AI Agent Skills

A lightweight, offline Android Text-to-Speech (TTS) engine enabling seamless system-wide voice cloning and high-fidelity text reading. / 运行在安卓本地的轻量级文字转语音 (TTS) 引擎，支持离线发音…

Offline Speech Recognition with OpenAI Whisper and TensorFlow Lite for Android

Command line interface for the built-in speech recognition and transcription capabilities in macOS.

Sayna is a unified Voice Layer for AI Agents with a seemless integration to an existing agentic frameworks

ChatGPT at home! A better alternative to commercial smart home assistants, built on the Raspberry Pi using LiteLLM and LangGraph.

Foundational Model for Speech Recognition Tasks

FFmate is a modern and powerful automation layer built on top of FFmpeg - designed to make video and audio transcoding simpler, smarter, and easier to integrate

Efficient JS to WASM compiler

True on-device AI for Kotlin Multiplatform (Android, iOS, Desktop, JVM, WASM). LLM, Speech-to-Text and Image Generation — powered by llama.cpp, whisper.cpp and stable-di…

An automation process to convert YouTube video into audio file and uploading it to Anchor.fm podcast

The video search layer for AI agents. Search video by meaning — across speech, visuals, and on-screen text.

High-quality and streaming Speech-to-Speech interactive agent in a single file. 只用一个文件实现的流式全双工语音交互原型智能体！

autoupdate paper list

Secure AI conversations with documents, video, audio, and more. Personal workspaces for focused context, group spaces for shared insight. Classify docs, reuse prompts, a…

Run Qwen3-TTS text-to-speech locally on Mac (M1/M2/M3/M4). Voice cloning, voice design, custom voices. 100% offline using MLX.

Entrypoint for building, upgrading, and finishing Three.js browser games. Routes work across the sibling threejs-* skills for gameplay, graphics, UI, 3D/image/audio asse…