FunASR
Verified · 27 days agoTranscribe local audio with FunASR and SenseVoice using private, on-device inference.
Pay-per-call AI: 59 generative models (image, video, music, speech). No signup, no API key.
Flagged: ~1,277 weekly downloads three weeks after first publish, against zero stars, zero watchers, zero forks, and an anonymous Gliana-Labs org (created September 2025, zero followers, gmail maintainer) — the no-community-but-four-figure-downloads signature of download inflation. The server itself is real, working TypeScript: free list_models/get_price/get_schema discovery plus a paid generate tool that runs image/video/music/speech models via api.glianalabs.com and settles each call as a USDC micropayment over x402/MPP on Base, Tempo, or Solana. The catch is the trust model: you paste a raw EVM or Solana private key into your MCP client config so the server can sign payments to an unaudited, unidentifiable vendor's gateway (the README does at least warn you to use a dedicated low-balance wallet), and the model count doesn't match the registry blurb (59 claimed there, 70+ in the README). The no-signup pay-per-call idea is genuinely convenient, but inflated popularity plus wallet-key custody from an anonymous operator is a combination to avoid until the project earns a track record.
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.
Trim, convert, resize, compress, and remix audio and video.
Screen recording, meeting notes, and voice dictation - all with AI
Let any LLM watch a video locally — and search everything it has ever watched.