2 releases
Uses new Rust 2024
| 0.7.2 | Jan 20, 2026 |
|---|---|
| 0.7.1 | Jan 18, 2026 |
#665 in Audio
530KB
10K
SLoC
Introduction
The terminal-native voice-to-text tool. Record, transcribe, paste — all from your shell. Supports hotkey mode, presets, and pipes nicely with AI assistants.
Quick Start
cargo install whis-cli
whis setup # Interactive wizard
whis
Usage
# Record once
whis # Press Enter to stop — text copied!
# Background service (hotkey mode)
whis start # Start service (ctrl+alt+w toggles recording)
whis stop # Stop background service
whis status # Check if running
# Transcribe from file
whis -f recording.wav # Transcribe a WAV file
# Output options
whis --print # Print to stdout instead of clipboard
whis -d 10 # Record for 10 seconds (non-interactive)
whis -v # Verbose output
# Presets
whis --as email # Use preset (auto-enables post-processing)
whis preset # List all
whis preset new # Print template for new preset
whis preset edit xyz # Edit preset in $EDITOR
# Post-process with LLM (presets define the transformation)
whis --post-process
# Configuration
whis config # Show current settings
whis config provider openai # Set provider
whis config language en # Set language hint
whis model # List available models
Environment Variables
API keys can be set via environment variables instead of whis setup:
OPENAI_API_KEY=sk-...
MISTRAL_API_KEY=...
GROQ_API_KEY=gsk_...
DEEPGRAM_API_KEY=...
ELEVENLABS_API_KEY=...
OLLAMA_URL=http://localhost:11434 # Default
OLLAMA_MODEL=qwen2.5:1.5b # Default post-processing model
Requirements
- API key from OpenAI, Mistral, Groq, Deepgram, or ElevenLabs — or use local Whisper/Parakeet (no API key needed)
- Linux (X11/Wayland), macOS, or Windows
For hotkey mode (Linux):
# Option 1: Compositor keybinding (no permissions needed)
# GNOME: Settings > Keyboard > Custom Shortcuts → whis toggle
# Sway: bindsym Ctrl+Alt+w exec whis toggle
# Option 2: Direct capture
sudo usermod -aG input $USER
# Logout and login, then: whis start
Prefer a GUI?
See whis-desktop — same functionality, with system tray.
License
MIT
Dependencies
~14–56MB
~845K SLoC