关于
Voice Mode provides natural, human-like voice interactions for AI assistants, primarily integrating with LLMs via the Model Context Protocol (MCP). It supports real-time speech-to-text (STT) and text-to-speech (TTS) functionalities, allowing users to engage in dynamic conversations with their AI, whether through a local microphone or a LiveKit-based communication channel. It offers flexible deployment by being OpenAI API-compatible, supporting both cloud and local speech services.
主要功能
- Supports real-time voice conversations with Claude and other LLMs.
- Offers multiple transports including local microphone and LiveKit room-based communication.
- OpenAI-compatible, allowing use with any STT/TTS service (local or cloud).
- Provides low-latency voice interactions with automatic transport selection.
- Seamlessly integrates with Claude Desktop and other MCP clients.
- 18 GitHub stars
使用案例
- Engaging in natural, real-time voice conversations with AI assistants.
- Integrating custom or local speech-to-text and text-to-speech services with LLMs.
- Developing AI applications that require human-like voice interaction capabilities.