FunASR
Verified · 6 days agoTranscribe local audio with FunASR and SenseVoice using private, on-device inference.
Podcast transcripts as clean Markdown with real speaker names — via the Spoken API.
claude mcp add spoken -- npx -y [email protected]
A media-processing server that turns podcast transcripts into clean Markdown with named speakers via the Spoken API. It is for teams working with podcast research, republishing, summarization, or editorial pipelines. The value proposition is concrete, but dependence on a separate API and limited visible adoption make it more of a focused integration than a proven general-purpose tool.
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