FunASR
Verified · todayTranscribe local audio with FunASR and SenseVoice using private, on-device inference.
being-human
Verified · todayLearns your writing voice from your own prompt history, then makes the model write like that.
Install
claude mcp add being-human -- uvx being-human
Our take
A writing-style server that tries to learn a user's voice from prior prompt history and steer model outputs toward that style. It is mainly for individual users or creators who care about tone consistency more than broad workflow automation. The concept is understandable, but it raises privacy and data-handling questions, and the lack of visible adoption signals suggests caution until maintenance and safeguards are clearer.
Verification record
- today
- 0
- today
- no
- MIT
- 2026-08-13
More in media
browse all →Figma-Context-MCP
Verified · 2 days agoGive your coding agent access to your Figma data. Implement designs in any framework in one-shot.
openshorts
Verified · 10 days agoTurn long videos into viral vertical shorts and publish them to TikTok, Instagram and YouTube.
claude-real-video
Verified · 10 days agoLet any LLM watch a video locally — and search everything it has ever watched.
Figma MCP Server
Verified · 5 days agoThe Figma MCP server brings Figma design context directly into your AI workflow.
voicemode
Verified · 2 days agoNatural voice conversations for AI assistants - STT/TTS via MCP