speaksy 0.1.0__py3-none-any.whl

speaksy/service.py

@@ -0,0 +1,205 @@
+"""Systemd service management for Speaksy."""
+
+import os
+import shutil
+import subprocess
+import sys
+from datetime import datetime
+from pathlib import Path
+
+from speaksy.config import CONFIG_DIR, ENV_FILE
+
+SYSTEMD_USER_DIR = Path.home() / ".config" / "systemd" / "user"
+SERVICE_FILE = SYSTEMD_USER_DIR / "speaksy.service"
+
+SERVICE_TEMPLATE = """[Unit]
+Description=Speaksy - Voice Typing for Linux
+After=graphical-session.target
+PartOf=graphical-session.target
+
+[Service]
+Type=simple
+ExecStart={python_path} -m speaksy.runner
+Restart=on-failure
+RestartSec=5
+EnvironmentFile={env_file}
+
+[Install]
+WantedBy=graphical-session.target
+"""
+
+
+def get_python_path() -> str:
+    """Get the path to the current Python interpreter."""
+    return sys.executable
+
+
+def install_service() -> bool:
+    """Install the systemd user service."""
+    try:
+        SYSTEMD_USER_DIR.mkdir(parents=True, exist_ok=True)
+
+        service_content = SERVICE_TEMPLATE.format(
+            python_path=get_python_path(),
+            env_file=ENV_FILE,
+        )
+
+        with open(SERVICE_FILE, "w") as f:
+            f.write(service_content)
+
+        # Reload systemd
+        subprocess.run(
+            ["systemctl", "--user", "daemon-reload"],
+            check=True,
+            capture_output=True,
+        )
+
+        # Enable the service
+        subprocess.run(
+            ["systemctl", "--user", "enable", "speaksy.service"],
+            check=True,
+            capture_output=True,
+        )
+
+        return True
+    except Exception as e:
+        return False
+
+
+def uninstall_service() -> bool:
+    """Uninstall the systemd user service."""
+    try:
+        stop_service()
+
+        subprocess.run(
+            ["systemctl", "--user", "disable", "speaksy.service"],
+            capture_output=True,
+        )
+
+        if SERVICE_FILE.exists():
+            SERVICE_FILE.unlink()
+
+        subprocess.run(
+            ["systemctl", "--user", "daemon-reload"],
+            capture_output=True,
+        )
+
+        return True
+    except Exception:
+        return False
+
+
+def start_service() -> bool:
+    """Start the speaksy service."""
+    try:
+        result = subprocess.run(
+            ["systemctl", "--user", "start", "speaksy.service"],
+            capture_output=True,
+            text=True,
+        )
+        return result.returncode == 0
+    except Exception:
+        return False
+
+
+def stop_service() -> bool:
+    """Stop the speaksy service."""
+    try:
+        result = subprocess.run(
+            ["systemctl", "--user", "stop", "speaksy.service"],
+            capture_output=True,
+            text=True,
+        )
+        return result.returncode == 0
+    except Exception:
+        return False
+
+
+def restart_service() -> bool:
+    """Restart the speaksy service."""
+    try:
+        result = subprocess.run(
+            ["systemctl", "--user", "restart", "speaksy.service"],
+            capture_output=True,
+            text=True,
+        )
+        return result.returncode == 0
+    except Exception:
+        return False
+
+
+def is_running() -> bool:
+    """Check if the speaksy service is running."""
+    try:
+        result = subprocess.run(
+            ["systemctl", "--user", "is-active", "speaksy.service"],
+            capture_output=True,
+            text=True,
+        )
+        return result.stdout.strip() == "active"
+    except Exception:
+        return False
+
+
+def is_installed() -> bool:
+    """Check if the service is installed."""
+    return SERVICE_FILE.exists()
+
+
+def get_uptime() -> str:
+    """Get how long the service has been running."""
+    try:
+        result = subprocess.run(
+            [
+                "systemctl", "--user", "show", "speaksy.service",
+                "--property=ActiveEnterTimestamp",
+            ],
+            capture_output=True,
+            text=True,
+        )
+        if result.returncode == 0:
+            line = result.stdout.strip()
+            if "=" in line:
+                timestamp_str = line.split("=", 1)[1].strip()
+                if timestamp_str:
+                    # Parse timestamp and calculate uptime
+                    try:
+                        # Format: "Thu 2026-02-05 16:23:51 CST"
+                        from dateutil import parser
+                        start_time = parser.parse(timestamp_str)
+                        delta = datetime.now(start_time.tzinfo) - start_time
+                        hours, remainder = divmod(int(delta.total_seconds()), 3600)
+                        minutes, _ = divmod(remainder, 60)
+                        if hours > 0:
+                            return f"{hours}h {minutes}m"
+                        return f"{minutes}m"
+                    except Exception:
+                        pass
+        return "unknown"
+    except Exception:
+        return "unknown"
+
+
+def get_logs(lines: int = 20) -> str:
+    """Get recent service logs."""
+    try:
+        result = subprocess.run(
+            [
+                "journalctl", "--user", "-u", "speaksy.service",
+                "-n", str(lines), "--no-pager",
+            ],
+            capture_output=True,
+            text=True,
+        )
+        return result.stdout if result.returncode == 0 else "No logs available"
+    except Exception:
+        return "Unable to fetch logs"
+
+
+def get_status() -> dict:
+    """Get comprehensive service status."""
+    return {
+        "installed": is_installed(),
+        "running": is_running(),
+        "uptime": get_uptime() if is_running() else None,
+    }

speaksy/setup_wizard.py

@@ -0,0 +1,216 @@
+"""Interactive setup wizard for Speaksy."""
+
+import shutil
+import subprocess
+
+import httpx
+from rich.console import Console
+from rich.panel import Panel
+from rich.prompt import Confirm, Prompt
+
+from speaksy import config
+from speaksy import service
+
+console = Console()
+
+
+def check_system_deps() -> dict:
+    """Check if required system dependencies are installed."""
+    deps = {
+        "xclip": shutil.which("xclip") is not None,
+        "xdotool": shutil.which("xdotool") is not None,
+    }
+
+    # Check audio
+    try:
+        import sounddevice as sd
+        devices = sd.query_devices()
+        deps["audio"] = any(d.get("max_input_channels", 0) > 0 for d in devices)
+    except Exception:
+        deps["audio"] = False
+
+    return deps
+
+
+def install_missing_deps(missing: list) -> bool:
+    """Attempt to install missing dependencies."""
+    console.print("\n[yellow]trying to install missing deps...[/yellow]")
+
+    apt_packages = []
+    if "xclip" in missing:
+        apt_packages.append("xclip")
+    if "xdotool" in missing:
+        apt_packages.append("xdotool")
+
+    if apt_packages:
+        try:
+            cmd = ["sudo", "apt", "install", "-y"] + apt_packages
+            result = subprocess.run(cmd, capture_output=True, text=True)
+            if result.returncode != 0:
+                console.print("[red]failed to install. try manually:[/red]")
+                console.print(f"[dim]sudo apt install {' '.join(apt_packages)}[/dim]")
+                return False
+        except Exception:
+            console.print("[red]couldn't run apt. install manually:[/red]")
+            console.print(f"[dim]sudo apt install {' '.join(apt_packages)}[/dim]")
+            return False
+
+    return True
+
+
+def validate_api_key(api_key: str) -> tuple:
+    """Validate the Groq API key by making a test request."""
+    try:
+        resp = httpx.get(
+            "https://api.groq.com/openai/v1/models",
+            headers={"Authorization": f"Bearer {api_key}"},
+            timeout=10.0,
+        )
+        if resp.status_code == 200:
+            return True, None
+        elif resp.status_code == 401:
+            return False, "invalid_api_key"
+        else:
+            return False, f"api_error_{resp.status_code}"
+    except httpx.TimeoutException:
+        return False, "timeout"
+    except Exception as e:
+        return False, str(e)
+
+
+def run_setup():
+    """Run the interactive setup wizard."""
+    console.print()
+    console.print("[bold cyan]aight let's get you set up real quick[/bold cyan]")
+    console.print()
+    console.print("[dim]" + "━" * 40 + "[/dim]")
+    console.print()
+
+    # Check system deps
+    console.print("[bold]checking system deps...[/bold]")
+    deps = check_system_deps()
+
+    all_good = True
+    for dep, found in deps.items():
+        if found:
+            console.print(f"   [green]├─ {dep}: found ✓[/green]")
+        else:
+            console.print(f"   [red]├─ {dep}: missing ✗[/red]")
+            all_good = False
+
+    if not all_good:
+        missing = [d for d, found in deps.items() if not found]
+        if "audio" in missing:
+            console.print("\n[red]no audio input detected. check your mic![/red]")
+            missing.remove("audio")
+
+        if missing:
+            if Confirm.ask("\n[yellow]want me to try installing missing deps?[/yellow]"):
+                if not install_missing_deps(missing):
+                    return False
+                # Recheck
+                deps = check_system_deps()
+                if not all(deps.values()):
+                    console.print("\n[red]still missing deps. fix and try again[/red]")
+                    return False
+            else:
+                console.print("\n[yellow]install them manually and run /setup again[/yellow]")
+                return False
+
+    console.print()
+
+    # Get API key
+    console.print("[bold]drop your Groq API key[/bold]")
+    console.print("[dim](get one free at console.groq.com/keys)[/dim]")
+    console.print()
+
+    while True:
+        api_key = Prompt.ask("   [cyan]key[/cyan]", password=True)
+
+        if not api_key:
+            console.print("   [red]need a key to continue[/red]")
+            continue
+
+        if not api_key.startswith("gsk_"):
+            console.print("   [yellow]hmm that doesn't look like a groq key[/yellow]")
+            console.print("   [dim]should start with gsk_[/dim]")
+            continue
+
+        console.print("   [dim]validating...[/dim]", end=" ")
+        valid, error = validate_api_key(api_key)
+
+        if valid:
+            console.print("[green]we're in ✓[/green]")
+            break
+        else:
+            console.print(f"[red]nah that ain't it[/red]")
+            if error == "invalid_api_key":
+                console.print("   [dim]double check your key and try again[/dim]")
+            else:
+                console.print(f"   [dim]error: {error}[/dim]")
+
+    # Save API key
+    config.save_api_key(api_key)
+    console.print()
+
+    # Hotkey customization
+    if Confirm.ask("[bold]wanna customize hotkeys?[/bold]", default=False):
+        console.print()
+        console.print("[dim]examples: Key.ctrl_r, Key.f8, Key.alt_l[/dim]")
+
+        current_ptt, current_toggle = config.get_hotkeys()
+
+        ptt = Prompt.ask(
+            f"   [cyan]push-to-talk[/cyan] [dim](default: {current_ptt})[/dim]",
+            default=current_ptt,
+        )
+        toggle = Prompt.ask(
+            f"   [cyan]toggle mode[/cyan] [dim](default: {current_toggle})[/dim]",
+            default=current_toggle,
+        )
+
+        config.set_hotkeys(ptt, toggle)
+        console.print("   [green]locked in ✓[/green]")
+    else:
+        # Save default config
+        cfg = config.load_config()
+        config.save_config(cfg)
+
+    console.print()
+
+    # Install service
+    console.print("[bold]installing service...[/bold]")
+    if service.install_service():
+        console.print("   [green]└─ auto-start on login: enabled ✓[/green]")
+    else:
+        console.print("   [red]└─ failed to install service[/red]")
+        return False
+
+    # Start service
+    console.print()
+    console.print("[dim]starting speaksy...[/dim]")
+    if service.start_service():
+        console.print("[green]service started ✓[/green]")
+    else:
+        console.print("[red]failed to start service[/red]")
+        return False
+
+    console.print()
+    console.print("[dim]" + "━" * 40 + "[/dim]")
+    console.print()
+
+    # Success message
+    ptt, toggle = config.get_hotkeys()
+    ptt_display = ptt.replace("Key.", "").replace("_", " ").title()
+    toggle_display = toggle.replace("Key.", "").upper()
+
+    console.print("[bold green]you're all set fam![/bold green]")
+    console.print()
+    console.print(f"   [cyan]hold {ptt_display}[/cyan] = push-to-talk")
+    console.print(f"   [cyan]tap {toggle_display}[/cyan] = toggle on/off")
+    console.print()
+    console.print("[dim]speaksy is now running in the background[/dim]")
+    console.print("[dim]just start talking wherever you type ✨[/dim]")
+    console.print()
+
+    return True

speaksy-0.1.0.dist-info/METADATA

@@ -0,0 +1,246 @@
+Metadata-Version: 2.4
+Name: speaksy
+Version: 0.1.0
+Summary: Voice typing for Linux. Talk it. Type it. Ship it.
+Project-URL: Homepage, https://github.com/oneKn8/speaksy
+Project-URL: Repository, https://github.com/oneKn8/speaksy
+Project-URL: Issues, https://github.com/oneKn8/speaksy/issues
+Author: oneknight
+License-Expression: MIT
+License-File: LICENSE
+Keywords: dictation,linux,speech-to-text,typing,voice,whisper
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: End Users/Desktop
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
+Classifier: Topic :: Text Processing
+Requires-Python: >=3.10
+Requires-Dist: faster-whisper>=1.1.0
+Requires-Dist: httpx>=0.27.0
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: pillow>=10.0.0
+Requires-Dist: pynput>=1.7.0
+Requires-Dist: pystray>=0.19.0
+Requires-Dist: python-dotenv>=1.0.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: rich>=13.0.0
+Requires-Dist: sounddevice>=0.5.0
+Description-Content-Type: text/markdown
+
+<p align="center">
+  <img src="https://img.shields.io/badge/speaksy-voice%20typing-blueviolet?style=for-the-badge&logo=microphone" alt="speaksy">
+</p>
+
+<h1 align="center">speaksy</h1>
+
+<p align="center">
+  <strong>talk it. type it. ship it.</strong>
+</p>
+
+<p align="center">
+  <a href="https://github.com/oneKn8/speaksy/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-green.svg" alt="License"></a>
+  <a href="https://www.python.org/downloads/"><img src="https://img.shields.io/badge/python-3.10+-blue.svg" alt="Python"></a>
+  <a href="https://github.com/oneKn8/speaksy"><img src="https://img.shields.io/badge/platform-Linux-orange.svg" alt="Platform"></a>
+  <a href="https://console.groq.com"><img src="https://img.shields.io/badge/powered%20by-Groq-ff6600.svg" alt="Groq"></a>
+</p>
+
+<p align="center">
+  <em>Voice typing for Linux that actually works.<br>Hold a key, speak, release — your words appear wherever you're typing.</em>
+</p>
+
+---
+
+## Demo
+
+```
+$ speaksy
+
+  ╭────────────────────────────────────────╮
+  │  SPEAKSY                               │
+  │  talk it. type it. ship it.            │
+  ╰────────────────────────────────────────╯
+
+  Status: vibing
+  Hotkeys: Right Ctrl (hold) | F8 (toggle)
+
+speaksy> _
+```
+
+<!-- TODO: Add demo GIF here -->
+<!-- ![Demo](assets/demo.gif) -->
+
+---
+
+## Quick Start
+
+```bash
+# 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](https://console.groq.com)
+
+System dependencies (auto-installed during setup):
+```bash
+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](https://github.com/SYSTRAN/faster-whisper) on your CPU. Slower (~3-5s) but your voice never leaves your machine.
+
+---
+
+## Troubleshooting
+
+<details>
+<summary><strong>No audio input detected</strong></summary>
+
+- Check your mic is connected
+- Run `arecord -l` to list audio devices
+</details>
+
+<details>
+<summary><strong>Text not appearing</strong></summary>
+
+- Install dependencies: `sudo apt install xclip xdotool`
+- Some pure Wayland apps may not work with xdotool
+</details>
+
+<details>
+<summary><strong>Service won't start</strong></summary>
+
+- Check logs: run `speaksy` then `/logs`
+- Verify API key at console.groq.com
+</details>
+
+---
+
+## Uninstall
+
+```bash
+# 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](https://groq.com) / [faster-whisper](https://github.com/SYSTRAN/faster-whisper)
+- **LLM:** Llama 3.1 8B (via Groq) for text cleanup
+- **Audio:** [sounddevice](https://python-sounddevice.readthedocs.io/)
+- **Hotkeys:** [pynput](https://pynput.readthedocs.io/)
+- **CLI:** [Rich](https://rich.readthedocs.io/)
+
+---
+
+## Contributing
+
+PRs and issues welcome!
+
+<a href="https://github.com/oneKn8/speaksy/issues">Report Bug</a>
+·
+<a href="https://github.com/oneKn8/speaksy/issues">Request Feature</a>
+
+---
+
+## License
+
+MIT - do whatever you want with it.
+
+---
+
+<p align="center">
+  <sub>Built with caffeine and voice commands</sub>
+</p>

speaksy-0.1.0.dist-info/RECORD

@@ -0,0 +1,13 @@
+speaksy/__init__.py,sha256=eG5kdi4U1tayyWwhBUByiHrdFcZpCJ6bninHJclA4VU,63
+speaksy/__main__.py,sha256=Y5c4dtERDNv0x1C-HcP1nauSAbssfyuP7MlyN8l1M28,110
+speaksy/cli.py,sha256=Fd-g5g11RMFyKgpdYGtvQAuYIVY6BcL7nyOwFa5GMHM,10225
+speaksy/config.py,sha256=bGiATdV79E27pu7TQTm2VxDDdAKYdzjQrrIbu5GCz2o,4163
+speaksy/core.py,sha256=xkE0KtS3paGzZSnc481R47bECnns3_wSXkysSW66Uzs,16987
+speaksy/runner.py,sha256=l5aiczErHVLBc3Ir3XIfqxZUAiq4tN6T8OCVqTWwnEU,643
+speaksy/service.py,sha256=EwQs3yB3Ys-WwvP0UI2K_U5_zJqJCJLkK29_MTTcVTE,5449
+speaksy/setup_wizard.py,sha256=-Glu74R-ZKL097Ji8vOmEDC7salaSk9kueONxWs0t4c,7033
+speaksy-0.1.0.dist-info/METADATA,sha256=JwjfdFK_CSimqUGGZC0VwJxW1lvWmrCENw9B56cFCBw,6926
+speaksy-0.1.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+speaksy-0.1.0.dist-info/entry_points.txt,sha256=LFch1KPmgD4hHNVXY_DSJ24fPnB8GaVKF4aKUrqDjzs,45
+speaksy-0.1.0.dist-info/licenses/LICENSE,sha256=KgmDIQPh17s8aGNha9ebeUXZHi533ew6VyCLcY7IJE4,1066
+speaksy-0.1.0.dist-info/RECORD,,

speaksy-0.1.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.28.0
+Root-Is-Purelib: true
+Tag: py3-none-any

speaksy-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+speaksy = speaksy.cli:main