关于
Voice empowers users to engage in natural, real-time voice conversations with large language models, including Claude. It functions as an MCP server, facilitating seamless speech-to-text and text-to-speech interactions using OpenAI-compatible services. With support for both local microphone input and LiveKit room-based communication, it offers flexible, low-latency voice capabilities for enhanced LLM interactions, requiring only an OpenAI API key.
主要功能
- Compatible with OpenAI and other STT/TTS services
- Provides real-time, low-latency voice interactions
- Seamlessly integrates with Claude Desktop and other MCP clients
- Offers multiple communication transports (local microphone, LiveKit)
- 3 GitHub stars
- Supports voice conversations with LLMs (e.g., Claude)
使用案例
- Generate spoken responses from LLM-generated text
- Conduct interactive voice conversations with LLMs
- Transcribe spoken input to text for LLM processing