About
Say bridges the gap between digital text and audible communication by leveraging macOS's native text-to-speech capabilities. Through a simple MCP server interface, it allows users to convert text into spoken words, with options for voice selection, rate adjustment, volume control, and even advanced features like dynamic rate changes and emphasis. The tool integrates seamlessly with other MCP servers, enabling use cases such as reading search results aloud, narrating YouTube transcripts, or providing background audio while performing other tasks.
Key Features
- 0 GitHub stars
- Text-to-speech conversion using macOS 'say' command
- Supports plain text, punctuation, newlines, and custom silence/rate/volume tags
- MCP Server integration for modular usage
- Background speech mode for concurrent operations
- Voice selection and customization (rate, volume)
Use Cases
- Narrating YouTube transcripts
- Reading search results aloud
- Providing background audio during tasks
