FunASR
Verified · yesterdayTranscribe local audio with FunASR and SenseVoice using private, on-device inference.
Run multi-step AI pipelines for video, image, audio and text: upload media, run, poll results.
claude mcp add --transport http mcp https://mcp.pipe2.ai/mcp
A remote-only orchestration server for running multi-step AI media pipelines across video, image, audio, and text, including upload, execution, and result polling. It is for developers who need a unified MCP surface over asynchronous generation workflows rather than model-by-model integration. The capability set is practical, but platform dependence and limited public maintenance signals make it worth treating as an integration layer that needs real-world testing.
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.
Screen recording, meeting notes, and voice dictation - all with AI
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.