python-voiceio 0.2.3__tar.gz → 0.3.0__tar.gz

{python_voiceio-0.2.3/python_voiceio.egg-info → python_voiceio-0.3.0}/PKG-INFO

@@ -1,16 +1,20 @@
 Metadata-Version: 2.4
 Name: python-voiceio
-Version: 0.2.3
+Version: 0.3.0
 Summary: Speak → text, locally, instantly.
 Author: Hugo Montenegro
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/Hugo0/voiceio
+Project-URL: Repository, https://github.com/Hugo0/voiceio
 Project-URL: Issues, https://github.com/Hugo0/voiceio/issues
-Keywords: voice,speech-to-text,whisper,linux,dictation,wayland,ibus
+Project-URL: Changelog, https://github.com/Hugo0/voiceio/releases
+Keywords: voice,speech-to-text,whisper,linux,windows,dictation,wayland,ibus
 Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: X11 Applications
 Classifier: Intended Audience :: End Users/Desktop
 Classifier: Operating System :: POSIX :: Linux
+Classifier: Operating System :: Microsoft :: Windows
+Classifier: Operating System :: MacOS
 Classifier: Programming Language :: Python :: 3
 Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
 Requires-Python: >=3.11
@@ -19,14 +23,28 @@ License-File: LICENSE
 Requires-Dist: faster-whisper>=1.0.0
 Requires-Dist: sounddevice>=0.4.6
 Requires-Dist: numpy>=1.24.0
+Requires-Dist: onnxruntime>=1.16.0
+Requires-Dist: wordfreq>=3.0
 Requires-Dist: evdev>=1.6.0; sys_platform == "linux"
+Requires-Dist: pynput>=1.7.6; sys_platform == "win32"
+Requires-Dist: pynput>=1.7.6; sys_platform == "darwin"
+Requires-Dist: pyperclip>=1.8.0; sys_platform == "win32"
+Requires-Dist: win11toast>=0.36; sys_platform == "win32"
 Provides-Extra: x11
 Requires-Dist: pynput>=1.7.6; extra == "x11"
 Provides-Extra: mac
 Requires-Dist: pynput>=1.7.6; extra == "mac"
+Provides-Extra: win
+Requires-Dist: pynput>=1.7.6; extra == "win"
+Requires-Dist: pyperclip>=1.8.0; extra == "win"
+Requires-Dist: win11toast>=0.36; extra == "win"
 Provides-Extra: tray
 Requires-Dist: pystray>=0.19; extra == "tray"
 Requires-Dist: Pillow>=10.0; extra == "tray"
+Provides-Extra: tts
+Requires-Dist: piper-tts>=1.2.0; extra == "tts"
+Provides-Extra: tts-cloud
+Requires-Dist: edge-tts>=6.1.0; extra == "tts-cloud"
 Provides-Extra: dev
 Requires-Dist: pytest>=7.0; extra == "dev"
 Requires-Dist: pytest-mock; extra == "dev"
@@ -41,15 +59,6 @@ Dynamic: license-file
 
 Speak → text, locally, instantly.
 
-<!-- demo video -->
-<p align="center">
-  <a href="https://www.tella.tv/video/YOUR_VIDEO_ID">
-    <img src="https://github.com/Hugo0/voiceio/raw/main/assets/demo-thumbnail.png" alt="voiceio demo" width="600">
-  </a>
-  <br>
-  <em>Click to watch the demo</em>
-</p>
-
 ## Quick start
 
 ```bash
@@ -85,6 +94,31 @@ voiceio setup
 ```
 </details>
 
+<details>
+<summary><strong>Windows</strong></summary>
+
+```powershell
+# Option A: Install with pip (requires Python 3.11+)
+pip install python-voiceio
+voiceio setup
+
+# Option B: Download the installer from GitHub Releases (no Python needed)
+# https://github.com/Hugo0/voiceio/releases
+# Also available as a portable .zip if you prefer no installation.
+```
+
+Windows uses pynput for hotkeys and text injection. No extra system dependencies required.
+</details>
+
+<details>
+<summary><strong>macOS</strong></summary>
+
+```bash
+pipx install python-voiceio
+voiceio setup
+```
+</details>
+
 <details>
 <summary><strong>Build from source</strong></summary>
 
@@ -93,12 +127,16 @@ If you want the source code locally to hack on or customize for personal use. PR
 ```bash
 git clone https://github.com/Hugo0/voiceio
 cd voiceio
-pip install -e ".[linux,dev]"
-voiceio setup
+uv pip install -e ".[linux,dev]"
+
+# Bootstrap CLI commands onto PATH (creates ~/.local/bin/voiceio)
+uv run voiceio setup
 ```
+
+> **Note:** Source installs live inside a virtualenv, so `voiceio` isn't on PATH until setup creates symlinks in `~/.local/bin/`. If `voiceio` isn't found after setup, restart your terminal or run `export PATH="$HOME/.local/bin:$PATH"`.
 </details>
 
-> You can also install with `uv tool install voiceio` or `pip install voiceio`.
+> You can also install with `uv tool install python-voiceio` or `pip install python-voiceio`.
 
 ## How it works
 
@@ -107,11 +145,7 @@ hotkey → mic capture → whisper (local) → text at cursor
           pre-buffered   streaming        IBus / clipboard
 ```
 
-1. Press your hotkey: voiceio starts recording (with a 1-second pre-buffer, so it catches the beginning even if you start speaking before pressing)
-2. Speak naturally: text streams into the focused app in real-time as an underlined preview
-3. Press the hotkey again: the final transcription replaces the preview and is committed
-
-Transcription runs locally via [faster-whisper](https://github.com/SYSTRAN/faster-whisper). Text is injected through IBus (works in any GTK/Qt app: browsers, Telegram, editors) with an automatic clipboard fallback for terminals.
+Press your hotkey to start recording (1s pre-buffer catches the first syllable). Text streams into the focused app as an underlined preview. Press again to commit. Transcription runs locally via [faster-whisper](https://github.com/SYSTRAN/faster-whisper), text is injected through IBus (any GTK/Qt app) with clipboard fallback for terminals.
 
 ## Features
 
@@ -143,14 +177,18 @@ voiceio setup            Interactive setup wizard
 voiceio doctor           Health check (--fix to auto-repair)
 voiceio test             Test microphone + live transcription
 voiceio toggle           Toggle recording on a running daemon
-voiceio service install  Autostart on login via systemd
+voiceio update           Update to latest version
+voiceio service install  Autostart on login (systemd / Windows Startup)
 voiceio logs             View recent logs
 voiceio uninstall        Remove all system integrations
 ```
 
 ## Configuration
 
-`voiceio setup` handles everything interactively. To tweak later, edit `~/.config/voiceio/config.toml` or override at runtime:
+`voiceio setup` handles everything interactively. To tweak later, edit the config file or override at runtime:
+
+- Linux/macOS: `~/.config/voiceio/config.toml`
+- Windows: `%LOCALAPPDATA%\voiceio\config\config.toml`
 
 ```bash
 voiceio --model large-v3 --language auto -v
@@ -172,7 +210,9 @@ voiceio logs             # check debug output
 | Hotkey doesn't work on Wayland | `sudo usermod -aG input $USER` then log out and back in |
 | Transcription too slow | Use a smaller model: `voiceio --model tiny` |
 | Want to start fresh | `voiceio uninstall` then `voiceio setup` |
-| Doesn't work on MacOS | I haven't added proper support for apple yet. either use https://aquavoice.com/ or make a PR |
+| Windows: antivirus blocks hotkeys | pynput uses global keyboard hooks — add an exception for voiceio |
+| Windows: no sound feedback | Check `voiceio logs` for audio device info |
+| macOS issues | Experimental — consider [aquavoice.com](https://aquavoice.com/) or contribute a PR |
 
 ## Platform support
 
@@ -183,6 +223,7 @@ voiceio logs             # check debug output
 | Fedora (GNOME) | Supported | IBus | evdev / GNOME shortcut | Yes |
 | Arch Linux | Supported | IBus | evdev | Yes |
 | KDE / Sway / Hyprland | Should work | IBus / ydotool / wtype | evdev | Yes |
+| Windows 10/11 | Experimental | pynput / clipboard | pynput | Type-and-correct (no preedit) |
 | macOS | Experimental | pynput / clipboard | pynput | Type-and-correct (no preedit) |
 
 voiceio auto-detects your platform and picks the best available backends. Run `voiceio doctor` to see what's working on your system.
@@ -194,63 +235,36 @@ voiceio uninstall        # removes service, IBus, shortcuts, symlinks
 pipx uninstall python-voiceio   # removes the package
 ```
 
-## TODO
-
-**Launch**
-- [ ] Publish to PyPI
-- [ ] Record demo video + thumbnail
-- [ ] Test clean install on a fresh VM/container
-- [ ] GitHub repo: description, topics, social preview image
-- [ ] Bump version to 0.2.0
-
-**Code quality**
-- [ ] IBus activation on non-GNOME desktops (KDE, Sway, Hyprland), currently GNOME-only via gsettings
-- [ ] `voiceio doctor --json` for machine-readable output
-- [ ] Shell completions (`voiceio completion bash/zsh/fish`)
-- [ ] Refactor wizard.py (882 lines) into smaller, testable modules
-- [ ] Socket protocol versioning (e.g. `v1:preedit:text`)
-- [ ] Configurable log file path
-
-## Wishlist
-
-Contributions welcome! Open an issue to discuss before starting.
-
-**High impact**
-- [ ] **Text-to-speech (voice output)**: select text, press a hotkey, hear it spoken aloud. Completes the "io" in voiceio. Use a local TTS engine (Piper, Coqui, espeak-ng), same philosophy: no cloud, no API keys
-- [ ] **Wake word**: "Hey voiceio" hands-free activation (no hotkey needed). Use a small always-on keyword model (e.g. openWakeWord, Porcupine)
-- [ ] **Custom vocabulary / hot words**: user-defined word list for names, jargon, technical terms that Whisper gets wrong. Boost via `initial_prompt` or fine-tuned logit bias
-- [ ] **Per-app profiles**: different language/model/output settings per application (e.g. formal writing in docs, casual in chat)
-- [ ] **Voice commands**: "select all", "new line", "undo that", "delete last sentence". Parse transcribed text for command patterns before injecting
-- [ ] **Punctuation & formatting commands**: "period", "comma", "new paragraph", "capitalize that"
-- [ ] **Auto-punctuation model**: post-process Whisper output with a small punctuation/capitalization model for cleaner text
-
-**Platform expansion**
-- [ ] **macOS Input Method (IMKit)**: native streaming preedit on macOS, matching IBus quality on Linux
-- [ ] **Windows support**: Text Services Framework (TSF) for text injection, global hotkeys via win32api
-- [ ] **Flatpak / Snap packaging**: sandboxed distribution for Linux
-- [ ] **AUR package**: community package for Arch Linux
-
-**UX polish**
-- [ ] **System tray icon with recording animation**: pulsing/colored icon showing recording state, quick menu for model/language switching
-- [ ] **Desktop notifications with transcribed text**: show what was typed, with an undo button
-- [ ] **Confidence indicator**: visual hint when Whisper is uncertain (maybe highlight low-confidence words)
-- [ ] **Recording timeout**: auto-stop after N seconds of silence or max duration, preventing forgotten recordings
-- [ ] **Sound themes**: bundled sound packs (subtle, mechanical, sci-fi, none)
-- [ ] **First-run onboarding overlay**: lightweight "press Ctrl+Alt+V to start" hint on first launch
-
-**Power features**
-- [ ] **Multi-language in one session**: auto-detect language switches mid-dictation (Whisper supports this but needs tuning)
-- [ ] **Speaker diarization**: "Person 1: ... Person 2: ..." for meeting notes (via pyannote or whisperX)
-- [ ] **LLM post-processing**: pipe transcription through a local LLM (Ollama) for grammar correction, summarization, or reformatting
-- [ ] **Clipboard history**: keep last N transcriptions, quick-paste from history
-- [ ] **Transcription log / journal**: searchable history of everything you've dictated, with timestamps
-- [ ] **API / webhook**: expose a local API so other tools can trigger recording or receive transcriptions
-- [ ] **Browser extension**: inject text into web apps that don't work with IBus (e.g. some Electron apps)
-
-**Developer experience**
-- [ ] **Plugin system**: hooks for pre/post processing (e.g. custom formatters, translators, text transforms)
-- [ ] **Alternative STT backends**: support Whisper.cpp, Deepgram, AssemblyAI, OpenAI Whisper API as optional backends
-- [ ] **GPU acceleration docs**: CUDA/ROCm setup guide for faster transcription on large models
+## Roadmap
+
+Contributions welcome! See [CONTRIBUTING.md](CONTRIBUTING.md) and [open issues](https://github.com/Hugo0/voiceio/issues).
+
+**Now**
+- [ ] macOS polish (IMKit for native preedit, Accessibility API for text injection)
+
+**Soon**
+- [ ] Per-app context awareness (detect focused app, adapt formatting/behavior)
+- [ ] File/audio transcription mode (`voiceio transcribe recording.mp3`)
+
+**Backlog**
+- [ ] Multiple engine backends (whisper.cpp for Vulkan/AMD, VOSK for low-end hardware)
+- [ ] Echo cancellation (filter system audio for meeting use)
+- [ ] Wake word activation ("Hey voiceio")
+- [ ] Text-to-speech output (Piper/espeak-ng — completes the "io")
+
+**Done**
+- [x] LLM auto-audit dictionary (`voiceio correct --auto` — scan history with LLM, interactive correction)
+- [x] LLM post-processing via Ollama (grammar cleanup, spelling fixes on final pass)
+- [x] Corrections dictionary — auto-replace misheard words, "correct that" voice command
+- [x] Transcription history — searchable log of everything you've dictated
+- [x] Number-to-digit conversion ("three hundred forty two" → "342")
+- [x] VAD-based silence filtering (Silero VAD, prevents Whisper hallucinations)
+- [x] Voice commands — "new line", "new paragraph", "scratch that", punctuation by name
+- [x] Custom vocabulary / personal dictionary (bias Whisper via `initial_prompt`)
+- [x] Smart punctuation & capitalization post-processing
+- [x] Windows support
+- [x] System tray icon with animated states
+- [x] Auto-stop on silence
 
 ## License
 

python_voiceio-0.3.0/README.md

@@ -0,0 +1,219 @@
+# voiceio
+
+[![CI](https://github.com/Hugo0/voiceio/actions/workflows/ci.yml/badge.svg)](https://github.com/Hugo0/voiceio/actions/workflows/ci.yml)
+[![PyPI](https://img.shields.io/pypi/v/python-voiceio)](https://pypi.org/project/python-voiceio/)
+[![Python](https://img.shields.io/pypi/pyversions/python-voiceio)](https://pypi.org/project/python-voiceio/)
+[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
+
+Speak → text, locally, instantly.
+
+## Quick start
+
+```bash
+# 1. Install system dependencies (Ubuntu/Debian)
+sudo apt install pipx ibus gir1.2-ibus-1.0 python3-gi portaudio19-dev
+
+# 2. Install voiceio
+pipx install python-voiceio
+
+# 3. Run the setup wizard
+voiceio setup
+```
+
+That's it. Press **Ctrl+Alt+V** (or your chosen hotkey) to start dictating.
+
+<details>
+<summary><strong>Fedora</strong></summary>
+
+```bash
+sudo dnf install pipx ibus python3-gobject portaudio-devel
+pipx install python-voiceio
+voiceio setup
+```
+</details>
+
+<details>
+<summary><strong>Arch Linux</strong></summary>
+
+```bash
+sudo pacman -S python-pipx ibus python-gobject portaudio
+pipx install python-voiceio
+voiceio setup
+```
+</details>
+
+<details>
+<summary><strong>Windows</strong></summary>
+
+```powershell
+# Option A: Install with pip (requires Python 3.11+)
+pip install python-voiceio
+voiceio setup
+
+# Option B: Download the installer from GitHub Releases (no Python needed)
+# https://github.com/Hugo0/voiceio/releases
+# Also available as a portable .zip if you prefer no installation.
+```
+
+Windows uses pynput for hotkeys and text injection. No extra system dependencies required.
+</details>
+
+<details>
+<summary><strong>macOS</strong></summary>
+
+```bash
+pipx install python-voiceio
+voiceio setup
+```
+</details>
+
+<details>
+<summary><strong>Build from source</strong></summary>
+
+If you want the source code locally to hack on or customize for personal use. PRs are welcome!
+
+```bash
+git clone https://github.com/Hugo0/voiceio
+cd voiceio
+uv pip install -e ".[linux,dev]"
+
+# Bootstrap CLI commands onto PATH (creates ~/.local/bin/voiceio)
+uv run voiceio setup
+```
+
+> **Note:** Source installs live inside a virtualenv, so `voiceio` isn't on PATH until setup creates symlinks in `~/.local/bin/`. If `voiceio` isn't found after setup, restart your terminal or run `export PATH="$HOME/.local/bin:$PATH"`.
+</details>
+
+> You can also install with `uv tool install python-voiceio` or `pip install python-voiceio`.
+
+## How it works
+
+```
+hotkey → mic capture → whisper (local) → text at cursor
+          pre-buffered   streaming        IBus / clipboard
+```
+
+Press your hotkey to start recording (1s pre-buffer catches the first syllable). Text streams into the focused app as an underlined preview. Press again to commit. Transcription runs locally via [faster-whisper](https://github.com/SYSTRAN/faster-whisper), text is injected through IBus (any GTK/Qt app) with clipboard fallback for terminals.
+
+## Features
+
+- **Streaming**: text appears as you speak, not after you stop
+- **Works everywhere**: IBus input method for GUI apps, clipboard for terminals
+- **Wayland + X11**: evdev hotkeys work on both, no root required
+- **Pre-buffer**: never miss the first syllable
+- **Auto-healing**: falls back to the next working backend if one fails
+- **Autostart**: optional systemd service, restarts on crash
+- **Self-diagnosing**: `voiceio doctor` checks everything, `--fix` repairs it
+
+## Models
+
+| Model | Size | Speed | Accuracy | Good for |
+|-------|------|-------|----------|----------|
+| `tiny` | 75 MB | ~10x realtime | Basic | Quick notes, low-end hardware |
+| `base` | 150 MB | ~7x realtime | Good | Daily use (default) |
+| `small` | 500 MB | ~4x realtime | Better | Longer dictation |
+| `medium` | 1.5 GB | ~2x realtime | Great | Accuracy-sensitive work |
+| `large-v3` | 3 GB | ~1x realtime | Best | Maximum quality, GPU recommended |
+
+Models download automatically on first use. Switch anytime: `voiceio --model small`.
+
+## Commands
+
+```
+voiceio                  Start the daemon
+voiceio setup            Interactive setup wizard
+voiceio doctor           Health check (--fix to auto-repair)
+voiceio test             Test microphone + live transcription
+voiceio toggle           Toggle recording on a running daemon
+voiceio update           Update to latest version
+voiceio service install  Autostart on login (systemd / Windows Startup)
+voiceio logs             View recent logs
+voiceio uninstall        Remove all system integrations
+```
+
+## Configuration
+
+`voiceio setup` handles everything interactively. To tweak later, edit the config file or override at runtime:
+
+- Linux/macOS: `~/.config/voiceio/config.toml`
+- Windows: `%LOCALAPPDATA%\voiceio\config\config.toml`
+
+```bash
+voiceio --model large-v3 --language auto -v
+```
+
+See [config.example.toml](config.example.toml) for all options.
+
+## Troubleshooting
+
+```bash
+voiceio doctor           # see what's working
+voiceio doctor --fix     # auto-fix issues
+voiceio logs             # check debug output
+```
+
+| Problem | Fix |
+|---------|-----|
+| No text appears | `voiceio doctor --fix` - usually a missing IBus component or GNOME input source |
+| Hotkey doesn't work on Wayland | `sudo usermod -aG input $USER` then log out and back in |
+| Transcription too slow | Use a smaller model: `voiceio --model tiny` |
+| Want to start fresh | `voiceio uninstall` then `voiceio setup` |
+| Windows: antivirus blocks hotkeys | pynput uses global keyboard hooks — add an exception for voiceio |
+| Windows: no sound feedback | Check `voiceio logs` for audio device info |
+| macOS issues | Experimental — consider [aquavoice.com](https://aquavoice.com/) or contribute a PR |
+
+## Platform support
+
+| Platform | Status | Text injection | Hotkeys | Streaming preview |
+|----------|--------|---------------|---------|-------------------|
+| Ubuntu / Debian (GNOME, Wayland) | **Tested daily** | IBus | evdev / GNOME shortcut | Yes |
+| Ubuntu / Debian (GNOME, X11) | Supported | IBus | evdev / pynput | Yes |
+| Fedora (GNOME) | Supported | IBus | evdev / GNOME shortcut | Yes |
+| Arch Linux | Supported | IBus | evdev | Yes |
+| KDE / Sway / Hyprland | Should work | IBus / ydotool / wtype | evdev | Yes |
+| Windows 10/11 | Experimental | pynput / clipboard | pynput | Type-and-correct (no preedit) |
+| macOS | Experimental | pynput / clipboard | pynput | Type-and-correct (no preedit) |
+
+voiceio auto-detects your platform and picks the best available backends. Run `voiceio doctor` to see what's working on your system.
+
+## Uninstall
+
+```bash
+voiceio uninstall        # removes service, IBus, shortcuts, symlinks
+pipx uninstall python-voiceio   # removes the package
+```
+
+## Roadmap
+
+Contributions welcome! See [CONTRIBUTING.md](CONTRIBUTING.md) and [open issues](https://github.com/Hugo0/voiceio/issues).
+
+**Now**
+- [ ] macOS polish (IMKit for native preedit, Accessibility API for text injection)
+
+**Soon**
+- [ ] Per-app context awareness (detect focused app, adapt formatting/behavior)
+- [ ] File/audio transcription mode (`voiceio transcribe recording.mp3`)
+
+**Backlog**
+- [ ] Multiple engine backends (whisper.cpp for Vulkan/AMD, VOSK for low-end hardware)
+- [ ] Echo cancellation (filter system audio for meeting use)
+- [ ] Wake word activation ("Hey voiceio")
+- [ ] Text-to-speech output (Piper/espeak-ng — completes the "io")
+
+**Done**
+- [x] LLM auto-audit dictionary (`voiceio correct --auto` — scan history with LLM, interactive correction)
+- [x] LLM post-processing via Ollama (grammar cleanup, spelling fixes on final pass)
+- [x] Corrections dictionary — auto-replace misheard words, "correct that" voice command
+- [x] Transcription history — searchable log of everything you've dictated
+- [x] Number-to-digit conversion ("three hundred forty two" → "342")
+- [x] VAD-based silence filtering (Silero VAD, prevents Whisper hallucinations)
+- [x] Voice commands — "new line", "new paragraph", "scratch that", punctuation by name
+- [x] Custom vocabulary / personal dictionary (bias Whisper via `initial_prompt`)
+- [x] Smart punctuation & capitalization post-processing
+- [x] Windows support
+- [x] System tray icon with animated states
+- [x] Auto-stop on silence
+
+## License
+
+MIT

{python_voiceio-0.2.3 → python_voiceio-0.3.0}/pyproject.toml

@@ -4,18 +4,20 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "python-voiceio"
-version = "0.2.3"
+version = "0.3.0"
 description = "Speak → text, locally, instantly."
 readme = "README.md"
 license = "MIT"
 requires-python = ">=3.11"
 authors = [{ name = "Hugo Montenegro" }]
-keywords = ["voice", "speech-to-text", "whisper", "linux", "dictation", "wayland", "ibus"]
+keywords = ["voice", "speech-to-text", "whisper", "linux", "windows", "dictation", "wayland", "ibus"]
 classifiers = [
     "Development Status :: 4 - Beta",
     "Environment :: X11 Applications",
     "Intended Audience :: End Users/Desktop",
     "Operating System :: POSIX :: Linux",
+    "Operating System :: Microsoft :: Windows",
+    "Operating System :: MacOS",
     "Programming Language :: Python :: 3",
     "Topic :: Multimedia :: Sound/Audio :: Speech",
 ]
@@ -23,18 +25,29 @@ dependencies = [
     "faster-whisper>=1.0.0",
     "sounddevice>=0.4.6",
     "numpy>=1.24.0",
+    "onnxruntime>=1.16.0",
+    "wordfreq>=3.0",
     "evdev>=1.6.0; sys_platform == 'linux'",
+    "pynput>=1.7.6; sys_platform == 'win32'",
+    "pynput>=1.7.6; sys_platform == 'darwin'",
+    "pyperclip>=1.8.0; sys_platform == 'win32'",
+    "win11toast>=0.36; sys_platform == 'win32'",
 ]
 
 [project.optional-dependencies]
 x11 = ["pynput>=1.7.6"]
 mac = ["pynput>=1.7.6"]
+win = ["pynput>=1.7.6", "pyperclip>=1.8.0", "win11toast>=0.36"]
 tray = ["pystray>=0.19", "Pillow>=10.0"]
+tts = ["piper-tts>=1.2.0"]
+tts-cloud = ["edge-tts>=6.1.0"]
 dev = ["pytest>=7.0", "pytest-mock"]
 
 [project.urls]
 Homepage = "https://github.com/Hugo0/voiceio"
+Repository = "https://github.com/Hugo0/voiceio"
 Issues = "https://github.com/Hugo0/voiceio/issues"
+Changelog = "https://github.com/Hugo0/voiceio/releases"
 
 [project.scripts]
 voiceio = "voiceio.cli:main"
@@ -52,3 +65,4 @@ include = ["voiceio*"]
 
 [tool.setuptools.package-data]
 "voiceio.sounds" = ["*.wav"]
+"voiceio.models" = ["*.onnx"]