Systemprompt Multimodal
Enables voice-controlled AI workflows using Google Gemini and the Model Control Protocol.
소개
Systemprompt Multimodal is a modern voice-controlled AI interface that revolutionizes interactions with AI systems by combining Google Gemini's multimodal capabilities with the Model Control Protocol (MCP). It supports both custom MCP servers and Systemprompt MCP servers, which can be easily installed with a Systemprompt API key. This Vite + TypeScript application allows users to control AI workflows through natural speech and process multimodal inputs, making it ideal for developers building voice-controlled AI applications.
주요 기능
- Extensible tool system through MCP
- Real-time voice synthesis for instant audio responses
- Modern tech stack: Vite, React, TypeScript, and NextUI
- Natural voice control for AI workflows
- 148 GitHub stars
- Multimodal understanding of text, voice, and visual inputs
사용 사례
- Building voice-controlled AI applications
- Implementing multimodal AI interactions
- Creating complex AI workflows orchestrated by voice commands