FunASR
Verified · 19 days agoTranscribe local audio with FunASR and SenseVoice using private, on-device inference.
Any video URL to LLM-ready transcript. ASR built in, no captions needed. TikTok, X, TED and more.
claude mcp add --transport http video-transcript https://api.payload.cool/mcp/
This server converts arbitrary video URLs into transcripts with built-in ASR, including sources beyond YouTube such as TikTok, X, and TED. It is useful for research, media ingestion, and content-processing pipelines that need text without relying on platform captions. The value proposition is clear, but broad source support and remote-only delivery mean quality will likely vary by input source and should be validated on real workloads.
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