AI Agent Skills

A fast, high-quality neural vocoder.

The Naomi Project is an open source, technology agnostic platform for developing always-on, voice-controlled applications!

Python library for designing and training your own Diffusion Models with PyTorch

Machine Learning applied to sound

Google TTS (Text-To-Speech) for node.js

General Speech Restoration

Unofficial PyTorch Implementation of UnivNet Vocoder (https://arxiv.org/abs/2106.07889)

Use when driving Niagara VFX from C++: spawning a system, overriding User parameters, binding data interfaces, sending gameplay data through Niagara Data Channels, pooli…

Use when playing Level Sequences from C++, building cutscenes or in-game camera moments, binding actors to sequence tracks at runtime, wiring Sequencer event tracks, or…

Provider-independent audio mixing and mastering direction for AI agents finishing generated videos, ads, trailers, explainers, podcasts, recuts, avatar clips, music vide…

Provider-independent captions and media accessibility direction for AI agents producing or finishing generated videos, ads, social clips, explainers, avatar videos, docu…

基于标贝数据继续训练，同时对原本的FastSpeech2模型做了改进，引入了韵律表征以及韵律预测模块，使中文发音更生动且富有节奏

Implementation of Spear-TTS - multi-speaker text-to-speech attention network, in Pytorch

Use when playing, mixing or debugging sound in Unreal Engine — one-shot SFX, looping ambience, music, dialogue or procedural audio. Also use when the user mentions 'UAud…

[ACL 2025 Main] ControlSpeech: Towards Simultaneous Zero-shot Speaker Cloning and Zero-shot Language Style Control With Decoupled Codec

ttslearn: Library for Pythonで学ぶ音声合成 (Text-to-speech with Python)