Overview
Title
Speech.sh - A powerful command-line utility for text-to-speech conversion using OpenAI's API.
How to Use
- Installation: Clone the repository, make scripts executable, and ensure dependencies (curl, jq, ffmpeg/mplayer) are installed.
- Basic Usage: Run
./speech.sh --text "Your text" for default TTS conversion.
- Advanced Options: Customize voice, speed, output file, API key, and audio player.
- MCP Integration: Use
mcp.sh for AI assistant compatibility.
Key Features
- Multiple Voices: Choose from six voice options (e.g., nova, shimmer).
- Adjustable Speed: Control speech rate (0.25x to 4.0x).
- API Key Flexibility: Supports command-line, environment variable, or file-based API key input.
- Auto-Caching: Avoids duplicate API calls by caching audio files.
- Retry Mechanism: Handles network issues with exponential backoff.
- Audio Player Support: Works with ffmpeg or mplayer.
- MCP Compatibility: Integrates with AI assistants via Model Context Protocol.
Use Cases
- Quick TTS Conversion: Convert text to speech for accessibility or convenience.
- AI Assistant Integration: Enable voice output for MCP-compatible AI tools.
- Batch Processing: Generate multiple audio files with customizable settings.
- Development Testing: Test voice interfaces or audio applications.
