Installation

Download Release

  1. Download the installer for your platform from the Releases page
  2. macOS: Open the DMG and drag to Applications
  3. Windows: Run the installer
  4. Linux: chmod +x *.AppImage && ./Yap-*.AppImage or sudo dpkg -i *.deb

Build from Source

Prerequisites

# macOS
brew install portaudio

# Ubuntu/Debian
sudo apt-get install portaudio19-dev

# For local transcription (optional)
brew install whisper-cpp  # macOS
# Or build from source: https://github.com/ggerganov/whisper.cpp

Build

git clone https://github.com/ApplauseLab/yap.git
cd yap

# Install Wails CLI
go install github.com/wailsapp/wails/v2/cmd/wails@latest

# Build
wails build

# Run
open build/bin/Yap.app  # macOS

Development

# Install dependencies
cd frontend && npm install && cd ..

# Run in development mode with hot reload
wails dev

Permissions (macOS)

The app requires the following permissions:

  • Microphone — For audio recording
  • Accessibility — For global hotkey and auto-paste functionality

Documentation

For comprehensive documentation, visit applauselab.ai/docs/yap.

  • Getting Started — Installation, quick start, and permissions
  • User Guide — Recording, transcription, models, history, and settings
  • Developer Guide — Building from source, project structure, and contributing
  • Reference — API reference, configuration, troubleshooting, and FAQ

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Commit Convention

This project uses Conventional Commits. Commit messages are validated using commitlint.

feat: add new feature
fix: resolve bug
docs: update documentation
chore: maintenance task

License

MIT License — Copyright (c) 2024 Applause Lab

About

Yap is a fast, local-first, and cross-platform speech-to-text desktop application.

Resources

License

Stars

Watchers

Forks

Contributors