Provides an MCP server to integrate Yandex SpeechKit's speech recognition and synthesis API for converting audio to text and text to audio.
Integrate Yandex SpeechKit's powerful speech recognition and synthesis directly into your applications as an MCP server. This tool is a key component within the Russian API MCP series, offering seamless conversion of Base64 encoded audio to text and generating natural-sounding speech from text, making advanced voice functionalities accessible for various AI-driven use cases.
주요 기능
010 GitHub stars
02Synthesize text into Base64 encoded audio using various voices
03Requires Yandex API Key and Folder ID for authentication
04Recognize speech from Base64 encoded audio files into text
05Easy installation and configuration for Claude Desktop, Claude Code, and VS Code/Cursor
사용 사례
01Generating custom audio responses from AI models or applications
02Adding voice interaction capabilities to development environments and tools
03Transcribing spoken audio from recordings into text format
