FunASR
Verified · 6 days agoTranscribe local audio with FunASR and SenseVoice using private, on-device inference.
Hand any social video to your AI agent — frames + transcript bundled. MCP server for watch-cli.
claude mcp add watch-cli -- npx -y @sonpiaz/[email protected]
A media-ingestion server that packages video frames and transcripts so an agent can analyze social video content. It is for workflows like summarization, monitoring, clipping, or downstream reasoning over video, rather than general media management. The utility is easy to understand, but it is still a specialized wrapper around one ingestion path, so its long-term value depends on how actively that pipeline is maintained.
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