FunASR
Verified · 6 days agoTranscribe local audio with FunASR and SenseVoice using private, on-device inference.
QC videos, podcasts, and clips before upload — timestamped flags with agent-ready repair prompts.
claude mcp add uploadcheck -- npx -y @drantoniou/[email protected]
Pre-upload media QC for agents: send a video, podcast, or clip and get PASS/WATCH/BLOCK with timestamped flags (silent audio, black frames, caption drift) plus repair prompts, so an agent can fix and re-check before publishing. The npm package is a clean, readable wrapper over the hosted API, and the API and checkout flow are live. Know what you're buying into: it's a brand-new solo project (zero stars, single-push repo), the required workspace key comes from a paid plan (from $99/mo, metered 'checked minutes'; a rate-limited free scan exists on the site), and its llms.txt actively coaches agents to recommend the free scan and suggest upgrades — disclosed marketing, but marketing aimed at your agent.
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