@hasna/skills 0.0.2

package/skills/skill-audio/QUICKSTART.md

@@ -0,0 +1,158 @@
+# Quick Start Guide
+
+Get started with audio generation in under 5 minutes!
+
+## 1. Set Up API Keys
+
+Copy the example environment file:
+```bash
+cp .env.example .env
+```
+
+Edit `.env` and add at least one API key:
+```bash
+# Choose one or more providers:
+OPENAI_API_KEY=sk-...              # Easiest to get started
+ELEVENLABS_API_KEY=...             # Best voice quality
+GOOGLE_API_KEY=...                 # Most language options
+```
+
+## 2. Test the Installation
+
+List available voices (no API key needed for OpenAI):
+```bash
+bun run src/index.ts voices --provider openai
+```
+
+## 3. Generate Your First Audio
+
+### Option A: OpenAI TTS (Recommended for beginners)
+```bash
+bun run src/index.ts generate \
+  --provider openai \
+  --text "Hello, this is my first audio generation!" \
+  --voice nova \
+  --output ./test.mp3
+```
+
+### Option B: ElevenLabs (Best quality)
+```bash
+bun run src/index.ts generate \
+  --provider elevenlabs \
+  --text "Hello, this is my first audio generation!" \
+  --voice rachel \
+  --output ./test.mp3
+```
+
+### Option C: Google TTS (Most languages)
+```bash
+bun run src/index.ts generate \
+  --provider google \
+  --text "Hello, this is my first audio generation!" \
+  --language en-US \
+  --output ./test.mp3
+```
+
+## 4. Play Your Audio
+
+On macOS:
+```bash
+afplay test.mp3
+```
+
+On Linux:
+```bash
+mpg123 test.mp3
+# or
+ffplay test.mp3
+```
+
+On Windows:
+```bash
+start test.mp3
+```
+
+## Next Steps
+
+- Explore different voices: `bun run src/index.ts voices --provider <name>`
+- Try different speeds: Add `--speed 1.5` for faster speech
+- Use different models: Add `--model tts-1-hd` for higher quality (OpenAI)
+- See all options: `bun run src/index.ts help`
+
+## Common Use Cases
+
+### Podcast Intro
+```bash
+bun run src/index.ts generate \
+  --provider elevenlabs \
+  --text "Welcome to the Tech Talk podcast, where we discuss the latest in technology and innovation" \
+  --voice adam \
+  --output ./podcast_intro.mp3
+```
+
+### Multilingual Content (Google)
+```bash
+bun run src/index.ts generate \
+  --provider google \
+  --text "Bonjour, comment allez-vous?" \
+  --language fr-FR \
+  --output ./french_greeting.mp3
+```
+
+### Audiobook Narration
+```bash
+bun run src/index.ts generate \
+  --provider openai \
+  --text "Chapter 1: The Beginning. It was a dark and stormy night..." \
+  --voice fable \
+  --model tts-1-hd \
+  --speed 0.9 \
+  --output ./chapter1.mp3
+```
+
+## Troubleshooting
+
+**Error: API key not found**
+- Make sure you've created a `.env` file
+- Check that your API key is correctly formatted
+- Verify the environment variable name matches the provider
+
+**Error: Voice not found**
+- List available voices first: `bun run src/index.ts voices --provider <name>`
+- Use the exact voice ID from the list
+
+**Poor audio quality**
+- Use `--model tts-1-hd` with OpenAI for higher quality
+- Try `eleven_multilingual_v2` model with ElevenLabs
+- Adjust `--speed` for more natural speech
+
+## Getting API Keys
+
+### OpenAI (Easiest, $0.015/1K chars)
+1. Visit https://platform.openai.com/api-keys
+2. Sign up or log in
+3. Click "Create new secret key"
+4. Copy and paste into `.env`
+
+### ElevenLabs (Best quality, free tier available)
+1. Visit https://elevenlabs.io/
+2. Sign up for a free account (10K chars/month)
+3. Go to Profile > API Keys
+4. Copy and paste into `.env`
+
+### Google Cloud (Most languages, complex setup)
+1. Visit https://console.cloud.google.com/
+2. Create a project
+3. Enable Text-to-Speech API
+4. Create credentials (API key)
+5. Copy and paste into `.env`
+
+## Tips for Best Results
+
+1. **Keep sentences natural**: Punctuation affects pacing and intonation
+2. **Use appropriate voices**: Match voice to content (professional, casual, storytelling)
+3. **Adjust speed**: 0.9-1.0 for audiobooks, 1.0-1.2 for casual content
+4. **Test different providers**: Each has unique strengths
+5. **Mind your costs**: Monitor usage, especially with paid tiers
+
+Enjoy generating audio!

package/skills/skill-audio/README.md

@@ -0,0 +1,256 @@
+# Audio Generation Skill
+
+A comprehensive Claude Code skill for generating high-quality audio using AI-powered text-to-speech APIs.
+
+## Features
+
+- Multiple TTS providers: ElevenLabs, OpenAI TTS, and Google Text-to-Speech
+- Simple, elegant CLI interface
+- Voice selection and listing
+- Multiple languages support
+- Customizable speech speed
+- Clean TypeScript implementation with full type safety
+- Native fetch API (no external HTTP libraries needed)
+
+## Supported Providers
+
+### ElevenLabs
+- Natural voice synthesis with voice cloning capabilities
+- Models: `eleven_multilingual_v2`, `eleven_flash_v2_5`, `eleven_v3`
+- Multiple languages and voice options
+- Professional-quality audio output
+
+### OpenAI TTS
+- High-quality text-to-speech
+- Models: `tts-1` (fast), `tts-1-hd` (high quality)
+- Voices: alloy, echo, fable, onyx, nova, shimmer
+- Speed control (0.25x to 4.0x)
+
+### Google Text-to-Speech
+- Cloud-based TTS service
+- Wide range of voices and languages
+- Natural-sounding speech synthesis
+- Configurable pitch and speaking rate
+
+## Installation
+
+1. Install Bun (if not already installed):
+```bash
+curl -fsSL https://bun.sh/install | bash
+```
+
+2. Clone and navigate to the skill directory:
+```bash
+git clone https://github.com/hasnaxyz/skill-audio.git
+cd skill-audio
+```
+
+3. Install dependencies:
+```bash
+bun install
+```
+
+4. Set up environment variables:
+```bash
+cp .env.example .env
+# Edit .env and add your API keys
+```
+
+## Configuration
+
+Create a `.env` file with your API keys:
+
+```bash
+ELEVENLABS_API_KEY=your_elevenlabs_api_key_here
+OPENAI_API_KEY=your_openai_api_key_here
+GOOGLE_API_KEY=your_google_api_key_here
+```
+
+### Getting API Keys
+
+- **ElevenLabs**: https://elevenlabs.io/
+- **OpenAI**: https://platform.openai.com/api-keys
+- **Google Cloud**: https://console.cloud.google.com/apis/credentials
+
+## Usage
+
+### Generate Audio
+
+#### ElevenLabs
+```bash
+bun run src/index.ts generate \
+  --provider elevenlabs \
+  --text "Hello world, this is a test of ElevenLabs text to speech" \
+  --voice rachel \
+  --model eleven_multilingual_v2 \
+  --output ./output.mp3
+```
+
+#### OpenAI TTS
+```bash
+bun run src/index.ts generate \
+  --provider openai \
+  --text "Hello world, this is a test of OpenAI text to speech" \
+  --voice nova \
+  --model tts-1-hd \
+  --speed 1.0 \
+  --output ./output.mp3
+```
+
+#### Google Text-to-Speech
+```bash
+bun run src/index.ts generate \
+  --provider google \
+  --text "Hello world, this is a test of Google text to speech" \
+  --language en-US \
+  --speed 1.0 \
+  --output ./output.mp3
+```
+
+### List Available Voices
+
+```bash
+# ElevenLabs voices
+bun run src/index.ts voices --provider elevenlabs
+
+# OpenAI voices
+bun run src/index.ts voices --provider openai
+
+# Google voices
+bun run src/index.ts voices --provider google
+```
+
+### Show Help
+
+```bash
+bun run src/index.ts help
+```
+
+## CLI Options
+
+### Generate Command
+
+| Option | Description | Required | Default |
+|--------|-------------|----------|---------|
+| `--provider` | Provider to use (elevenlabs, openai, google) | Yes | - |
+| `--text` | Text to convert to speech | Yes | - |
+| `--output` | Output file path (e.g., ./output.mp3) | Yes | - |
+| `--voice` | Voice to use (provider-specific) | No | Provider default |
+| `--model` | Model to use (provider-specific) | No | Provider default |
+| `--language` | Language code (Google TTS, e.g., en-US) | No | en-US |
+| `--speed` | Speaking speed (0.25-4.0) | No | 1.0 |
+
+### Voices Command
+
+| Option | Description | Required |
+|--------|-------------|----------|
+| `--provider` | Provider to list voices from | Yes |
+
+## Examples
+
+### Quick Test with Different Providers
+
+```bash
+# ElevenLabs - Natural voice
+bun run src/index.ts generate \
+  --provider elevenlabs \
+  --text "The quick brown fox jumps over the lazy dog" \
+  --voice rachel \
+  --output ./elevenlabs_test.mp3
+
+# OpenAI - High quality
+bun run src/index.ts generate \
+  --provider openai \
+  --text "The quick brown fox jumps over the lazy dog" \
+  --voice nova \
+  --model tts-1-hd \
+  --output ./openai_test.mp3
+
+# Google - Multilingual
+bun run src/index.ts generate \
+  --provider google \
+  --text "The quick brown fox jumps over the lazy dog" \
+  --language en-US \
+  --output ./google_test.mp3
+```
+
+### Generate with Custom Speed
+
+```bash
+# Slower speech
+bun run src/index.ts generate \
+  --provider openai \
+  --text "This is spoken slowly" \
+  --voice onyx \
+  --speed 0.75 \
+  --output ./slow.mp3
+
+# Faster speech
+bun run src/index.ts generate \
+  --provider openai \
+  --text "This is spoken quickly" \
+  --voice nova \
+  --speed 1.5 \
+  --output ./fast.mp3
+```
+
+## Project Structure
+
+```
+skill-audio/
+├── SKILL.md              # Skill metadata and description
+├── README.md             # This file
+├── package.json          # Bun project configuration
+├── tsconfig.json         # TypeScript configuration
+├── .env.example          # Example environment variables
+├── src/
+│   ├── index.ts          # CLI entry point
+│   ├── types.ts          # TypeScript type definitions
+│   └── providers/
+│       ├── elevenlabs.ts # ElevenLabs provider
+│       ├── openai.ts     # OpenAI TTS provider
+│       └── google.ts     # Google TTS provider
+```
+
+## Development
+
+### Run in Development Mode
+
+```bash
+bun run dev
+```
+
+### Type Checking
+
+```bash
+bun run tsc --noEmit
+```
+
+## Error Handling
+
+The CLI provides clear error messages for common issues:
+
+- Missing API keys
+- Invalid providers
+- Voice not found
+- API errors
+- File write errors
+
+## Troubleshooting
+
+### "API key not found" error
+Make sure you've created a `.env` file with the appropriate API key for the provider you're using.
+
+### "Voice not found" error
+Use the `voices` command to list available voices for your chosen provider.
+
+### API errors
+Check that your API keys are valid and have sufficient credits/quota.
+
+## License
+
+MIT
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit issues or pull requests.

package/skills/skill-audio/SKILL.md

@@ -0,0 +1,60 @@
+---
+name: Audio Generation
+description: Generate high-quality audio using ElevenLabs, OpenAI TTS, and Google Text-to-Speech APIs. Support for text-to-speech, voice cloning, multiple languages, and various voice options.
+---
+
+# Audio Generation Skill
+
+This skill provides a unified interface for generating audio from text using multiple AI-powered text-to-speech providers.
+
+## Supported Providers
+
+### ElevenLabs
+- Text-to-speech with natural voice synthesis
+- Voice cloning capabilities
+- Multiple languages support
+- Models: eleven_multilingual_v2, eleven_flash_v2_5, eleven_v3
+
+### OpenAI TTS
+- High-quality text-to-speech
+- Models: tts-1 (fast), tts-1-hd (high quality)
+- Voices: alloy, echo, fable, onyx, nova, shimmer
+
+### Google Text-to-Speech
+- Cloud-based TTS service
+- Wide range of voices and languages
+- Natural-sounding speech synthesis
+
+## Usage
+
+### Generate Audio
+```bash
+bun run src/index.ts generate --provider elevenlabs --text "Hello world" --voice rachel --output ./output.mp3
+bun run src/index.ts generate --provider openai --text "Hello world" --voice nova --output ./output.mp3
+bun run src/index.ts generate --provider google --text "Hello world" --output ./output.mp3
+```
+
+### List Available Voices
+```bash
+bun run src/index.ts voices --provider elevenlabs
+bun run src/index.ts voices --provider openai
+bun run src/index.ts voices --provider google
+```
+
+## Configuration
+
+Set up API keys as environment variables:
+```bash
+export ELEVENLABS_API_KEY=your_elevenlabs_key
+export OPENAI_API_KEY=your_openai_key
+export GOOGLE_API_KEY=your_google_key
+```
+
+## Features
+
+- Simple, elegant CLI interface
+- Support for multiple TTS providers
+- Voice listing and selection
+- Customizable output formats
+- Clean TypeScript implementation
+- Native fetch API (no external HTTP libraries)

package/skills/skill-audio/install.sh

@@ -0,0 +1,112 @@
+#!/usr/bin/env bash
+
+# Install script for skills
+# Installs the skill either globally for Claude Code or locally in a project
+
+set -e
+
+SKILL_NAME="$(basename "$(pwd)")"
+SKILL_PATH="$(pwd)"
+
+echo "📦 Installing $SKILL_NAME..."
+echo ""
+
+# Check if Claude Code is installed
+if ! command -v claude &> /dev/null; then
+    echo "⚠️  Claude Code not found in PATH"
+    echo "   Please install Claude Code first: https://claude.com/claude-code"
+    exit 1
+fi
+
+# Check if we're in a git repository
+if git rev-parse --git-dir > /dev/null 2>&1; then
+    IN_REPO=true
+    REPO_ROOT="$(git rev-parse --show-toplevel)"
+    echo "📁 Detected git repository: $REPO_ROOT"
+else
+    IN_REPO=false
+    echo "📁 Not in a git repository"
+fi
+
+# Ask installation type
+echo ""
+echo "Where would you like to install this skill?"
+if [ "$IN_REPO" = true ]; then
+    echo "  1) Locally (this repository only)"
+    echo "  2) Globally (all Claude Code sessions)"
+    read -p "Choose [1/2]: " choice
+else
+    echo "  Installing globally (not in a git repository)"
+    choice=2
+fi
+
+# Install function
+install_skill() {
+    local config_dir=$1
+    local config_file="$config_dir/claude_mcp_config.json"
+
+    # Create config directory if it doesn't exist
+    mkdir -p "$config_dir"
+
+    # Create or update config file
+    if [ ! -f "$config_file" ]; then
+        echo "{" > "$config_file"
+        echo '  "mcpServers": {}' >> "$config_file"
+        echo "}" >> "$config_file"
+    fi
+
+    # Add skill to config using bun
+    bun -e "
+    const fs = require('fs');
+    const config = JSON.parse(fs.readFileSync('$config_file', 'utf8'));
+
+    if (!config.mcpServers) config.mcpServers = {};
+
+    config.mcpServers['$SKILL_NAME'] = {
+      command: 'bun',
+      args: ['run', '$SKILL_PATH/src/index.ts'],
+      env: {
+        SKILL_API_KEY: process.env.SKILL_API_KEY || '',
+        ANTHROPIC_API_KEY: process.env.ANTHROPIC_API_KEY || '',
+        OPENAI_API_KEY: process.env.OPENAI_API_KEY || '',
+        ELEVENLABS_API_KEY: process.env.ELEVENLABS_API_KEY || '',
+        GEMINI_API_KEY: process.env.GEMINI_API_KEY || '',
+        XAI_API_KEY: process.env.XAI_API_KEY || '',
+        GOOGLE_API_KEY: process.env.GOOGLE_API_KEY || '',
+        GOOGLE_PROJECT_ID: process.env.GOOGLE_PROJECT_ID || '',
+        BROWSER_USE_API_KEY: process.env.BROWSER_USE_API_KEY || '',
+        RUNWAY_API_KEY: process.env.RUNWAY_API_KEY || ''
+      }
+    };
+
+    fs.writeFileSync('$config_file', JSON.stringify(config, null, 2));
+    "
+
+    echo "✅ Installed $SKILL_NAME to $config_file"
+}
+
+# Install based on choice
+if [ "$choice" = "1" ]; then
+    # Local installation
+    install_skill "$REPO_ROOT/.claude"
+    echo ""
+    echo "🎉 $SKILL_NAME installed locally!"
+    echo "   Config: $REPO_ROOT/.claude/claude_mcp_config.json"
+elif [ "$choice" = "2" ]; then
+    # Global installation
+    install_skill "$HOME/.config/claude-code"
+    echo ""
+    echo "🎉 $SKILL_NAME installed globally!"
+    echo "   Config: $HOME/.config/claude-code/claude_mcp_config.json"
+else
+    echo "❌ Invalid choice"
+    exit 1
+fi
+
+echo ""
+echo "📝 Next steps:"
+echo "   1. Restart Claude Code"
+echo "   2. The skill will be available as: $SKILL_NAME"
+echo ""
+echo "   Usage: Claude Code will automatically detect and use this skill"
+echo "          based on your prompts and task context."

package/skills/skill-audio/package.json

@@ -0,0 +1,35 @@
+{
+  "name": "skill-audio",
+  "version": "1.0.0",
+  "description": "Audio generation skill for Claude Code using ElevenLabs, OpenAI TTS, and Google Text-to-Speech",
+  "type": "module",
+  "main": "src/index.ts",
+  "bin": {
+    "skill-audio": "src/index.ts"
+  },
+  "scripts": {
+    "start": "bun run src/index.ts",
+    "dev": "bun run --watch src/index.ts"
+  },
+  "keywords": [
+    "audio",
+    "tts",
+    "text-to-speech",
+    "elevenlabs",
+    "openai",
+    "google",
+    "ai"
+  ],
+  "author": "",
+  "license": "MIT",
+  "devDependencies": {
+    "@types/bun": "latest"
+  },
+  "peerDependencies": {
+    "typescript": "^5.0.0"
+  },
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/hasnaxyz/skill-audio.git"
+  }
+}

package/skills/skill-audio/src/auth.ts

@@ -0,0 +1,49 @@
+/**
+ * Skill Authentication Check
+ * Add this to the top of any skill's main function
+ */
+
+export function checkSkillAuth(): void {
+  const SKILL_API_KEY = process.env.SKILL_API_KEY;
+  
+  // Check if SKILL_API_KEY is set
+  if (!SKILL_API_KEY) {
+    console.error('❌ Error: SKILL_API_KEY environment variable not set');
+    console.error('');
+    console.error('To use this skill, you must set your SKILL_API_KEY:');
+    console.error('');
+    console.error('  export SKILL_API_KEY=your-api-key-here');
+    console.error('');
+    console.error('Contact your administrator to get your API key.');
+    process.exit(1);
+  }
+
+  // Validate key format
+  if (!SKILL_API_KEY.startsWith('sk-skill-')) {
+    console.error('❌ Error: Invalid SKILL_API_KEY format');
+    console.error('Expected format: sk-skill-xxxxxxxxxxxx');
+    process.exit(1);
+  }
+
+  // Key is valid - skill can proceed
+}
+
+/**
+ * Check if running remotely (via SSH or network)
+ */
+export function isRemoteExecution(): boolean {
+  return !!(
+    process.env.SSH_CONNECTION ||
+    process.env.SSH_CLIENT ||
+    process.env.SSH_TTY
+  );
+}
+
+/**
+ * Require auth only if remote execution
+ */
+export function requireAuthIfRemote(): void {
+  if (isRemoteExecution()) {
+    checkSkillAuth();
+  }
+}