FunASR
Verified · 11 days agoTranscribe local audio with FunASR and SenseVoice using private, on-device inference.
Let any LLM actually watch a video: scene-aware keyframes plus a timestamped transcript, local.
claude mcp add claude-real-video -- uvx claude-real-video
Provides local video understanding by extracting scene-aware keyframes and pairing them with a timestamped transcript so an LLM can work over video content. It is for users who need practical video analysis without sending footage to a hosted service. The package availability and relatively strong star count are good signals, though this is still a specialized tool whose quality will matter most on real-world accuracy and performance across different video types.
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.
The Figma MCP server brings Figma design context directly into your AI workflow.
Natural voice conversations for AI assistants - STT/TTS via MCP
Extract brand assets (logos, colors, backdrop images, brand name) from any website URL