ChatTTS: ChatTTS is a generative speech model specifically designed for daily dialogue scenarios, such as LLM assistants. It offers natural and expressive speech with fine-grained control over prosodic features like laughter, pauses, and interjections.; mcp-youtube-transcript: This MCP server provides tools to retrieve YouTube video transcripts (plain text or with timestamps) and video metadata. It supports response pagination for long content and proxy configuration for restricted environments. It can be used with Claude Desktop, LM Studio, Goose, and other MCP clients via uvx or Docker.
Providing voice output for LLM assistants in dialogue scenarios
Language learning by reading video transcripts