Burst accelerated mesh simplification.

On-device TTS model by Neuphonic

About Build minimal ONNX Runtime with GitHub Actions

VoiceStar: Robust, Duration-controllable TTS that can Extrapolate

PyTorch implementation of Miipher-2 [2025] which is a speech restoration model by Google DeepMind

A Survey of Spoken Dialogue Models (60 pages)

A program that automatically transcribes karaoke MIDI scores and lyrics, along with another program to play them

Privacy-focused local‑first platform that scales.

Real-time & local speech-to-text server.

Frontier Open-Source Text-to-Speech

ncnn android piper the fast and local neural text-to-speech engine

KawaiiPhysics : Simple Bone Physics for UnrealEngine 4 & 5

Unity Editor integration with Model Context Protocol (MCP) enabling AI assistants like Claude to interact with Unity projects. Features a TypeScript MCP server and C# Unity plugin with extensible c…

A Tensor Computation Library with JIT Compilation

A real-time and light-weight software for generation of non-linguistic behaviors (turn-taking, backchannel, and head-nodding) in conversational AIs

State-of-the-art TTS model under 25MB 😻

tsumiki

Prominence-Based Segmentation with Clustering for Word Discovery and Lexicon Learning in Python

Browser-based visual editor for building WebGL, WebGPU, WebXR apps

PyTorch native quantization and sparsity for training and inference

Simplify your onnx model (Support for Python 3.12/3.13 & Linux aarch64 pre-built wheels)

Fast and local neural text-to-speech engine

uLoopMCP enables AI to autonomously compile, test, debug, and manipulate Unity projects. It bridges Unity Editor with AI coding assistants (Claude Code, Cursor, GitHub Copilot, Windsurf) using Mode…

PyTorch implementation of Audio Flamingo: Series of Advanced Audio Understanding Language Models

Survey of audio language models

Fine-tuning Moshi/J-Moshi on your own spoken dialogue data