FunASR
Verified · 9 days agoTranscribe local audio with FunASR and SenseVoice using private, on-device inference.
Magic Hour hosted MCP: AI video (Sora 2, Veo 3.1, Kling 3.0), images, audio, face swap, lip sync.
claude mcp add --transport http magic-hour https://mcp.magichour.ai/
This is a hosted media-generation server covering video, image, audio, face swap, and lip-sync workflows through a remote API. It is for users who want one MCP surface over multiple generative media capabilities rather than stitching together separate tools. The breadth is notable, but as a remote-only service with no public maintenance signal here, its quality depends heavily on the operator and underlying service stability.
Transcribe local audio with FunASR and SenseVoice using private, on-device inference.
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Turn long videos into viral vertical shorts and publish them to TikTok, Instagram and YouTube.
Let any LLM watch a video locally — and search everything it has ever watched.
The Figma MCP server brings Figma design context directly into your AI workflow.
Natural voice conversations for AI assistants - STT/TTS via MCP