FunASR
Verified · 6 days agoTranscribe local audio with FunASR and SenseVoice using private, on-device inference.
Source-first AI knowledge control tower MCP server for YouTube, Bilibili, RSSHub, and RSS.
claude mcp add sourceharbor-mcp -- uvx sourceharbor
A YouTube/Bilibili/RSS ingestion and digest system whose PyPI package genuinely ships a substantial MCP server with a large tool schema and extensive tests — plus the full FastAPI backend it bridges to. The catch: the project has since been rebranded to 'BrewMe' and the linked repo no longer mentions SourceHarbor at all, so every documentation link from the listing lands on a different-looking product and the advertised self-hosted API has no current docs. The code is real, but you'd be adopting an orphaned snapshot of a pivoted project.
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