speaksy

talk it. type it. ship it.

Voice typing for Linux that actually works.
Hold a key, speak, release — your words appear wherever you're typing.

---

Demo

$ speaksy

  ╭────────────────────────────────────────╮
  │  SPEAKSY                               │
  │  talk it. type it. ship it.            │
  ╰────────────────────────────────────────╯

  Status: vibing
  Hotkeys: Right Ctrl (hold) | F8 (toggle)

speaksy> _

---

Quick Start

# Install
pipx install speaksy

# Run (interactive setup on first launch)
speaksy

That's it. 30 seconds to voice typing.

---

Features

	Feature	Description
Speed	< 1 second latency	Groq's Whisper API is blazing fast
Smart	AI text cleanup	Fixes grammar, removes "um", "uh", "like"
Free	No credit card	Groq's free tier is generous
Offline	Local fallback	Works without internet via faster-whisper
Private	Privacy mode	Keep voice 100% on your machine
Auto	Runs on login	Always ready when you are

---

How It Works

┌─────────────┐    ┌─────────────┐    ┌─────────────┐    ┌─────────────┐
│  Hold Key   │ -> │   Speak     │ -> │  Release    │ -> │ Text Appears│
│  (Right Ctrl)    │  naturally  │    │   key       │    │  at cursor  │
└─────────────┘    └─────────────┘    └─────────────┘    └─────────────┘
                            |
                            v
                   ┌─────────────────┐
                   │  Groq Whisper   │
                   │  + LLM cleanup  │
                   └─────────────────┘

1. Press hotkey (Right Ctrl = hold, F8 = toggle)
2. Speak naturally
3. Release — text appears in < 1 second

Works everywhere: browser, terminal, IDE, Slack, Discord, anywhere you type.

---

Commands

Run speaksy to open the interactive CLI:

Command	Description
/setup	Configure API key & hotkeys
/start	Start voice typing
/stop	Take a break
/status	Check the vibe
/logs	View receipts
/config	Tweak settings
/help	Get backup
/quit	Peace out

---

Requirements

• OS: Linux (X11 or XWayland)
• Python: 3.10+
• API Key: Free from console.groq.com

System dependencies (auto-installed during setup):

sudo apt install xclip xdotool

---

Privacy Mode

By default, audio goes to Groq for fast transcription. Want to keep it local?

speaksy> /config
# Select "Privacy mode" -> "local"

Local mode uses faster-whisper on your CPU. Slower (~3-5s) but your voice never leaves your machine.

---

Troubleshooting

No audio input detected

• Check your mic is connected
• Run arecord -l to list audio devices

Text not appearing

• Install dependencies: sudo apt install xclip xdotool
• Some pure Wayland apps may not work with xdotool

Service won't start

• Check logs: run speaksy then /logs
• Verify API key at console.groq.com

---

Uninstall

# Stop service
speaksy
# > /stop
# > /quit

# Remove package
pipx uninstall speaksy

# Remove config (optional)
rm -rf ~/.config/speaksy
rm ~/.config/systemd/user/speaksy.service
systemctl --user daemon-reload

---

Tech Stack

• STT: Groq Whisper API / faster-whisper
• LLM: Llama 3.1 8B (via Groq) for text cleanup
• Audio: sounddevice
• Hotkeys: pynput
• CLI: Rich

---

Contributing

PRs and issues welcome!

Report Bug · Request Feature

---

License

MIT - do whatever you want with it.

---

_{Built with caffeine and voice commands}