关于
The Text to Speech (TTS) server converts text into magnificent audible experiences through a computer's speakers, powered by OpenAI's advanced TTS models. It empowers AI agents with the ability to speak, acting as a tireless personal narrator. This sophisticated tool allows for the configuration of various voices and the provision of optional delivery instructions to guide character, pacing, tone, and emotion, significantly enhancing interactive agent capabilities.
主要功能
- Empowers agents with the ability to voice any given text
- Supports optional instructions to guide delivery, character, pacing, tone, and emotion
- Offers blocking and non-blocking modes for audio playback control
- Implements queue-based audio playback for sequential message delivery
- 0 GitHub stars
- Configurable OpenAI TTS model via environment variables
使用案例
- Customize spoken output with specific voices, tones, and emotional instructions for diverse applications
- Enable AI agents to vocalize text responses and communicate audibly
- Integrate advanced text-to-speech functionality into MCP-compatible AI environments like Cursor
Advertisement