Browse The Skill Store

Free speech-to-text and SRT subtitle generation using OpenAI Whisper on Cloudflare Workers AI.

SoundTag AI: Automatically describe and batch-rename audio files based on their actual sound using local ML or Gemini AI.

Turn low-quality voice recordings into professional studio-grade audio using NVIDIA Maxine AI.

Automate Google NotebookLM: create notebooks, add sources, and generate AI audio/podcasts via Python or CLI.

Fast, asynchronous Whisper transcription for audio and video files with SRT subtitle export.

Generate professional-grade 48kHz music clips and full songs for free using Google's Lyria 3 models.

Convert text to lifelike, expressive speech using the ElevenLabs Multilingual v2 API.

Generate custom AI sound effects and Foley directly from text descriptions using ElevenLabs.

Synced shared screen for a Three.js multiplayer room: a SharedScreen client (YouTube on a canvas texture, clock-based playback tracking, 3D positional audio), a screenHandlers Colyseus pattern (setUrl, play, pause, seek, volume, stop, controlled-by tracking), an optional yt-dlp plus ffmpeg proxy, and an optional Puppeteer BrowserManager. Field-verified from nex-vr-room.

Clone any voice or generate professional text-to-speech using NVIDIA's zero-shot Magpie NIM technology.

Professional AI-powered audio denoising using NVIDIA Maxine to remove keyboard clicks, fans, and background chatter.