FunASR
Verified · 11 days agoTranscribe local audio with FunASR and SenseVoice using private, on-device inference.
Compose and render video from one JSON template. Deterministic, runs locally, no generative model.
claude mcp add video -- npx -y @leclap/[email protected]
LeClap appears to be a local, deterministic video composition server driven by a JSON template rather than generative media. It is for developers who want reproducible programmatic rendering, likely for templated clips, explainers, or automated media pipelines. The concept is clear and usefully constrained, but the low star count points to an early-stage or niche project rather than a widely proven standard.
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